Introduction
Business process monitoring is concerned with the analysis of events produced
during the execution of a business process in order to assess the ful llment
of compliance requirements and performance objectives [
Advances in machine learning combined with the availability of process execution data have led to the emergence of predictive process monitoring techniques. Predictive business process monitoring refers to a family of online process monitoring techniques that seek to predict the future state or properties of ongoing (incomplete) cases, stored in an event stream. These predictions are based on models extracted from historical (complete) cases recorded in event logs.
In the past years, numerous approaches have been proposed to address
typical prediction targets, such as compliance violations [
To address this gap, this thesis starts with a systematic literature review of
methods for predictive monitoring of temporal measures of business processes.
The review was conducted using a range of search keywords and exclusion
criteria, and retrieved 25 relevant studies containing unique contribution [
A key gap in the existing body of methods, identi ed through the literature
review, is the lack of support for explainability in existing approaches. Indeed,
a major drawback of black-box prediction methods in practical deployments is
that users have di culties trusting the prediction when the reasoning behind the
prediction is unclear [
A recent survey by Guidotti et al. [
The rst group of research proposals focus on explaining how the model
makes certain predictions. To this end, reverse engineering is typically exploited
to understand the black box model. These approaches are also known as
posthoc explainability, and they provide interpretations based on natural language
explanations, visualizations or by examples. Thus, we can separate two processes
{ decision making (prediction) and decision explaining. Post-hoc interpretations
are also most suitable to provide intuition for complex non-transparent models,
such as deep neural networks [
Rather than providing post-hoc explanations for a black-box classi er, the
second group of proposals focus on directly designing a transparent classi er
that solves the same classi cation problem. This principle, known as
\Transparent Box Design", is used in this thesis. Speci cally, our approach is grounded
in the eld of transparent box design for local interpretability, i.e. we provide
explanations for individual predictions, rather than globally for all predictions.
To this end, we apply the idea of decompositional explanation [
In one embodiment of this general idea, we used deep learning models, speci cally RNNs and LSTMs, that had been shown to achieve higher levels of accuracy in predictive monitoring, owing to their ability to learn relevant features from trace pre xes automatically. In order to make these models explainable, we used an instance of multi-task learning where several related predictive monitoring tasks were integrated into a single system which is trained jointly, as a way to decompose the predictions. Namely, our technique provides a prediction of the temporal measure in terms of the predicted temporal measures of each of the activities in the most likely remaining path of the current trace.
In a second embodiment, we propose an explainable predictive process
monitoring method by automatically discovering a BPMN process model from the
event log [
We conducted a comparative evaluation of two proposed explainable approaches with each other and with various state-of-the-art baselines, using a uni ed experimental set-up and 17 real-life event logs originating from di erent business domains. The results of the evaluation highlighted the trade-o between the prediction accuracy and explainability of predictions in the context of predictive monitoring of temporal measures. The most accurate predictions were typically obtained via black-box models. Speci cally, in 13 out of 17 datasets, LSTM-based models trained in a single-task learning setting achieve the best accuracy. At the same time, explainable models are generally less accurate. This trade-o should be considered by business process analysts when choosing a suitable prediction method. Another observation yielded by our evaluation is the correlation between structural characteristics of event logs and the performance of various pre x bucketing and encoding combinations. As such, the former is also an important factor when selecting a prediction method.
The research contributions of the thesis have been consolidated into an opensource toolset for predictive business process monitoring, namely Nirdizati1. It is a Web-based predictive business process monitoring engine that can be used to train predictive models using the methods described in this thesis, as well as third-party methods, and then to make predictions at runtime, for ongoing process instances. Currently, the tool is able to predict remaining time of process instances, their binary outcome, the next activity to be executed as well as various static case attributes. Predictions can be presented visually in a dashboard or exported for periodic reporting.
Nirdizati has been validated in collaboration with industry partners, providing important feedback as to how this technology is likely to be used in an enterprise setting. One important observation noted in our validation is that the designed predictive monitoring platform shall be used in conjunction with other business intelligence (BI) or monitoring systems. To this end, the platform should o er an API to allow integration with other tools. This task is beyond the scope of the thesis; however, we provide functionality to export the predictions in a CSV le, for importing into third-party BI tools. In this way, analysts will be able to build customized dashboards to highlight the required measures.
Another important lesson learned by testing Nirdizati is that there exist several use cases for predictive process monitoring in practice. One of them is the real-time dashboard use case where users can see the current predictions updated continuously. This is especially relevant for very dynamic processes with high throughput. For slower processes, the regular reports use case may be su cient where a user wants to get reports on a regular basis with the current set of predictions. These predictions are possibly ltered so that the report focuses 1 http://nirdizati.org on the cases that are most likely to become deviant and therefore need attention. Finally, the alarm use case may be helpful, where users only want to know about a prediction when a case is likely to be deviant.
The last but not least contribution of the thesis is the application of the
proposed explainable predictive monitoring methods to improve the e ciency of
business processes [