Alexander Felfernig, Juha Tiihonen, and Paul Blazek, Editors Proceedings of the 1st International Workshop on Personalization & Recommender Systems in Financial Services April 16, 2015, Graz, Austria Alexander Felfernig, Graz University of Technology, Austria
Juha Tiihonen, University of Helsinki, Finland
Paul Blazek, cyLEDGE, Austria
Martin Stettinger, Graz University of Technology, Austria Personalization and recommendation technologies provide the basis for applications that are tailored to the needs of individual users. These technologies play an increasingly important role for financial service providers. The selection of papers of this year’s workshop demonstrates the wide range of techniques including contributions on knowledge-based recommender systems, case-based reasoning, knowledge interchange, psychological aspects of recommender systems in financial services, MediaWiki-based recommendation technologies, smart data analysis and big data, and campaign customization. The workshop is of interest for both, researchers working in the various fields of personalization and recommender systems as well as for industry representatives. It provides a forum for the exchange of ideas, evaluations, and experiences. As such, this year's workshop on “Personalization & Recommender Systems in Financial Services” aims at providing a stimulating environment for knowledge-exchange among academia and industry and thus building a solid basis for further developments in the field.
Alexander Felfernig, Juha Tiihonen, and Paul Blazek Smart Data Analysis for Financial Services (invited talk) Mathias Bauer Conflict Management in Interactive Financial Service Selection Alexander Felfernig and Martin Stettinger An Integrated Knowledge Engineering Environment for Constraint-based Recommender Systems Stefan Reiterer A Personal Data Framework for Exchanging Knowledge about Users in New Financial Services Beatriz San Miguel, Jose M. del Alamo and Juan C. Yelmo Human Computation Based Acquisition Of Financial Service Advisory Practices Alexander Felfernig, Michael Jeran, Martin Stettinger, Thomas Absenger, Thomas Gruber, Sarah Haas, Emanuel Kirchengast, Michael Schwarz, Lukas Skofitsch, and Thomas Ulz Case-based Recommender Systems for Personalized Finance Advisory (invited talk) Cataldo Musto and Giovanni Semeraro PSYREC: Psychological Concepts to enhance the Interaction with Recommender Systems Gerhard Leitner 1—2 3—10 11—18 19—26 27—34 35—36 Smart Data Analysis for Financial Services
Mathias Bauer1 Abstract.1 This talk addresses opportunities for the application of intelligent data analysis techniques at various stages of the value added chain for financial services. After introducing some basic notions and explaining the fundamental steps of data mining, we will have a closer look at various recent and ongoing projects and discuss issues of practical relevance such as data quality and expert knowledge. The talk concludes with some remarks on the potential impact of new developments, e. g. in the context of Big Data. Data mining – this notion will be used as a synonym for all kinds of smart data analysis – is a complex process that aims at turning raw data into actionable knowledge (see Figure 1 which depicts a standard process model). We will introduce the basic notions, discuss the various steps and in particular have a closer look at the choices to be made and a few pitfalls to be avoided.
In particular, we will address the crucial aspects of how to choose an appropriate modeling approach and how to assess the quality of a solution found by a data analyst.
We show that in many cases it is not a good idea to simply apply the data analyst's favorite modeling technique. Instead we describe the various dimensions of such a choice and encourage the end users of a data analysis to clearly state their requirements. 2
Data Analysis can (and should) play a central role at various stages of the value added chain in the financial industry. In the following we will have a closer look at some relevant activities in this context. 2.1
Scoring and rating processes are at the heart of financial industry. Here we will demonstrate an approach to appraise vessels as typical representatives of real economic goods which form an important class of investments. There are numerous aspects that can make a customer particularly interesting to a company – his/her interest in certain products, credit-worthiness and default risk, churn rate etc. We describe an integrated approach to identify these individuals that reduces the marketing effort required while simultaneously improving the company's insight into their customer base and the quality of customer contact.
In particular, we will see how the modeling technique applied affects the usefulness of the analytical findings. From an abstract point of view, selecting a relevant set of stocks is similar to the previous task as it mainly involves segmentation and classification efforts. However, we will see that data preprocessing in this case is significantly more complex and requires some advanced expert knowledge. 3
Big data is more than a buzzword – even if it's not the silver bullet for all problems ahead. We will discuss various techniques and attempts to commercially make use of huge, largely unstructured data sets and briefly discuss potential future applications.
Page 2
and
Abstract. Knowledge-based systems are often used to support
search and navigation in a set of financial services. In a typical
process users are defining their requirements and the system selects and
ranks alternatives that seem to be appropriate. In such scenarios
situations can occur in which requirements can not be fulfilled and
alternatives (repairs) must be proposed to the user. In this paper we
provide an overview of model-based diagnosis techniques that can
be applied to indicate ways out from such a ”no solution could be
found” dilemma. In this context we focus on scenarios from the
domain of financial services.
1
Knowledge-based systems such as recommenders [
The mentioned systems have the potential to improve the
underlying business processes, for example, by reducing error rates in the
context of order recording and by reducing time efforts related to
customer advisory. Furthermore, customer domain knowledge can
be improved by recommendation and configuration technologies;
through the interaction with these systems customers gain a deeper
understanding of the product domain and – as a direct consequence
– less efforts are triggered that are related to the explanation of basic
domain aspects. For a detailed overview of the advantages of
applying such technologies we refer the reader to [
When interacting with knowledge-based systems, situations can occur where no recommendation or configuration can be identified.
In order to avoid inefficient manual adaptations of requirements, techniques can be applied which automatically determine repair actions that allow to recover from an inconsistency. For example, if a customer is interested in financial services with high return rates but at the same time does not accept risks related to investments, no corresponding solution will be identified.
There are quite different approaches to deal with the so-called no solution could be found dilemma – see Table 1. In the context of 1 Applied Software Engineering, Institute for Software Technology,
Graz University of Technology, Austria, email: ffelfernig,
stettingerg@ist.tugraz.at.
this paper we will focus on the application of the concepts of
modelbased diagnosis [
Beside the automated testing and debugging of inconsistent
knowledge bases, model-based diagnosis is also applied in situations
where the knowledge base per se is consistent but a set of customer
requirements induces an inconsistency. Felfernig et al. [
A couple of different approaches to the determination of personalized diagnoses for inconsistent requirements have been proposed.
DeKleer [
Different types of knowledge-based systems have already been applied to support the interactive selection and configuration of fi
Topic
Foundations of model-based diagnosis Conflict detection and model-based diagnosis of inconsistent
constraint satisfaction problems (CSPs)
Regression testing and automated debugging of configuration knowledge bases using model-based diagnosis (breadth-first search)
Identification of minimal diagnoses for user requirements for the
purpose of consistency preservation (breadth-first search) Identification of preferred minimal conflict sets on the basis of a
divide-and-conquer based algorithm (QUICKXPLAIN) Identification of representative explanations (each existing diagnosis element is contained in at least one diagnosis of the result set)
Identification of personalized diagnoses on the basis of
recommendation algorithms
Probability based identification of leading diagnoses Identification of preferred minimal diagnoses on the basis of a
divide-and-conquer based algorithm (FASTDIAG)
Preferred minimal diagnoses for SAT based knowledge representations
Reiter 1987 [
et al. 1992 [
Junker 2004 [
[
DeKleer 1990 [
The major focus of this paper is to provide an overview of techniques that help to recover from inconsistent situations in an automated fashion. In this context we show how inconsistencies can be identified and resolved. The major contributions of this paper are the following: (1) we provide an overview of error identification and repair techniques in the context of financial services recommendation and configuration. (2) We show how diagnosis and repair techniques can be applied on the basis of different knowledge representations (CSPs as well as table-based representations). (3) We provide an outlook of major issues for future work.
The remainder of this paper is organized as follows. In Section
2 we introduce basic definitions of a constraint satisfaction problem
(CSP) and a corresponding solution. On the basis of these
definitions we introduce a first working example from the financial
services domain. Thereafter (in Section 3) we introduce a basic
definition of a diagnosis task and show how diagnoses and repairs for
inconsistent user requirements can be determined. In Section 4 we
switch from constraint-based to table-based knowledge
representations where (personalized) solutions are determined on the basis of
conjunctive queries [
Constraint-based Representations
Constraint Satisfaction Problems (CSPs) [
Definition 1 (Constraint Satisfaction Problem (CSP) and Solution). A constraint satisfaction problem (CSP) can be defined as a triple (V; D; C) where V = fv1; v2; :::; vng represents a set of variables, dom(v1); dom(v2); :::; dom(vn) represents the corresponding variable domains, and C = fc1; c2; :::; cmg represents a set of constraints that refer to corresponding variables and reduce the number of potential solutions. A solution for a CSP is defined by an assignment A of all variables in V where A is consistent with the constraints in C.
Usually, user requirements are interpreted as constraints CREQ = fr1; r2; :::; rqg where ri represent individual user requirements. In this paper we assume that the constraints in C are consistent and inconsistencies are always induced by the constraints in CREQ. If such a situation occurs, we are interested in the elements of CREQ which are responsible for the given inconsistency.
On the basis of a first example we will now provide an overview of
diagnosis techniques that can be used to recover from such
inconsistent situations. An example of a CSP in the domain of financial
services is the following. For simplicity we assume that each
variable has the domain flow, medium, highg.
of HSDAG construction (an example is depicted in Figure 1). In the
context of our example of C and CREQ, a first minimal conflict set
that could be returned by an algorithm such as QUICKXPLAIN [
V = fav; wr; rrg dom(av) = dom(wr) = dom(rr) = flow; medium; highg C = fc1 : :(av = high^wr = high); c2 : :(wr = low^rr = high); c3 : :(rr = high ^ av = high)g An overview of the variables of this CSP is given in Table 2.
variable av wr rr description availability willingness to take risks expected return rate ri 2 CREQ r1 : av = high r2 : wr = low r3 : rr = high
In addition to this basic CSP definition we introduce an example set of customer requirements CREQ = fr1 : av = high; r2 : wr = low; r3 : rr = highg which is inconsistent with the constraints defined in C. On the basis of this simplified financial service knowledge base defined as a CSP we will now show how inconsistencies induced by customer requirements can be identified and resolved. 3
Diagnosis & Repair of Inconsistent Constraints In our working example, the requirements CREQ and the set of constraints C are inconsistent, i.e., inconsistent(CREQ [ C). In such situations we are interested in a minimal set of requirements that have to be deleted or adapted such that consistency is restored.
