In the paper discusses the use of big data as a tool to increase data transfer speed while providing access to multidimensional data in the process of forecasting product sales in the market. In this paper discusses modern big data tools that use the MapReduce model. The big data presented in this article is a single, centralized source of information across your entire domain. In the paper also proposes the structure of a marketing analytics system that includes many databases in which transactions are processed in real time. For marketing forecasting of multidimensional data in Matlab, a neural network is considered and built. For training and building a network, it is proposed to construct a matrix of input data for presentation in a neural network and a matrix of target data that determine the output statistical information. Input and output data in the neural network is presented in the form of a 5x10 matrix, which represents static information about 10 products for five days of the week. The application of the Levenberg-Marquardt algorithm for training a neural network is considered. The results of the neural network training process in Matlab are also presented. The obtained forecasting results are given, which allows us to conclude about the advantages of a neural network in multivariate forecasting in real time.
As Flors [
Intelligent systems and the use of multidimensional communication determined the
emergence of a new concept by Schwab [
It should be noted that with the use of digital marketing, D2C models have come to be used. The D2C (Direct to Consumer) model represents a direct selling system, where companies LGOBE
CEUR
CEUR Workshop Proceedings (CEUR-WS.org)
themselves manufacture, promote, sell and deliver their product without the involvement of
intermediaries. So, the article provides an analysis that shows that, unlike traditional promotion
through retail chains, companies using the D2C model develop faster with their own distribution
channels [
Given the widespread use of digital marketing, Kats [
So in the presented report by Enberg [
Therefore, the modern market is based on direct selling (D2C) models. allow you to get images of buyers and segment them. In addition to these tasks, it is necessary to solve forecasting the market, which changes every year.
It should be noted that worldwide targeted statistics for the entire sales system. This information is stored in cloud storage (Big Data). The information used includes data from the time of attracting a new consumer to the required resource information about the number, including repeated ones.
In this article, we propose a marketing analytics method based on artificial neural networks.
Marketing forecasting is part of any firm’s overall marketing analytics. An important role in the forecasting method is played by the multidimensionality of information and methods of their processing. The use of Big Data with OLAP technologies requires new approaches to processing and applying large amounts of data. This is due to the wide range of communication systems used in the e-commerce market. Therefore, marketing forecasting based on Big Data is an urgent task, which is discussed in this article.
The article is devoted to marketing forecasting based on the use of neural networks. The information base of marketing forecasting is Big Data. The process of constructing training matrices, training a neural network and making the predictions are presented in the result of paper.
Modern companies use many available forecasting methods, they not only improve the quality of their products, but also get information about the needs of customers. Marketing forecasting models are a great way to predict customer preferences and apply new ways to stand out from the competition. Using practical forecasting models today is the best way to get the most efective and complete data to improve marketing decisions. In this case, forecasting methods in digital marketing should include not only customer surveys, their age, interests and price, but also the characteristics of the product, brand, logistics and others.
In the work of Bard [
According to the results of a study of the opinions of experts, Ashton [
Further development of the principle of intentions was found by Morwitz [
A continuation of these works found themselves in the work of Armstrong [
This forecasting method is currently rarely used. Rowe and Wright [
The task “Intentions” was considered by Wittink and Bergestuen [
The formation of a digital marketing strategy was considered by Mandal and Joshi [
The analysis of the state of the digital economy and digital marketing is discussed by Ivanov
[
The analysis of the overview of macroeconomic forecasting are discussed by Carnot et al.
[
The research of the technological sources of the next long wave of growth is made by Vázquez [21], Lee and Lee [22]. The authors study the impacts of national innovation systems (NIS) and economic complexity index (ECI) on economic growth.
The use of Exponential smoothing (ES) forecasting methods is discussed by Chatfield et al. [23], Hyndman et al. [24]. The authors research revolution of exponential smoothing, which has been improved with the introduction of a complete modeling framework incorporating innovations state space models, likelihood calculation, prediction intervals and procedures for model selection.
The modern economy is characterized by rapid dynamics of economic processes. Under these conditions, marketing forecasting models acquire new meanings in managerial decision-making. The process of the importance of making management decisions in digital marketing systems is shown in figure 1.
Traditional Marketing Analytics (MTA) is based on the use of classical approaches and forecasting methods. MRA is aimed at solving economic important forecasting problems from the moment information appears to several hours.
These tasks are solved using neural networks and marketing robots.