Consistency resolution is in many cases based on the resolution of conflicts. In our case, a minimal conflict is represented by a minimal set of requirements in CREQ that have to be deleted or adapted such that consistency can be restored.
Definition 2 (Conflict Set). A conflict set CS is a subset of CREQ s.t. inconsistent (CS [ C). A conflict set is minimal if there does not exist another conflict set CS0 with CS0 CS. A minimal cardinality conflict set CS is a minimal conflict set with the additional property that there does not exist another minimal conflict CS0 with jCS0j < jCSj.
Minimal conflict sets can be determined on the basis of
conflict detection algorithms such as QUICKXPLAIN [
Definition 3 (Diagnosis Task and Diagnosis). A diagnosis task can be defined as a tuple (C; CREQ) where C represents a set of constraints in the knowledge base and CREQ represents a set of customer requirements. is a diagnosis if CREQ [C is consistent.
A diagnosis is minimal if there does not exist a diagnosis 0 with
0 . Furthermore, is a minimal cardinality diagnosis if there does not exist a diagnosis 0 with j 0j < j j.
A standard approach to the determination of diagnoses is based on
the construction of a hitting set directed acyclic graph (HSDAG) [
There are two possibilities of resolving CS1, either by deleting requirement r1 or by deleting requirement r3. If we delete r3 (see Figure 1), we managed to identify the first minimal diagnosis
1 = fr3g which is also a minimal cardinality diagnosis. The second option to resolve CS1 is to delete r1. In this situation, another conflict exists in CREQ, i.e., a conflict detection algorithm would return CS2 : fr2; r3g. Again, there are two possibilities to resolve the conflict (either by deleting r2 or by deleting r3). Deleting r3 leads to a diagnosis which is not minimal since fr3g itself is already a diagnosis. Deleting r2 leads to the second minimal diagnosis which is 2 = fr1; r2g.
The diagnoses 1 and 2 are indicators of minimal changes that need to be performed on the existing set of requirements such that a consistency between CREQ and C can be restored. The issue of finding concrete repair actions for the requirements contained in a diagnosis will be discussed later in this paper.
There can be quite many alternative diagnoses. In this context it
is not always clear which diagnosis should be selected or in which
order alternative diagnoses should be shown to the user. In the
following we present one approach to rank diagnoses. The approach we
sketch is based on multi-attribute utility theory [
Formula 1 can be used for determining the overall importance (imp) of a set of requirements (RS). The higher the importance the lower the probability that these requirements are element of a diagnosis shown to the customer. Requirement r3 has a high importance for customer 1, consequently, the probability that r3 is contained in a diagnosis shown to customer 1 is low.
imp(RS) = importance(RS) = r2RS weight(r) (1)
Formula 2 can be used to determine the relevance of a partial or complete (minimal) diagnosis, i.e., this formula can be used to rank weight(r1 : av = high) 0.1 0.3 diagnoses with regard to their relevance for the customer. The higher the relevance of a diagnosis, the higher the ranking of the diagnosis in a list of diagnoses shown to the customer.
rel( ) = relevance( ) = importa1nce( ) (2)
Tables 4 and 5 show the results of applying Formulae 1 and 2 to the customer preferences (weights) shown in Table 3. For customer 1 (see Table 4), diagnosis 2 = fr1; r2g has the highest relevance.
For customer 2 (see Table 5), diagnosis 1 = fr3g has the highest relevance. Consequently, diagnosis 2 is the first one that will be shown to customer 1 and diagnosis 1 is the first one that will be shown to customer 2.
diagnosis j
1 : fr3g 2 : fr1; r2g importance( j ) 0.7 0.3
On the basis of the relevance values depicted in Table 4, Figure 2
depicts a HSDAG [
The afore discussed approaches to diagnosis determination are
based on the construction of a HSDAG [
FASTDIAG is based on the principle of divide and conquer – see Figure 3: if a set of requirements CREQ is inconsistent with a corresponding set of constraints C and the first part fr1; r2; :::; rk=2g of CREQ is consistent with C then diagnosis search can focus on frk=2+1; :::; rkg, i.e., can omit the requirements in fr1; r2; :::; rk=2g.
A detailed discussion of FASTDIAG can be found in [
Determination of Repair Actions. Repair actions for diagnosis elements can be interpreted as changes to the originial set of requirements in CREQ in such a way that at least one solution can be identified. If we assume that CREQ is a set of unary constraints that are inconsistent with C and is a corresponding diagnosis, then a set of repair actions R = fa1; a2; :::; alg can be identified by the consistency check CREQ [ C where aj (a variable assignment) is a repair for the constraint rj if rj is in .
In this section we took a look at different approaches that support the determination of diagnoses in situations where a given set of requirements becomes inconsistent with the constraints in C. In the following we will take a look at an alternative knowledge representation where tables (instead of CSPs) are used to represent knowledge return rate p.a. (rr) 4.2 4.7 4.8 5.2 4.3 5.6 6.7 7.9 about financial services. Again, we will show how to deal with inconsistent situations. 4
Table-based Representations
In Section 3 we analyzed different ways of diagnosing inconsistent
CSPs [
The existence of a financial service in T that is able to fulfill all requirements can be checked by a relational query [CREQ]T where CREQ represents a set of selection criteria and T represents the corresponding product table.
An example query on the product table T could be [rr 5:5]T which would return the financial services f6,7,8g. For the query
[r1;r2;r3;r4]T there does not exist a solution. In such situations we are interested in finding diagnoses that indicate minimal sets of requirements in CREQ that have to be deleted or adapted in order to be able to identify a solution.
Definition 4 (Conflict Sets in Table-based Representations). A conflict set CS is a subset of CREQ s.t. [CS]T returns an empty result set. Minimality properties of conflict sets are the same as introduced in Definition 2.
A diagnosis task and a corresponding diagnosis in the context of table-based representations can be defined as follows.
Definition 5 (Diagnosis in Table-based Representations). A diagnosis task can be defined as a tuple (T ; CREQ) where T represents a product table and CREQ represents a set of customer requirements.
is a diagnosis if [CREQ ]T returns at least one solution. Minimality properties of diagnoses are the same as in Definition 3.
The requirements rj 2 CREQ are inconsistent with the items included in T (see Table 6), i.e., there does not exist a financial service in T that completely fulfills the user requirements in CREQ. Minimal conflict sets that can be derived for CREQ = fr1 : rr 5:5; r2 : rt = 3:0; r3 : acc = yes; r4 : bc = yesg are CS1 : fr1; r2g, CS2 : fr2; r3g, and CS3 : fr1; r4g. The determination of the corresponding diagnoses is depicted in Figure 4.
Diagnoses are determined in the same fashion as discussed in Section 2. Minimal diagnoses that can be derived from the conflict sets CS1; CS2; and CS3 are 1 : fr1; r2g, 2 : fr1; r3g and 3 : fr2; r4g (see Figure 4).
Again, the question arises which of the diagnoses has the highest relevance for the user (customer). Table 7 depicts the importance distributions for the requirements of our example. Based on the importance distributions depicted in Table 7 we can derive a preferred diagnosis (see Figure 5). Diagnosis 3 will be first shown to customer 1 since 3 has the highest evaluation in terms of relevance (see Formula 2). The first diagnosis shown to customer 2 is 2. diagnosis
j 1 : fr1; r2g 2 : fr1; r3g 3 : fr2; r4g
Loans: creditworthiness (cw), loan limit (ll), runtime in years (rt), and interest rate (ir). As a third example we introduce the domain of loans. The entries in Table 10 represent different loan variants that can be chosen by customers. Customers can specify their requirements on the basis of the variables depicted in Table 11. Furthermore, the different loan variants are characterized by their expected creditworthiness (cw), loan limit (ll), runtime in yrs. (rt), and interest rate (ir). These variables are basic elements of the definition of the following Constraint Satisfaction Problem (CSP).
variable ccw ils mpp irt pir
V = fccw, ils, mpp, irt, pir, cw, ll, rt, irg dom(ccw) = dom(cw) = f1,2,3g; dom(ils) = dom(ll) = float; dom(mpp) = float; dom(irt) = dom(rt) = integer; dom(pir) = dom(ir) = integer.
C = fc1 : ccw cw; c2 : ils ls; c3 : irt = rt; c4 : pir ir; c5 : see below; c6;7 : see belowg
Constraint c5 represents the entities of Table 10 in disjunctive normal form, for example, the first table row can be represented as basic constraint fcw = 1 ^ ll = 30:000 ^ rt = 5:0 ^ ir = 3%g.
The disjunct of all basic constraints is the disjunctive normal form.
Constraints c6;7 can be used to avoid situations where the periodical payments for a loan exceed the financial resources of the customer.
c6 : mpp costs(id) + ils rt
(3) c7 : costs(id) = ils ir(id) (rt(id2) + 1) (4)
For the purpose of our example let us assume that the customer has the following requirements: CREQ = fr1 : ccw = 3; r2 : ils = 30:000; r3 : irt = 6yrs:; r4 : pir = 4:5%g. Since the customer creditworthiness has been evaluated with 3, only three alternative loan variants are available (the ids 3,6,9). These variants are depicted in Table 12.
id 3 6 9 cw 3 3 3
The requirements CREQ include one minimal conflict set which
is CS1 : fr3; r4g. Consequently, there exist two different
possibilities to resolve the conflict: one possibility is to change the value for
the intended runtime (irt) from 6.0 years to 5.0 years and to keep the
preferred interest rate (pir) as is. The other possibility is to change
the preferred interest rate from 4.5% to 6% and to keep the intended
runtime as is. The overall loan costs related to these two alternatives
are depicted in Table 13. If the overall loan costs are a major criteria
then repair alternative 1 would be chosen by the customer, otherwise
– if the upper limit for periodical payments is strict – repair
alternative 2 will be chosen.
A major issue for interactive applications is to guarantee reasonable
response times which should be below one second [
Although the prediction quality of diagnoses significantly increases and numerous recommendation algorithms have already been evaluated, there is still a need for further advancing the state-of-theart in diagnosis prediction. One research direction is to focus on learning-based approaches that help to figure out which combination of a set of basic diagnosis prediction methods best performs in the considered domain. Such approaches are also denoted as ensemblebased methods which focus on figuring out optimal configurations of basic diagnosis prediction methods.
Efficient calculation and high predictive quality are for sure central issues of future research. Beyond efficiency and prediction quality, intelligent visualization concepts for diagnoses are extremely important. For example, the the context of group decision scenarios where groups of users are in charge of resolving existing inconsistencies in the preferences between group members, visualizations have to be identified that help to restore consistency (consensus) in the group as soon as possible. Such visualizations could focus on visualizing the mental state on individual group members as well visualizing the individual decision behavior (e.g., egoism vs. altruism).
Since CREQ is inconsistent with the constraints in C we could determine minimal diagnoses as indicators for possible adaptations in the requirements. A possible criteria for personalizing diagnosis ranking could be the costs related to a loan (see Formula 4). 7
Conclusions
In this paper we give an overview of existing approaches to
determine diagnoses in situations were no solution can be found. We first
provide an overview of existing related work and then focus on
basic approaches to determine diagnoses in the context of two
knowledge representation formalisms (constraint satisfaction and
conjunctive query based approaches). For explanation purposes we introduce
three different types of financial services as working examples (basic
investment decisions, selection of investment products, and loan
selection). On the basis of these examples we sketch the determination
of (preferred) diagnoses. Thereafter, we provide a short discussion of
open research issues which includes diagnosis efficiency, prediction
quality, and intelligent visualization.
Stefan Reiterer1
Abstract. Constraint-based recommenders support customers in
identifying relevant items from complex item assortments. In this
paper we present a constraint-based environment already deployed in
real-world scenarios that supports knowledge acquisition for
recommender applications in a MediaWiki-based context. This technology
provides the opportunity do directly integrate informal Wiki content
with complementary formalized recommendation knowledge which
makes information retrieval for users (readers) easier and less
timeconsuming. The user interface supports recommender development
on the basis of intelligent debugging and redundancy detection. The
results of a user study show the need of automated debugging and
redundancy detection even for small-sized knowledge bases.
1
Constraint-based recommenders support the identification of relevant
items from large and often complex assortments on the basis of an
explicitly defined set of recommendation rules [
Similar to the idea of Wikipedia to allow user communities to develop and maintain Wiki pages in a cooperative fashion, we introduce the WEEVIS2 environment, which supports the communitybased development of constraint-based recommender applications within a Wiki environment. WEEVIS has been implemented on the basis of MediaWiki3, which is an established standard Wiki platform.
Compared to other types of recommender systems such as
collaborative filtering [
email:stefan.reiterer@selectionarts.com 2 www.weevis.org. 3 www.mediawiki.org.
The user interface of the WEEVIS environment provides
intelligent mechanisms that help to make development and
maintenance operations easier. Based on model-based diagnosis techniques
[
The major contributions of this paper are the following. (1) on the basis of a working example from the domain of financial services, we provide an overview of the diagnosis and redundancy detection techniques integrated in the WEEVIS environment. (2) we report the results of an empirical study which analyzed the usability of WEEVIS functionalities.
The remainder of this paper is organized as follows. In Section
2 we discuss related work. In Section 3 we present an overview of
the recommendation environment WEEVIS and discuss the included
knowledge engineering support mechanisms. In Section 4 we present
results of an empirical study that show the need of intelligent
diagnosis and redundancy detection support. In Section 5 we discuss issues
for future work, with Section 6 we conclude the paper.
2
Based on original static Constraint Satisfaction Problem (CSP)
represenations [
A graphical recommender development environment for single
users is introduced in [
A Semantic Wiki-based approach to knowledge acquisition for
collaborative ontology development is introduced in [
A first approach to a conflict-directed search for hitting sets in
inconsistent CSP definitions was introduced by Bakker et al. [
The WEEVIS Environment
In it’s current version, WEEVIS supports scenarios where user
requirements can be defined in terms of functional requirements [
The corresponding recommendations (solutions) are retrieved from
a predefined set of alternatives (also denoted as item set or product
catalog). Requirements are checked with regard to their consistency
with the underlying item set (consistency is given if at least one
solution could be identified). If no solution could be found, WEEVIS
repair alternatives are determined on the basis of direct diagnosis
algorithms [
WEEVIS is based on the idea that a community of users cooperatively contributes to the development of a recommender knowledge base. The environment supports knowledge acquisition processes on the basis of tags that can be used for defining and testing recommendation knowledge bases. Using WEEVIS, standard Wikipedia pages can be extended with recommendation knowledge that helps to represent domain knowledge in a more accessible and understandable fashion. The same principles used for the developing Wikipedia pages can also be used for the development and maintenance of recommender knowledge bases, i.e., in the read mode recommenders can be executed and in the view source mode recommendation knowledge can be defined and adapted. This way, rapid prototyping processes can be supported in an intuitive fashion (changes to the knowledge can be immediately experienced by switching from the view source to the read mode). In the read mode, knowledge bases can as well be tested and in the case of inconsistencies (some test cases were not fulfilled within the scope of regression testing) corresponding diagnoses are shown to the user. The website www.weevis.org provides a selection of different recommender applications (full list, list of most popular recommenders, and recommenders that have been defined previously) that can be tested and extended. Most of these applications have been developed within the scope of university courses on recommender systems (conducted at four Austrian universities). WEEVIS recommenders can be integrated seamlessly into standard Wiki pages, i.e., informally defined knowledge can be complemented or even substituted with formal definitions.
In the following we will present the concepts integrated in the WEEVIS environment on the basis of a working example from the domain of financial services. In such a recommendation scenario, a user has to specify his/her requirements regarding, for example, the expected capital guarantee level of the financial product or the amount of money he or she wants to invest. A corresponding WEEVIS user interface is depicted in Figure 1 where requirements are specified on the left hand side and the corresponding recommendations are displayed in the right hand side.
Each recommendation (item) has a corresponding support value that indicates the share of requirements that are currently supported by the item. A support value of 100% indicates that each requirement is satisfied by the corresponding item. If the support value is below 100%, corresponding repair alternatives are shown to the user, i.e., alternative answers to questions that guarantee the recommendation of at least one item (with 100% support).
Since WEEVIS is a MediaWiki-based environment, the definition of a recommender knowledge base is supported in a textual fashion on the basis of a syntax similar to MediaWiki. An example of the definition of a (simplified) financial services recommender knowledge base is depicted in Figure 2. Basic syntactical elements provided in WEEVIS will be introduced in the next subsection. Constraint-based recommendation requires the explicit definition of questions and possible answers, items and their properties, and constraints (see Figure 2).
In WEEVIS the tag &QUESTIONS enumerates the set of user requirements where, for example, pension specifies whether the user wants a financial product to support his private pension plan [yes, no] and maxinvestment specifies the amout of money the user wants to invest. Furthermore, payment represents the frequency in which the payment should be done [once, periodical], payout specifies the frequency the customer gets a payout from the financial product (out of [once,monthly]), and guarantee the expected capital guarantee [low, high].
An item assortment can be specified in WEEVIS using the &PRODUCTS tag (see Figure 2). In our example, the item (product) assortment is specified by values related to the attributes name; guaranteep, the capital guarantee the product provides; payoutp, the payout frequency of the product; mininvestp the minimal amount of personal data in the PeDF. It interacts with the User Manager module to obtain the user consent.
Collector. This module is in charge of obtaining personal data from external data sources, checking user authorization. It can also include crawlers’ components that get personal data from public data sources.
Registry. It allows the PeDF to store pointers to external personal data that the PeDF is able to recover from data sources.
Generator. It comprises a set of components that allow PeDF to obtain user models from personal data. These implement different techniques of user modelling to uncover user needs, preferences, interests, etc.
User Data Store. It is a central repository that stores the personal data that is obtained from external data sources or by the Generator module. It contains different interfaces that allow the updating and refreshing of personal data.
Retriever. This module is in charge of communicating with data consumers who are interested in obtaining personal data and user models of a specific user. It interacts with the User Manager module to check user consent and with the Registry or User Data Store to retrieve the personal data requested. 4.1
External data sources We have considered two private data sources for PeDF validation: PosdataP2P service, and the social network Facebook.
PosdataP2P service [
The USC is a smart card issued by over 300 universities in collaboration with Santander Bank. It is used by 7.8 million people worldwide to access university services, such as libraries, control access (for example, to computers, campus, sports pavilions, etc.), electronic signature, discounts at retailers, etc. It can be also used to gain access to Santander Bank financial services, working as a credit/debit card linked to the holder’s saving account.
To use PosdataP2P service, USC holders have to activate the service first, providing their USC information. Then, they choose the social channels that they want to use to carry out financial transactions. Having done that, students can start making financial transactions by simply posting messages to their friends within their enabled social channels (Figure 3).
FRAMEWORK VALIDATION We have validated the PeDF in a banking scenario which considers a person-to-person payment service namely PosdataP2P, and the social network Facebook as data sources. Moreover, it includes a financial service called FriendLoans that uses user models from the PeDF to offer its users recommendations about microloans. It is an integration effort to provide user models that fulfill individual business needs of third entities. We have focused our work on a centralized integration based on semantic technologies, which improve the user modelling process. Moreover, we have validated the PeDF with five beta testers from our research group.