Traditional Marketing Analytics is based on the use of classical approaches and forecasting methods. Marketing Actual Analytics (MRA) is aimed at solving economic important forecasting problems from the moment information appears to several hours. These tasks are solved using neural networks and marketing robots. Today the number of information sources of data in the world is growing rapidly. Therefore, storage technologies and their processing of information are becoming more and more in demand. By storing information, one can single out the use of Big Data for which the basic principles of work can be formulated: 1. Horizontal scalability, which takes into account that the data can be arbitrarily large from any system. They have the ability to handle big data. 2. Tolerance to failures, which use the principles of horizontal scalability and apply methods of clustering systems; locality of data, which allows in large distributed systems to separate data from a large number of data centers. All modern tools for working with big data, one way or another, follow these three principles. The first principle is based on the MapReduce model. The MapReduce model provides for distributed data processing proposed by Google and is shown in figure 2.
MapReduce provides that data is organized as relational or multidimensional data (OLAP).
The data processing method takes place in three stages. The first stage is aimed at executing
the Map() function. At this stage, the data is preprocessed using the Map() function, which
is defined by the user. The work of this stage is to preprocess and filter the data. The second
stage of the model is performed by the Shufle() function. This stage goes unnoticed by the
user. At this stage, the Map() function performs the data immersion procedure similarly to
the formation of data marts (Data Mart), that is, one Map() data output corresponds to each
mart. In the future, these showcases will serve as an input for the Reduce() function. The
third stage of the model is aimed at executing the Reduce() function. Each data mart, which is
formed in the second stage, transfers information to the input of the Reduce() function. The
Reduce() function is user defined and calculates the result for individual storefronts. The set of
all values returned by Reduce() is the result in this method. Therefore, Big Data technology is
consider as a tool that allows you to increase the speed of data transfer while providing a large
capacity of information carriers. In addition, this technology can improve the availability of
cloud applications and data services. Thus, digital marketing is shape around the mainstream
e-commerce models. The interconnection of the main models (B2B, B2A, D2C, C2A and C2C) of
e-commerce systems based on the systems for collecting, storing and analyzing information in
real time. Which based on subsequent storage in historical data layers. For the implementation
of systems that perform Marketing Relevant Analytical tasks using data, OLAP data systems
are used, which are structured according to the principle of multidimensional information
presentation [
In a marketing analytical system, there are many databases. where transaction processing is done in real time. Therefore, online data source systems (ODS) provide information for processing in OLTP. OLTP systems provide storage and processing of information in real time. The processed data in OLTP is transferred to the Data Mart systems with the subsequent construction of multidimensional OLAP data cubes.
This multidimensional data is aimed at presenting information on thematic sections both on marketing information and other information from diferent areas of the economy. The marketer has the ability to access multidimensional data in the repository, as well as complete economic information for conducting an MRA. The advantages of this approach are: • simplicity of creating and filling OLAP, since filling comes from reliable sources of data marts; • reducing the load on working with multidimensional data, namely, one multidimensional query processes multiple OLAP layers.
The data coming from the OID is transferred to the OLTP and the data marts are moved.
OLAP stores data as multidimensional layers of measures and dimensions [
= { = ( , , )} , = 1, .., , where is the product included in the analyzed sets of – the object of research, – indicator of income of the product, – product marketing indicators .
Datasets from set stored in OLAP and on demand allow you to obtain and conduct marketing analysis with the subsequent storage of data, which are called transactions. Description of a transaction to set as follows: = { | ∈ } .
Such transactions for retail outlets on the Internet correspond to the nomenclature of goods that the consumer buys and the data stored in OLAP as multidimensional data cubes (OLAP).
Then solving the problem of marketing forecasting based on a neural network, data arrays of its training are formed. The forecasting technique using a neural network is formalized through the problem of pattern recognition. Data on the predicted economic indicators of a product for a certain period of time form an image, the class of which is determined by the values of the predicted indicators.
In the proposed methodology, the dimension of the multidimensional array will determine both the forecasting interval and the number of predicted indicators. Each next line of the array is formed as a result of a shift by one interval equal to the prediction interval.
The neural network is trained on the generated training array of product indicators and adjusts its weights accordingly. As a result, the neural network is trained to solve the forecasting problem for a certain forecasting horizon. It should be noted that two forecasting approaches are used: one-step and multi-step. One-step forecasting is used for short-term forecasts and multistep forecasting is used for long-term forecasting.
Let the time interval [ 0, ] be given, the indicators , , of the product are defined, where 0 is the initial time value, is the current time value. To find the predicted values on the prediction interval Δ, a method is proposed that includes the following stages: 1. Analytical analysis of marketing indicators and the formation of a learning matrix from selected values from historical slices of multidimensional databases (OLAP technology).
A learning matrix (ML - matrix learning) can be written as input data for representation in a neural network (equation (3)). (3) (4) where Δ – is the horizon (time interval) of forecasting.