Figure 2 represents our validation to the PeDF. Here, we can observe the two private data sources (PosdataP2P and Facebook), the data consumer (MicroLoans), the user and the main PeDF modules that we have validated: User Manager, Collector, User Data Store, Generators, and Retriever.
A Personal Socio-Economic Network The PeDF validation applies a centralized approach where personal data obtained from external data sources are stored in a central repository. Specifically, it is based on a semantic modelling and storing, and an ontology, namely the Personal Socio-Economic Network (PSEN).
The PSEN represents the exchange of money between people and user social data. We have considered the reusing of existing ontologies, which is a must to allow semantic and syntactic interoperability. Thus, we have identified the FOAF ontology as the best alternative for representing people in a social network context and the SUMO’s financial ontology (using the OWL version) for representing the financial concepts. We have also extended them and linked the different socio-economic concepts.
The nomenclature that we have used to represent the PSEN concepts is based on SUMO terms so it can be easily related to the upper ontology.
Briefly, the PSEN includes the main terms to describe people, the relationships between them, and the financial data and activities carried out between them (Figure 4). We represent people as the Person class from FOAF and we use the corresponding FOAF properties to describe their user’s demographic information: firstName, lastName, gender, age, birthday, and mbox (omitted in Figure 4 for the sake of simplicity). We also made use of the Online Account class from FOAF that allows the modelling of different web identities or online accounts of a person. We have extended it to include online payment and banking accounts. The former is devoted to service providers that allow users to carry out payment operations through the Internet, such as PosdataP2P service. It has associated a BankCard or a Financial Account class from the SUMO financial ontology that denotes where the payment will become effective. These classes have a relationship (namely, cardAccount) since a BankCard is always associated with a FinancialAccount. On the other hand, the Online Banking Account class represents online banking services including financial institutions, such as Santander Bank.
To model user economic activities, we have defined a SocialInteraction class within the PSEN ontology. It includes three main properties: timestamp, channel and patient. The timestamp and channel properties indicate when and where the social interaction happens respectively, and patient designates an Entity that participates in the social interaction, i.e. the money exchange.
The SocialInteraction class also has two subclasses: Transaction and Communication that have Payment and Request subclasses correspondingly. These are related to a hasPayment link that indicates whether a request for money has been paid.
In Figure 4, the rounded rectangles characterize the main concepts and the edges indicate the relationships between two classes. We have distinguished the terms of the different ontologies with darker rectangles indicated in the legend of the figure.
Knowledge retrieval
We have validated the retrieval of user knowledge through the
FriendLoans service, which is based on friendsourcing [
Generating a list of friends for a user requires user models that are unknown to FriendLoans, but can be retrieved from the PeDF.
The PeDF has incorporated two mechanisms that allow data consumers to ask for user financial relationships and other banking information, all with the consent of the user. Specifically, the PeDF abstracts a set of SPARQL sentences and calls the reasoners which obtain and derive additional knowledge from the PSEN.
The SPARQL sentences obtain personal data and user models directly from the PSEN which can be used by FriendLoans. This information does not derive facts or inferences under the PSEN data, just data contained in it. For example, the list of friends for a specific user, if a person has carried out payments or requests for money, if a person has received money, if a person has requests for money and no associated payments, etc.
As regards the reasoners, they include the mechanisms that allow the extration of derived data. For this, we have implemented four custom rules that detect: 1) whether a user knows another user
A; 2) whether a user owes money to a user A; 3) whether a user has received a payment greater than X euros; and 4) whether a user has requests for money with greater amount of money than Y euros. In the rules, the user A and the amount of money X and Y can be indicated by FriendLoans to give recommendations to its users. In this way, for the example shown in Figure 5, A will be the authenticated user Maria who needs money from her friends, X and Y could be at least 200€ or the amount wanted by FriendLoans.
The results obtained from executing these rules are a set of users that fulfill all conditions. This set is not ordered since the order of execution of the rules is not predictable in the reasoner. However, the PeDF has implemented an algorithm that orders the results including tags that indicate the prioritization.
The next program listing shows an example of a rule that tags the results as the most important ones (it is indicated by the tag isFirstFor) for the user Maria (specified by the second line of the rule). The conditions of the rule are: 1) a user who has debts with Maria (defined in a function called hasDebtWith), and 2) a user has not requested an amount of money greater than 5€ with other people (defined in a function called possibleProblem). [isFirst: (?Maria psen:isTarget “true”^^xs:Boolean) (?person psen:hasDebtWith psen:Maria) noValue(?ecAct psen:possibleProblem “true”^^xs:Boolean) -> (?person psen:isFirstFor ?Maria)] 4.4
Identity management and privacy We have based our identity management infrastructure on OAuth 2.0, as it has become the de facto standard to gain access to personal data on the Web. The User Manager includes the component that manages the interaction with external sites.
Users can currently link their accounts on the PosdataP2P service and Facebook to the PeDF. The process works as follows: when a user activates a data source (i.e. Facebook), he is then redirected to the service provider site to grant the PeDF the required level of authorization. If successful, the data source delivers a token that allows access to the user profile.
As regards privacy, the PeDF has been designed to observe European privacy and data protection principles following a privacy-by-design approach. The User Manager is also the key component here, since it provides users with an identity and privacy dashboard allowing them to 1) grant/revoke consent to the collection, processing and disclosure of their personal data, 2) check the PeDF privacy policies, 3) manage the personal data known and stored by the PeDF, their sources, and the details on the disclosures to third parties as well as exercising their right to access, rectify, erase or block personal data. At the same time, the User Data Store implements security safeguards to avoid and mitigate privacy threats derived from malicious attackers or unwitting users. Finally, as regards the data minimization principle, the use of reasoners allows third parties to be limited and allows justified users to be able to query and retrieve that specified and agreed to by the data subject. 5
RELATED WORK
The PeDF is an ambitious solution that covers four main
technological challenges related to personal data: collection,
integration, retrieval, and identity and privacy management. These
have been widely analyzed separately over time in different
contexts, and we can find many researchers addressing each of
them in depth. For example, the previously cited literature [
We can find aligned systems that attempt to solve the same issues
as the PeDF in the personal data context. For example, the
socalled data brokers [
On the other hand, there are also specialized systems, namely
Generic User Modelling Systems [
However, they focus on the reuse of technological user modelling
components rather on the reuse of the personal data and user
models themselves. Finally, there are solutions referred as Personal
Data Store, Personal Data Locker, or Personal Data Vault that
roughly describe the same concept. Generally, these solutions are
based on a central place where the user can save and manage all
their personal data, including data such as text, passwords, images,
video or music [
To summarize, the aforementioned solutions are rather diverse from one another, and each of them focuses on a main objective (i.e., personal data collection, identity management, and data storage). Our work is an integration effort to provide an end-to-end solution that aims at incorporating the best solutions for each issue.
Our first approach is based on integrating social and financial data.
To the best of our knowledge, this is the first effort in this context. 6
CONCLUSIONS AND FUTURE WORK In this paper we have presented a comprehensive framework intermediating between users and organizations to support the seamless integration of personal data from several, distributed sources and generating advanced knowledge on users, to be shared with interested third parties, all supervised by the users who control and manage the flow of their personal data. The framework includes components for personal data collection, integration, and retrieval, as well as users’ identity and privacy management.
10 http://personal-clouds.org
The framework has been validated in a financial context, integrating social information from Facebook and a person-toperson payment service, to generate knowledge useful for a personal lending application.
Our future work includes advancing on the design of the privacy-preserving elements required to minimize the personal information retrieved by the data consumers while keeping it useful enough to fit their business needs. These developments will comprise advanced privacy enhancing technologies for attributebased credentials and database privacy.
ACKNOWLEDGEMENTS This work is part of the Center for Open Middleware (COM), a joint technology center created by Universidad Politécnica de Madrid, Banco Santander and its technological divisions ISBAN and PRODUBAN.
Alexander Felfernig1 and Michael Jeran1 and Thomas Absenger1 and Thomas Gruber1 and Sarah Haas1
Michael Schwarz1 and Lukas Skofitsch1
Martin Stettinger1 and
and Emanuel Kirchengast1
and Thomas Ulz1
and
Abstract. Knowledge-based recommenders support an easier
comprehension of complex item assortments (e.g., financial services
and electronic equipment). In this paper we show (1) how such
recommenders can be developed in a Human Computation based
knowledge acquisition environment (PEOPLEVIEWS) and (2) how
the resulting recommendation knowledge can be exploited in a
competition-based e-Learning environment (STUDYBATTLE).
1
Knowledge-based recommenders [
In this paper we focus on constraint-based recommenders, i.e., recommenders that are based on explicit recommendation rules (constraints). The development of such recommenders is often a timeconsuming and error-prone process which can be primarily explained by the knowledge acquisition bottleneck: in the formalization of product domain and recommendation knowledge, misunderstandings can occur and as a result knowledge engineers encode this knowledge in an unintended fashion. The more recommenders have to be developed and maintained the higher the risk that the organization runs into a scalability problem where additional resources are needed to be able to perform knowledge engineering and maintenance.
An alternative to the hiring of additional staff for development and maintenance of recommendation knowledge bases is to change the underlying knowledge engineering paradigm. The idea of PEOPLEVIEWS is to engage domain experts more deeply into knowledge engineering tasks. We do not want to ”convert” them into technical experts but to define basic tasks (micro tasks) that are easy to understand and complete even for domain experts without the corresponding technical expertise. Micro tasks completed by users pro1 Applied Software Engineering, Institute for Software Technology, Graz University of Technology, Austria, email: ffelfernig, mjeran, stettingerg@ist.tugraz.at, fthomas.absenger, th.gruber, sarah.haas, emanuel.kirchengast, michael.schwarz, lukas.skofitsch, thomas.ulzg@student.tugraz.at. 2 The terms item and product are used synonymously throughout the paper. vide knowledge chunks that can be aggregated into a PEOPLEVIEWS recommender knowledge base.
The resulting PEOPLEVIEWS recommenders support customers (and especially in the financial services domain also sales representatives) in finding products that fit their wishes and needs. Using such a recommender, items are retrieved within the scope of a dialog (these systems are often also denoted as conversational) where users articulate their requirements and the system tries to identify corresponding solutions. Major advantages of such systems are reduced error rates in the phase of order acquisition, more time that can be invested in contacting new customers due to fewer errors, more satisfied customers, and also pre-informed customers due to the fact that recommender applications can be made publicly available.
Knowledge-based recommender systems have been applied in
various item domains – due to the diversity of applications, we can
only give some examples of applications of these systems. In the
financial services domain, for example, the following applications of
knowledge-based recommendation technologies are reported in the
literature. Felfernig et al. [
Time savings are reported as one of the major improvements directly
related to the application of recommendation technologies. Another
application of knowledge-based technologies in financial services is
presented by Fano and Kurth [
Felfernig et al. [
4 www.mediawiki.org.
In PEOPLEVIEWS, principles of Human Computation [
The idea of Human Computation is to let persons perform tasks in
which they are better than computers, for example, the identification
of product properties from a website. In the context of knowledge
base development and maintenance the idea is to let domain experts
perform tasks they are much better in compared to knowledge
engineers who typically have less knowledge about the product domain
and thus relieve the work of knowledge engineers. MATCHIN [
The major contributions of this paper are the following. First, we show how financial service recommender knowledge bases can be developed by a community of domain experts. Second, we sketch how such knowledge bases can also be exploited for teaching advisory practices on the basis of games (STUDYBATTLE environment).
Third, we provide a discussion of major issues for future research.
The remainder of this paper is organized as follows. In Section 2 we introduce basic concepts of Human Computation based knowledge construction. To give an impression of the PEOPLEVIEWS and the STUDYBATTLE user interface, we present example screenshots in Section 3. Preliminary results of empirical evaluations are shortly discussed in Section 4. In Section 5 we provide an overview of issues for future work. We conclude the paper with Section 6. 2
Developing PEOPLEVIEWS Recommenders The PEOPLEVIEWS environment supports two basic modes of interaction. First, recommender applications can be created in the modeling mode and second, the applications can be executed in the recommendation mode. In this section we discuss different tasks to be performed in order to create a PEOPLEVIEWS recommender. Table 1 provides an overview of the users of our working example. These users will jointly develop a PEOPLEVIEWS recommender.
user Andrea Mary
Luc Torsten
pwd **** ***** ****** ****
Table 2 contains an overview of items (financial services) that are used in our working example. The Investment Funds (A and B) have a higher risk of loss and require that customers have a high willingness to take risks, otherwise these services will not be recommended.
Building Loan, Bond, and Savings Book are lower-risk items. In the current version of PEOPLEVIEWS, items can be characterized by additional item attributes, however, these attributes are not used by recommendation rules constructed from micro contributions.
In PEOPLEVIEWS, user requirements reqi 2 REQ are specified as assignments of user attributes. For our financial services recommender we define a set of user attributes which are enumerated in Table 3. In the current version of the system, user attributes are defined by the creators of a recommender application, i.e., attribute definitions can not be extended by other users who contribute to the further id 1 2 3 4 5
item name Investment Fund A Investment Fund B
Building Loan
Bond
Savings Book development of the application on the basis of micro tasks.
user attribute goal (gl) runtime (rt) risk (ri) question to user What are your personal goals?
When is the money needed? Preparedness to take risks?
attribute domain fStudies, Pension, Speculation,
Car, House, World trip, novalg fin 1 year, in 2 years, in 3-5 years, in 5-10 years, in 10-20 years, in more than 20 years, novalg flow, medium, high, novalg
In the PEOPLEVIEWS recommendation mode, user attributes can be used to specify user (customer) requirements reqi 2 REQ. In the modeling mode, user attributes represent a central element of a micro task: given a certain item, users are asked to estimate which values of user attributes are compatible with the item, i.e., are a criteria for selecting and recommending the item. The evaluation of items with regard to user attributes is the central micro task implemented in the current PEOPLEVIEWS prototype. A detailed evaluation of the example items (Table 2) regarding the user attributes goal, runtime, and risk is provided in Table 4.
Each row of Table 4 specifies a so-called user-specific filter
constraint [
In order to derive recommendation-relevant filter constraints
(recommendation rules) [
Table 5 includes the complete set of recommendation-relevant filter constraints (recommendation rules). Exactly these conditions are applied by PEOPLEVIEWS to determine recommendations for a user. In PEOPLEVIEWS, each item has exactly one related recommendation-relevant filter constraint; each such filter constraint is represented by one row in Table 5. The general logical representation of a recommendation-relevant filter constraint f for an item
is shown in Formula 1. In this context, values( ; u) is the set of Investment Fund A ( 1)
goal Investment Fund A ( 1) Investment Fund A ( 1) Investment Fund B ( 2) Investment Fund B ( 2)
Building Loan ( 3) Building Loan ( 3) Building Loan ( 3) Savings Book ( 5) Savings Book ( 5) in 5-10 years, in 10-20
years in 5-10 years, in 10-20
years in 5-10 years, in 10-20
years in 3-5 years, in 5-10 years,
in 10-20 years in 3-5 years, in 5-10 years,
in 10-20 years in 5-10 years, in 10-20
years in 5-10 years in 5-10 years in 2 years, in 3-5 years, in
5-10 years in 1 year, in 2 years, in 3-5
years, in 5-10 years in 1 year, in 2 years, in 3-5 years, in 5-10 years risk high high high high low low
user Andrea
Luc Mary Torsten
Luc Mary Andrea
Luc Mary Andrea Torsten
u2U supported domain values of user attribute u 2 U (see Table 4). The constant noval denotes the fact that no value has been selected for the corresponding user attribute.
f ( ) : ^ u 2 values( ; u) [ fnovalg ! include( ) (1)
For each pair ( ; val 2 values( ; u)), PEOPLEVIEWS determines a corresponding support value (see Formula 2). In this context, occurrence( ; val) denotes the number of times, value val occurs in a user-specific filter constraint for item and occurrence( ) denotes the number of times an item is referred in a user-specific filter constraint. For example, support( 1; Studies) = 13 .
support( ; val) = occurrence( ; val) occurrence( ) (2)
The complete set of support values is depicted in Table 6. In PEOPLEVIEWS, an item can have an associated rating (rating( )) which represents an item evaluation with regard to quality and related services. Such a rating can be determined, for example, by calculating the average of the individual user item ratings.5 For simplicity, we do not take into account user ratings in the utility function discussed below (see Formula 3).
Depending on the requirements articulated by the current user (see, e.g., Table 7), PEOPLEVIEWS determines and ranks a set of relevant items as follows. First, recommendation-relevant filter constraints are applied to pre-select items that fulfill the user requirements REQ = freq1; req2; :::; reqkg. In our example, the set fInvestment Fund A, Building Loang would be selected by the recommendation-relevant filter constraints (see Table 5). item name
(id) Investment Fund A ( 1) Investment Fund B ( 2)
Building Loan ( 3)
Investment Fund A ( 1) Investment Fund B ( 2) Building Loan
( 3)
goal in 5-10 years, in 10-20
years in 3-5 years, in 5-10 years,
in 10-20 years in 5-10 years, in 10-20
years in 2 years, in 2-5 years, in
5-10 years in 1 year, in 2 years, in 3-5 years, in 5-10 years risk high low
The determined recommendation set must be ranked before being presented to the user. In PEOPLEVIEWS, item ranking is based on the following utility function (see Formula 3). The utility of each item is derived from the support values of individual requirements (see Formula 2). req2REQ support( ; req) (3)
The item ranking of our working example as a result of applying Formula 3 is depicted in Table 8. For example, utility( 3,REQ = fgoal = Studies, goal = Pension, runtime = in 5-10 years, risk = mediumg) = support( 3, goal = Studies) + support( 3, goal = Pension) + support( 3, runtime = in 5-10 years) + support( 3, risk = medium) = 1.0 + 1.0 + 1.0 + 1.0 = 4.0. 3 3.1
User Interface
PEOPLEVIEWS In this section we discuss the PEOPLEVIEWS user interface6 and also show how PEOPLEVIEWS recommendation knowledge can be exploited by the STUDYBATTLE learning environment. The PEOPLEVIEWS homescreen is depicted in Figure 1. For applying PEOPLEVIEWS recommenders, there is no explicit need for being logged in.
Recommenders can be selected and activated directly from the homescreen (see the tag cloud in Figure 1). 6 The user interface is currently only available in German.
If users are logged in, they are allowed to contribute to the development of PEOPLEVIEWS recommender applications. Only the creators of a recommender application are allowed to define user attributes. Other users can complete micro tasks in terms of evaluating items with regard to a defined set of user attributes. The list of user attributes used in our working example is depicted in Figure 2 (corresponds to the entries of Table 3). the recommender can directly be executed. The user interface of our financial services recommender is depicted in Figure 5. product knowledge and sales practices. Examples of STUDYBATTLE games are the following.
Assign Properties. Figure 6 depicts an example user interface of a STUDYBATTLE application that implements a quiz related to knowledge about the relationship between user attributes and items. In the example, users have the task to assign items on the left hand side to user attribute values on the right hand side where each product has to be assigned to at least one attribute value and vice-versa.
Find Items. A different version of the game depicted in Figure 6 is to ask for products that fulfill certain criteria (represented by a combination of user attribute settings).
Find Incompatibilities. This game focuses on combinations of user attribute values that do not lead to a solution, i.e., users have to specify combinations of user attribute values from which they think that no corresponding solution could be found.
Maximize Requirements. The task is to identify minimal sets of
requirements (from a given set of requirements REQ) that have to
be deleted from REQ such that the remaining requirements lead to
at least one solution. This game type reflects the principles of
modelbased diagnosis [
Maximize Items. A similar task is focused on the repair of item sets; in this context the task of users is to identify a maximal set of items from a given set of items such that there exists at least one combination of user attribute values that lead to these items (not necessarily exclusively). An additional criteria could be that at least n items from the original item list must remain in the result set.