= ⎡⎢⎢⎢ 0111 == …0111(( 00 ++ ΔΔ)) 1022 == 10…22(( 00 ++ 22ΔΔ)) ……… 10 == 10…(( 00 ++ ΔΔ)) ⎥⎤⎥⎥ , ⎣ 1 = 1 ( 0 + Δ) 2 = 2 ( 0 + 2Δ) … = ( 0 + Δ) ⎦ = 1, ...,
The input data in the neural network in Matlab is presented in the form of a 5x10 matrix, which represents static information on 10 products for five days of the week and has the following form (figure 4).
Target data that determine the output statistical information for the neural output can be represented in the form of learning value matrix ( , equation (4)).
The target data, which determines the output statistical information in Matlab for neural output, is presented in figure 5.
2. Neural network training. The process of training a neural network is to match to each element the value of the matrix corresponding to the mapping in the value of the elements of the weight matrix : (5) (6) ∶ → .
In the process of training the neural network, the task of minimizing the objective function is solved. With this approach, an algorithm is used for training, which is the most eficient not only in terms of errors, but also in time. The neural network in Matlab is trained using the Levenberg-Marquardt error backpropagation algorithm. The Levenberg-Marquardt algorithm uses a scalable conjugate gradient backpropagation. Therefore, the training of the neural network is represented in time, and the network is tuned in accordance with its error. The magnitude parameter is used to measure the generalization of the neural network and stop learning when the generalization stops improving. The test score itself does not afect training and provides an independent assessment of the performance of the neural network during and after training. The choice of the algorithm, as well as the learning process of the neural network, is shown in figure 6 and 7.
The number of neural network training epochs can be written as follows: ℎ = | − 0 | .
Δ
In the process of forecasting by a neural network, it is necessary to take into account the forecasting horizon. In the Matlab system, the sim (net,[;;]) function is implemented, which allows you to supply a variety of input values and get a solution at the output of a neural network. The forecast results for the sale of 10 goods are shown in figure 8.
Therefore, the created neural network does indeed make multiple predictive decisions. It allows you to solve the sales function of marketing and consider the dynamics of the sale of many products in real time. Marketing forecasting looks at the number of future periods that the forecast will cover. That is, you may need a forecast 7 days ahead, with data for every day. In this case, the period is a day, and the horizon is 7 days. Finally, the prediction interval is the frequency with which a new prediction is made. Often the prediction interval coincides with the prediction period. The choice of the forecasting period and horizon is usually dictated by the conditions for making marketing decisions. Choosing these two parameters is one of the hardest parts of marketing forecasting. For forecasting to be meaningful, the forecasting horizon must be no less than the time required to implement the decision made on the basis of the forecast.
Thus, forecasting is highly dependent on the nature of the decision being made.
It is known that making management decisions in digital marketing, taking into account the time of receipt and a large amount of information are an urgent task today.
In addition, in the article, the authors consider the use of Big Data as a tool to increase the data transfer speed while providing access to multidimensional data (OLAP).
The article proposes the structure of the marketing analytics system. It includes many databases, where transactions are processed in real time. Consequently, online data source systems (ODS) provide information for processing in OLTP. This ensures prompt processing of information in real time. For marketing forecasting of multidimensional data, a neural network in Matlab is built. To solve the problem of improving forecasts, the authors have proposed building input data matrices for presentation in a neural network and target data matrices that determine the output statistical information.
Also in the paper, the results of the neural network training process in Matlab are represented on a chosen learning algorithm. The obtained forecasting results allow us to draw a conclusion about the advantages of a neural network in multivariate forecasting in real time. Multidimensional data and the level of their detail are important to solving the problem of forecasting in real time.
The wider use of digital-marketing systems gives an opportunity for applying the proposed approach to marketing forecasting. [21] D. Vázquez, Variety patterns in defense and health technological systems: evidence from international trade data, Journal of Evolutionary Economics 30 (2020) 949–988. doi:10.1007/s00191-020-00700-9. [22] K. Lee, J. Lee, National innovation systems, economic complexity, and economic growth: country panel analysis using the us patent data, Journal of Evolutionary Economics 30 (2020) 897–928. doi:10.1007/s00191-019-00612-3. [23] C. Chatfield, A. B. Koehler, J. K. Ord, R. D. Snyder, A new look at models for exponential smoothing, Journal of the Royal Statistical Society: Series D (The Statistician) 50 (2001) 147–159. doi:10.1111/1467-9884.00267. [24] R. Hyndman, A. Koehler, K. Ord, R. Snyder, Forecasting with Exponential Smoothing: the State Space Approach, Springer, New York, 2008.