STUDYBATTLE
4
Recommendation-relevant filter constraints can be further exploited
for generating different learning applications that are part of the
STUDYBATTLE environment. STUDYBATTLE is a game-based
learning environment which can be utilized as an environment for learning
Human Computation based Knowledge Acquisition. Applying
Human Computation concepts [
Usability. An initial user study has been conducted with an early
version of PEOPLEVIEWS at the Graz University of Technology [
N=161 (15% female and 85% male) students interacted with the
system with the goal to develop different recommender applications.
After having completed the development, the study participants had to
complete a questionnaire which was based on the system usability
scale (SUS) [
Future Work The major goal of this paper was to provide an overview of the PEOPLEVIEWS recommendation environment. There are many issues for future work that we want to tackle and integrate corresponding solutions in upcoming PEOPLEVIEWS versions.
Weighting of Item Evaluations. In the current PEOPLEVIEWS version it is possible to assign user attribute values to items, i.e., to specify which criteria are relevant for the selection of a certain item.
In future versions of PEOPLEVIEWS it will be possible to integrate weights into item evaluations. This maybe does not play a major role in financial service related recommender applications but can be important in other domains were nuances and personal tastes play a more important role. For example, in the context of recommending digital cameras, it can be important to specify degrees regarding certain camera properties, for example, the degree to which a camera is able to support sports photography.
Further Micro Tasks. In the current system version, the only micro task to be completed is to define the relationship (compatibility properties) between items and corresponding user attribute values.
In future versions of PEOPLEVIEWS we will extend this list of micro tasks (see Table 9).
User Selection for Micro Tasks. An important enhancement will be the inclusion of methods that automatically select users for a given set of micro tasks and also take into account fairness in the distribution of micro tasks. As detected in our initial studies, users are willing to contribute to the further development of PEOPLEVIEWS recommenders. An important issue in this context is to find the users with the right expertise for certain tasks and also to not overload users.
Our approach in this context will be to maintain user profiles which are derived from observing the activities of a user within PEOPLEVIEWS. For example, if a user selects a certain item when interacting with the financial services recommender, the keywords extracted from the corresponding item description are stored in the user profile. If (in the future) micro tasks related to similar items (items with a similar description) have to be completed, users with expertise regarding such items will be the preferred contact persons.
Games. Games will be another mechanism for data collection in the PEOPLEVIEWS modeling mode. A single user game will be included that is quiz-based. The overall goal is to guess user attribute settings correctly that best describe a certain item. In a second game two users will jointly try to figure out user attribute values that best describe shown items. The more matching item evaluations exist the better the team performs.
Dependencies between User Attributes and Item Attributes. An extension of the current PEOPLEVIEWS version will be the possibility to identify direct relationships between user attribute values and technical product properties. This is not the case in the current PEOPLEVIEWS version since dependencies are only defined between user attribute values and items.
Recommendation Algorithms. The current version of PEOPLEVIEWS relies on the discussed recommendation-relevant filter constraints – item ranking is based on a utility-based evaluation (see Formula 3). In future versions of PEOPLEVIEWS we will extend the quality of recommendation algorithms by, for example, adapting the determination of support values. If, for example, additional information about the performance of a certain user is available (e.g., performance with regard to correctly completed micro tasks in the past), this information can be used to increase/decrease the weight of a user when determining support values. Finally, when users are specifying their requirements, future versions of PEOPLEVIEWS will allow the specification of preferences (weights) which indicate user preferences regarding certain requirements. This will also include approaches to the learning of weights (users should not have to specify all weights explicitly).
Inconsistency Management. Given a set of customer requirements
it could be the case that no solution can be presented to the user. In
upcoming versions of PEOPLEVIEWS we will focus on integrating
state-of-the-art diagnosis algorithms that help to automatically
determine repair actions in such inconsistent situations [
Quality Management. The major task of quality management is to assure the quality of the dataset collected on the basis of different micro tasks. Quality assurance must be capable of detecting and preventing manipulations of the dataset (also under the assumption that anonymous users are allowed to complete micro tasks), it must also identify changes to the given set of user-specific filter constraints that help to improve the prediction quality of recommendation algorithms. Quality assurance is also responsible for the generation of micro tasks that need to be completed in order to improve the overall quality of the PEOPLEVIEWS datasets. The micro tasks generated by quality assurance are summarized as an agenda – this agenda is forwarded to micro task scheduling that is responsible for distributing micro tasks to the PEOPLEVIEWS user community. 6 In this paper we gave an overview of the PEOPLEVIEWS recommendation environment which exploits concepts of Human Computation to integrate domain experts more deeply into knowledge base development and maintenance processes. PEOPLEVIEWS knowledge bases can be exploited to generate learning applications which can be used in the STUDYBATTLE environment. A major focus of this paper was to show how PEOPLEVIEWS can be applied in the context of financial service recommendation. The concepts presented in this paper have the potential to avoid scalability issues which already exist in many knowledge-based environments due to the increasing size and complexity of knowledge bases.
Cataldo Musto1 and
Giovanni Semeraro1 1 Wealth Management is a business model operated by banks and brokers, that offers a broad range of investment services to individual clients to help them reach their investment objectives. Wealth management services include investment advisory, subscription of mandates, sales of financial products, collection of investment orders by clients. Due to the complexity of the tasks, which largely require a deep knowledge of the financial domain, a trend in the area is the exploitation of recommendation technologies to support financial advisors and to improve the effectiveness of the process.
The talk presents a framework to support financial advisors in the
task of providing clients with personalized investment strategies. The
methodology is based on the exploitation of case-based reasoning
and the introduction of a diversification technique. A prototype of
the framework has been used to generate personalized portfolios, and
its performance, evaluated against 1,172 real users, shows that the
yield obtained by recommended portfolios overcomes that of
portfolios proposed by human advisors in most experimental settings.
2
Wealth management services have become a priority for most
financial services companies. As investors are pressing wealth managers
to justify their value proposition, turbulences in financial markets
reinforce the need to improve the advisory offering with more
customized and sophisticated services. As a consequence, a recent trend
in wealth management is to improve the advisory process by
exploiting recommendation technologies. However, some peculiarities of
the financial domain make hard to put into practice the most common
recommendation approaches, as the Content-Based (CB) or the
Collaborative Filtering (CF). As regards CB recommenders, the
available content, which is necessary to feed a CB recommendation
algorithm, is very inadequate and not meaningful, since each user can be
just modeled through her risk profile2 along with some
demographical features. Similarly, financial products are described through a
rating3 provided by credit rating agencies, an average yield on different
time intervals and the category it belongs to. In this
recommendation setting a pure CB strategy is likely to fail, since the overlap
between features is very poor. Moreover, the over-specialization
problem [
Bari, Italy, email:fcataldo.musto, giovanni.semerarog@uniba.it 2 The Risk Profile is defined as ”an evaluation of an individual or organization’s willingness to take risks”. Typically, this value is obtained by conducting the above mentioned standard MiFiD questionnaire. 3 http://en.wikipedia.org/wiki/Credit rating and diversify the investments over time. Similarly, CF algorithms can hardly be adopted because of the well-known sparsity problem, which makes very difficult to identify the neighbors of the target user.
These dynamics suggest to focus on different recommendation paradigms. Given that financial advisors have to analyze and sift through several investment portfolios4 before providing the user with a solution able to meet her investment goals, the insight behind our recommendation framework is to exploit Case-Based Reasoning (CBR) to tailor investment proposals on the ground of a case base of previously proposed investments. 3
Methodology
Our recommendation process is based on the typical CBR workflow
described in [
(a) Basic Ranking: portfolios are ranked in descending cosine similarity order, according to the scores returned by the RETRIEVE step. The first k portfolios are returned to the advisor as final solutions.
(b) Greedy Diversification: this strategy implements the
diversification algorithm described in [
(c) FCV: Financial Confidence Value (FCV) calculates how close to the optimal one is the distribution of the asset classes in a portofolio, according to the average historical yield obtained by each class.
Given a set of asset classes A, for each portfolio p the set P , of the asset classes in it, and its complement P are computed. Next, FCV is formally defined as:
F CV (p) = Y (p)log( )+1 yai
PjiP=j1 yai
PjkP=j1 yak where pai and yai are the percentage and the average yield of the i-th asset class in the portfolio, respectively. Y (p) is the total yield obtained by the portfolio, and is a drift factor which calculates the ratio in terms of average yield between the asset classes in the portfolio and those which are not in. For values of 1, it acts as a boosting factor (for 1, it acts as a dumping factor). Through this strategy, all the candidate solutions are ranked according to the FCV score and thetop-k solutions are returned to the advisor.
(d) FCV + Greedy: this combined strategy first uses the greedy algorithm to diversify the solutions, then exploits the FCV to rank the portfolios and obtain the final solutions. (3) Review and Retain: in the Review step the user and the human advisor can further discuss and modify the portfolio, before generating the final solution for the user. If the monthly yield obtained by the newly recommended portfolio is acceptable, the solution is stored in the case base and can be used in the future as input to resolve similar cases.
The performance of the framework has been evaluated in an experimental session against 1,172 real users. Results show that the yield obtained by recommended portfolios overcomes that of portfolios proposed by human advisors in many experimental settings.
As shown in Figure 2, FCV significantly outperforms human recommendations (the average monthly yield increases from 0.18 to almost 0.30) for all the neighboorhood (put on the X axis) taken into account.
The experimental results were further confirmed by an ex-post evaluation performed on real financial data from January to April 2014.
As shown in Figure 3, this experiment provided very interesting results: beyond confirming the goodness of FCV-based ranking and the statistically significance of the gap with respect to both collaborative and human baselines, the most interesting outcome was that the combination of the diversification technique and FCV can further improve the performance of the proposed portfolios. This result suggests that the integration of the approaches can make the framework even more effective. This is due to the fact that a combined strategy can merge the advantages of a ranking based on past performance, as FCV, with an algorithm that may lead to more diverse recommendations. This makes the investment strategy better, since the human advisor does not base her investment proposal on a set of very similar portfolios, but rather on a set of diversified solutions which is more stable and effective, especially when market fluctuations have to be tackled.
Deployment of the framework A demo version of the platform is available online6.
Given that the platform is supposed to be of aid for financial advisors, it lets the advisor to select the current user as well as the recommendation technique to be adopted. Next, the ”Recommendation” button shows the most promising portfolios for the target users along with the distribution of the asset classes. The distribution can be further discussed by user and advisor before coming to the final proposal which is stored in the case base.
REFERENCES
[
Springer, (2005).
[
soning Research and Development, 347–361, Springer, (2001).
6 http://193.204.187.192:8080/OBWFinance/ - Login: 2 - Password: 12345
P S Y R E C: Psychological Concepts to enhance the
Interaction with Recommender Systems
Gerhard Leitner1
Abstract. Although recommender systems are already a successful
part of many online systems, there are still areas of research which
are unexploited. One of them is the appropriate consideration of
psychological theories which could be beneficial for the interaction
between a computerized system and an online consumer, particularly in
the financial services sector. This paper emphasizes the potentials of
integrating psychological knowledge into the further development of
recommender systems on the basis of psychological theories and
basic decision processes. The enumerated concepts have been
demonstrated to be influential in consumer buying behaviour in numerous
studies and therefore are used as a theoretical basis of the presented
work. A conceptual framework is build upon the technology
acceptance model (TAM) which offers the possibility of integrating
psychological knowledge in the further development of online financial
services. Possible applications and implementations are shown on the
basis of empirical work that has been carried out in the past years.
1
The utility of recommender systems to enhance the quality of
decision processes and their outcome has been approved many times,
according to [
Specifically promising in this regard is knowledge from psychology
and research aiming to integrate it into recommender systems. This
area of research is, taking the words of [
The emphasis is put on interface and interaction aspects, because
recommender systems are typically characterized by highly
sophisticated algorithmic and technical basis. However, investigating also
efforts in the enhancement of the interface is important, or, as Louis
[
The rest of the paper is structured as follows. In the first sections
an introduction into the theoretical background with an emphasis on
psychological concepts is given. This part is followed by a detailed
discussion on decision phenomena and how these are related to
recommender systems. Afterwards a framework based on the TAM, the
technology acceptance model [
Alpen-Adria-Universita¨t Systems, Universita¨tsstrasse email:gerhard.leitner@aau.at
Klagenfurt, 65-67,
Institute for
Informatics9020 Klagenfurt, Austria,
carried out and showing concrete possibilities for combining
psychological knowledge and recommender technologies are
exemplified. The paper concludes with a discussion and an outlook on future
work.
In the history of online sales many examples of online platforms exist
which were characterized by high technical quality and
innovativeness but lost market share or even disappeared because they did not
appropriately consider user needs. For example, the first company
offering books online was superseded by competitors who provided
better user experience. Another example showing the importance of
considering user needs is Boo.com, which was based on cutting edge
technology but showed bad usability, see, for example, [
Recommender systems can be seen as the technical counterpart
of real shopping environments. For about a century research in
consumer psychology has been influential in advertising, marketing, and
sales. Speaking of the offline world it does not surprise any more
that the design of supermarkets in regard to shopping paths,
lighting conditions or sound exposure is not left to chance and consumer
psychology is omnipresent [
This is possible because recommender systems are able to
dynamically adapt to the individual user. This can constitute a meaningful
alternative to offline purchase situations where an average sales
assistant can be assumed to base his recommendations only on a limited
set of alternatives. On the other hand it is important to make the user
forget about the disadvantages online systems could have compared
to real shopping experiences. These are, for example, the
possibility to touch and investigate a product physically and to communicate
with a human counterpart, negotiate a price or ask questions. The
challenge for the service-provider is the increased difficulty to
convince an online user about the benefits of a product or even persuade
him or her to buy it, because there are limited possibilities to
establish a pleasant atmosphere. In the following a spotlight is put on a
selection of psychological concepts and theories which have a direct
relation to buying behaviour and therefore build a promising basis
for further research and to enhance recommender systems in a way
that they are capable of supporting all facets and phases of human
consumer behaviour. This is neither easy nor possible in just one
iteration.
3
The following list of theories is not intended to be exhaustive, it
should just point out the potentials of psychological concepts which
have, as demonstrated in numerous studies, a direct relation to
human behaviour and insofar could also be useful for the enhancement
of online behaviour in general and in regard to financial services in
particular. Some of the elements of the theories have been either
analysed for applicability or actually used within own studies [
Prospect Theory, PT
PT is of interest in regard to the behaviour of consumers in
situations characterized by uncertainty and and risk. These are, when
considering the work of [
Locus of Control Theory, LoC
LoC implies that behaviour depends on the interpretation of a
person whether she has control over a situation or interaction and the
outcome of an interaction (internal locus of control). When a
situation or outcome is beyond influence (e.g. the user has the feeling
that the system or external forces have the control), then external
locus of control is the case [
Attribution Theories, AT
Attribution theories are, as LoC, assuming internal/external
control as one important dimension, but also include other
dimensions, for example stability vs. flexibility. It is not only of
relevance whether control is perceived as internal or external but also
if it is stable, depending on the domain or a particular situation
[
Expectancy-Value Theories, EVT
This group of theories is based on the two dimensions expectancy
and value. Expectancy refers to the degree to which a person is
capable of reaching a goal. Value refers to the importance the goal
has for the person. Example theories of this group are the theory of
planned behaviour (TPB) or the theory of reasoned action (TRA)
and they are important in the context of online buying. Besides
personal aspects (i.e., attitude to a behaviour), social aspects play
an important role and influence the value. For example, how
people from relevant groups such as peer groups, family and friend
would judge a certain behaviour (e.g., the purchase of a certain
product) [
Need for Cognition / Elaboration Likelihood Model, NfC NfC implies that depending on the importance of the domain (”personal involvement”) a person tends to process information on different elaboration routes. In domains which are of high importance for the person information is processed on the central route, characterized by a high level of elaboration (extensive collection of information, comparison, outweighing of pros and cons, etc.) The alternative way of processing, the peripheral route, is characterized by low involvement of the person and, as an effect, an intentional low investment of efforts in processing information.
The type of elaboration is, for example, of interest when an online
platform is intending to include persuasive technologies [
Cognitive Dissonance, CD
CD is assuming a mental model that a person establishes about
a certain area of life, a behaviour or other relevant issues. The
model only includes ”consonant” information, which means that
information present in the model should not be contradictory. For
example, if a person thinks about financing a holiday trip with a
loan this may contradict with a negative attitude towards taking
out a loan for things that do not have a material value (such as
cars or real estates) . In this case dissonance occurs and,
according to the model, mental efforts are invested to restore consistency
[
Reactance Theory, RT
Implies that humans are driven by the assumption that they can
behave and act unrestrictedly. If a behaviour or an ”object of
desire” is not available or difficult to reach, its subjective value is
increased and the reactant user tries to overcome this shortage by
increased efforts [
Flow, F
The central concept of the theory is the state of flow which is
characterized by an immersion of the user with the system. Flow
is, for example, observable on computer game players, musicians
or craftsmen who smoothly interact with their tools without
observable disruptions [
How elements of the enumerated theories and concepts could affect the interaction with a financial services platform is illustrated in the following example.
Example. Imagine a potential consumer is using an online system to inform herself about loan opportunities. Based on her attributional patterns (AT, LoC) she has a certain understanding of whether she is able to use an online platform and can control the outcome of the product search. We assume that she is self-confident in the usage of the system (EVT, expectancy) and the system is appropriately designed that she can ”play around” and easily evaluate alternatives (and eventually reaches a kind of ”flow”, F). Depending on the personal importance (EVT, value) of the product she is searching for (loan for a holiday trip, a car or a house) she will put low or high efforts in the evaluation, comparison, and selection of the product (NfC). When she knows what she wants and has good experiences with a certain brand or provider (PT, CD) she will not care that much what others say about her decision (EVT, peers). If she is uncertain, doesn’t want to make a mistake or wants a product with a high status she will orient herself on information of other users (EVT, peers) and in what percentage they purchased what product (for example based on online ratings or discussions with her peer groups). If the product or service she has finally chosen is not available immediately, she will try to solve the problem by finding other sources from where to get the product (PT, RT) or she will resign and decide not to buy any product (AT). 4
Decisions as the Connecting Element
The direct application of the theories and concepts enumerated above
is difficult because many of them are too abstract. It is therefore
necessary to investigate the ”atomic” element of consumer behaviour
which is decision. Each purchase or even browsing for information
to prepare a purchase is characterized by a singular decision or a
sequence of decisions. They are made on the basis of gathered
information, the consultation of different information sources, the
outweighing of alternatives, etc. Economic theory has assumed that humans
can be considered as omniscient and make decisions on the basis of
optimal rationality. Since the work of Simon [
Felser [
Extensive Decision. If a person is planning to buy the apartment
this is a long term investment that influences the financial life of the
person for decades. Therefore the person is probably highly involved,
activated, and will invest high efforts to find out the best financing
alternative and therefore applies an extensive decision procedure until
he gets the best financial plan which the smallest influence in the
current financial situation. The strategy followed has characteristics
of the central route processing of need for cognition theory [
Although this type of decision making is highly sophisticated, it has
some weaknesses. For example, the amount of information
considered in the decision is not directly proportional to the amount of
information available, which means that even if higher amounts of
information would be available, people prefer short cuts [
Another insight is that higher effort invested into a decision does not mean that the outcome of the decision is better. One of the reasons is that the dimensions consulted for a decision are often unconscious.
An a posteriori justification is done on dimensions which can be rationalized but those may not be the ones which were responsible for the decision.
Limited Decision. Another person having in mind to rent an
apartment and just needs money for new furniture may be less passionate
and would apply other criteria to the decision process. She applies
the second type of decision, which is limited decision. Decisions
following this strategy are based on experiences (positive and negative
ones) and heuristics which were derived from these experiences, such
as ”Brand A is better than brand B” or, ”The more expensive, the
better a product”. The person may choose the company for financing
furniture based on an advertisement she recently saw. In this case the
availability heuristic, described by [
Habitual Decision. The third type of decision, habitual decision, can be seen as a combination of extensive and limited decision. Based on previous experiences a mental model has been established, on the basis of which consumer behaviour follows a routine sequence and may not involve explicit decisions. This strategy mainly is applied in routine behaviour when no extraordinary investment is planned (such as in the previous examples). For example, if a person has to transfer money to a country where the receiver still requires conventional paper based transfer, she typically goes to her familiar bank branch and transfers the money there although there might be another company who offers cheaper transfers to the target country. In the past the selection of the best bank might have involved extensive decision strategies. When these efforts were successful and resulted in selecting an appropriate bank, a mental model is build which drives future behaviour. If the combination of services, price and reputation has been working satisfactorily in the past it would not have a serious impact, if it did not work any more (e.g., prices for services are slightly increased) - in terms of financial loss or well-being.
Impulsive Decisions. The last form - impulsive buying - is characterized as a ”reaction” to environmental stimuli rather active behaviour and may not include decisions at all. This form of occurs in the context of financial services, for example, when a credit card is used for buying things. This also involves investing money, but the investment is hidden and partly unconscious.
The previous paragraph was describing decisions on a general
level. Beckett et al.[
The matrix has been evaluated in a series of focus groups and three product types are corresponding to the different decision types shown in Figure 1: basic transaction services (existing accounts), basic insurances products (car, house), and investment services (stocks, shares, pensions, etc.). Repeat-passive decisions mainly take place in the context of basic transaction services, when brand loyalty to banking institution and confidence in the decision is high. Rational-active decisions are made when price is one of the most important criteria.
This strategy is characterized by the necessity to search for products, to deal with a big amount of information and to thoroughly analyse the outcome. This could be necessary because, for example, insurance companies offer more or less the same services and products and deliberately make comparison to competitive products difficult.
Relational-dependent decisions are, according to the results achieved
by [
The previous paragraphs were devoted to the content of decision
processes involved in consumer behaviour. The second, similarly
important dimension in regard to online platforms based on
recommender systems is the presentation of information. We take the
differentiation of [
The application of conventional usability engineering methods to
accompany the development is crucial [
An Integrated Model as Basis of Research
The aspects addressed in the previous sections characterizing
consumer behaviour in general and online consumer behaviour in
particular are difficult to capture. Their comprehension would be easier if
a way could be found to operationalize them based on an integrated
framework. The technology acceptance model (TAM) originally
proposed by Davis [
Experience Already having used a system or similar ones can have an influence on many factors, such as the perceived usefulness and the subjective norm. In relation to psychological theories, experience can increase, for example, the confidence and the assumption of internal control (LoC, AT).
Voluntariness The extent to which users perceive the usage of a system to be non-mandatory. This aspect relates to reactance theory (RT) - if a person has the freedom to choose an online system for financial services additionally to offline services this makes a difference to being forced to use online services (because the nearby bank branch has been closed).
Subjective Norm A person’s perception that most people who are important think he or she should or should not perform a behaviour or use a system.
There could, for example, be a conflict between the personal preferences and the attitude of the relevant others, which could lead to cognitive dissonance (CD) (”I would issue a credit for a holiday trip”.) Image The degree to which the use of an innovation is perceived to enhance one’s status in the social system. In regard to the provision of different platforms (desktop or mobile platforms) this aspect,
Computer Self-Efficacy The degree to which a person beliefs that he or she has the ability to perform the intended task. This depends on the experience with computer systems in general, and on the experiences within a specific domain (e.g. financial services) in particular (LoC, AT).
Perceptions of External Control The degree to which a person believes that an organizational and technical infrastructure exists to support use of the system. This could also be influential in a negative way (according to LoC and AT) when a person feels that the organization behind a system limits his or her performance or degrees of freedom.
Computer Anxiety The degree of a person’s fear, when she/he is faced with the need of using computers to access services. Specifically in the context of financial services (or even online transactions with credit cards) people are anxious because of the danger to lose money (PT).
Computer Playfulness The degree of cognitive spontaneity in computer interactions. If a system supports this kind of interaction, such as simulating different variants of financing, this supports persons engaging in extensive decision making processes (NfC).
Perceived Enjoyment The extent to which using a specific system is perceived to be enjoyable, whereas enjoyment can have different dimensions. Feeling safe in the sense of nothing unexpected can happen when transferring money could be one form of enjoyment. Another one is developing trust towards an institution or a platform when the latter is characterized by transparency and comprehensibility (NfC).
Objective Usability A comparison of systems based on the actual level of effort required to complete specific tasks. If it is faster to go to the bank branch to transfer money than using the computer interface, then the objective usability of an online system would be low (EVT).
Perceived Usefulness The degree to which a person believes that using the system will help him or her to attain gains in life quality. Saving money by using an online system instead of personal services convinces people to adapt to new technologies (EVT).
Perceived Ease of Use The degree of ease associated with the use of the system. Besides the utility aspects of a system, the subjective usability is relevant.
If people do not trust a system or are doubtful in their usage, they would not use it (LoC, AT).
Behavioural Intention The degree to which a person has conscious plans to perform or not perform some specified behaviour. Only if the enumerated dimensions are fulfilled in a certain degree, a person will have the intention to use a system. The correlation between the intention and the actual use still is low (EVT).
Use Behaviour When every aspect is, depending on the individual preferences, optimally fulfilled, then a flow experience could occur (F).
As emphasized in the enumeration of elements, the TAM has
connections to the concepts and theories addressed in this paper [
The first work in this regard is a paper on serial position effects.
The effect, being one of the oldest phenomena in psychological
basic research [
A more recent work which builds upon the work on serial position
effects was carried out in the domain of group decision making [
Making decisions in groups, for example choosing a dinner with a business partner or deciding what movie to watch with friends in a cinema always involves psychological phenomena on the individual as well as on the group level. Decisions derived in group situations are influenced by rhetoric skills of the participants, negotiation techniques applied, leadership competency and other personality factors.
In contrast to this real-time and synchronous approach, an online tool
supports asynchronous and sequential decision procedures.
Psychological concepts that could have an impact in this kind of decision
process are, for example, originating from research groups who
developed the prospect theory [
A following small example illustrates their influence. To be able to sketch a financial plan it is necessary to have a starting point, the anchor stimulus. This starting point is typically the amount of money that has to be financed. A strategy that is frequently used in advertising is not to use the whole amount for evaluation (for example, 100.000 are needed + overhead costs) but the monthly rate (for example 500). Within the study we investigated alternatives of presenting information and were interest in the possibilities of manipulating serial position effects and other form of presentation, concretely based on the multi attribute utility model (MAUT). The results showed that MAUT concepts can counteract serial position effects and insofar represent an appropriate means to steer decision processes. Figure 4 is showing an example screen of the CHOICLA group decision support tool on which preferences can be declared based on multiple attributes.
The last empirical work presented was focused on persuasion [
Before introducing the decoy element (D) two products are available
to the customer, C (competitor product) and T (target product). C is
characterized by a lower price, but also by lower quality than T. As
price is one of the most important dimensions in purchase decisions
[
. 7
Discussion and Conclusions In this paper we have tried to emphasise the potentials of psychological theories to enhance the quality of interaction between users and computerised systems based on recommender technology. The theoretical basis builds a selection of psychological concepts and theories which have been empirically investigated in numerous studies and proved themselves as being relevant in the context of consumer behaviour. An increased consideration of knowledge from psychology could enhance the quality of recommender systems, specifically on the level of the user interface. The different types of decisions related to consumer behaviour were discussed and possibilities of recommender systems to support such decisions were exemplified.
The technology acceptance model serves as a basis for further research in this area because it already integrates many of the relevant psychological concepts and theories that have been demonstrated to be influential in the context of consumer behaviour. With an appropriate consideration of this knowledge, recommender systems could overcome the disadvantages online system have in comparison to offline interaction between consumers and, for example, shop assistants. The advantages of recommender systems such as their capabilities of processing huge amounts of data, selecting the correct products from millions of alternatives, and calculating the best product for are consumer within a few seconds could be exploited in a better way if not only the back-end functionalities but also the front-end, the interface to the customer is enhanced in an appropriate way.
Although our work is addressing different domains, the
conceptual work sketched and the empirical studies performed are also
applicable to the financial sector. Specifically of interest in this
regard are the different types of decisions driving potential customers
and motivating them to use an online system, choosing a product or
service, changing parts of his or her financial portfolio. In the
context of recent developments in the financial sector (e.g., merging of
banks and insurance companies, closing of branches) the importance
of online services will increase. Appropriate systems supporting the
different needs, motives of end consumers, and also respecting the
different levels of efforts people are willing to invest into financial
decisions will be more important than ever before. Recommender
systems integrating psychological aspect and simulating a ”human
image” [
The empirical work presented can only be seen as the starting point in the endeavour of enhancing human recommender interaction in the emphasized way. An unresolved problem in this regard is, for example, how a recommender system could find out what strategy a consumer is currently applying (e.g. extensive or limited decision) and to change the presentation of information accordingly.
There are of course domains where one strategy is the most probable one (e.g. financing a real estate are probably based on extensive and central route elaboration) but further research is necessary to address this problem. Of course transferring services form offline to online does not only have advantages. In the context of current developments in regard to privacy and business ethics this opens new challenges which are influencing the orientation of future research activities. Our major goal is to complete the ”puzzle” of which we have already identified elements in our past research work.