arXiv subjects
Publications and source records attributed to Peter Fettke.
We suggest systems mining as the next step after process mining. Systems mining starts with a more careful investigation of runs, and constructs a detailed model of behavior, more subtle than classical process mining. The resulting model is enriched with information about data. From this model, a system model can be deduced in a systematic way.
Heraklit is an ongoing research program and development project aimed at creating an infrastructure for modeling large-scale, computer-integrated systems. We discuss the key requirements for such models (hierarchies, user view, transformation of informal into formal ideas, schematic models, equal treatment of digital and person-bound processes) and explain how Heraklit supports these requirements. A case study demonstrates the applicability of Heraklit in practice.
Edsger W. Dijkstra has frequently suggested building a "firewall" between the technology- and application-side of computer science. His justification: The methods to attack the computer scientists' formal, mathematical "correctness problem" differ fundamentally from the methods to attack the applicants' informal "pleasantness problem". In this setting, a model is always confined to one side or the other of this wall. This keynote shows that a seamless transition between both sides can be achieved by a framework with architecture, statics, and dynamics as the three pillars of modeling computer-integrated systems. Selected examples justify this framework. It allows to "breath life" into (static) models, and it implies a new understanding of the "pleasantness" of computer-integrated systems, which is well-needed in the age of "digital first".
Conceptual modeling is a strongly interdisciplinary field of research. Although numerous proposals for axiomatic foundations of the main ideas of the field exist, there is still a lack of understanding main concepts such as system, process, event, data, and many more. Against the background of the tremendously gaining importance of digital phenomena, we argue that axiomatic foundations are needed for our discipline. Besides the general call, we provide a particular case study using HERAKLIT. This modeling infrastructure encompasses the architecture, statics, and dynamics of computer-integrated systems. The case study illustrates how axiomatically well-founded conceptual models may look like in practice. We argue that axiomatic foundations do not only have positive effects for theoretical research, but also for empirical research, because, for instance, assumed axioms can explicitly be tested. It is now time to spark the discussion on axiomatic foundations of our field.
It is known for decades that computer-based systems cannot be understood without a concept of modularization and decomposition. We suggest a universal, expressive, intuitively attractive composition operator for Petri nets, combined with a refinement concept and an algebraic representation of nets and their composition. Case studies show exemplarily, how large systems can be composed from tiny net snippets. In the future, more field studies are needed to better understand the consequences of the proposed ideas in the real world.
Learning meaningful representations of data is an important aspect of machine learning and has recently been successfully applied to many domains like language understanding or computer vision. Instead of training a model for one specific task, representation learning is about training a model to capture all useful information in the underlying data and make it accessible for a predictor. For predictive process analytics, it is essential to have all explanatory characteristics of a process instance available when making predictions about the future, as well as for clustering and anomaly detection. Due to the large variety of perspectives and types within business process data, generating a good representation is a challenging task. In this paper, we propose a novel approach for representation learning of business process instances which can process and combine most perspectives in an event log. In conjunction with a self-supervised pre-training method, we show the capabilities of the approach through a visualization of the representation space and case retrieval. Furthermore, the pre-trained model is fine-tuned to multiple process prediction tasks and demonstrates its effectiveness in comparison with existing approaches.
This study proposes an innovative explainable predictive quality analytics solution to facilitate data-driven decision-making for process planning in manufacturing by combining process mining, machine learning, and explainable artificial intelligence (XAI) methods. For this purpose, after integrating the top-floor and shop-floor data obtained from various enterprise information systems, a deep learning model was applied to predict the process outcomes. Since this study aims to operationalize the delivered predictive insights by embedding them into decision-making processes, it is essential to generate relevant explanations for domain experts. To this end, two complementary local post-hoc explanation approaches, Shapley values and Individual Conditional Expectation (ICE) plots are adopted, which are expected to enhance the decision-making capabilities by enabling experts to examine explanations from different perspectives. After assessing the predictive strength of the applied deep neural network with relevant binary classification evaluation measures, a discussion of the generated explanations is provided.
Process mining enables the reconstruction and evaluation of business processes based on digital traces in IT systems. An increasingly important technique in this context is process prediction. Given a sequence of events of an ongoing trace, process prediction allows forecasting upcoming events or performance measurements. In recent years, multiple process prediction approaches have been proposed, applying different data processing schemes and prediction algorithms. This study focuses on deep learning algorithms since they seem to outperform their machine learning alternatives consistently. Whilst having a common learning algorithm, they use different data preprocessing techniques, implement a variety of network topologies and focus on various goals such as outcome prediction, time prediction or control-flow prediction. Additionally, the set of log-data, evaluation metrics and baselines used by the authors diverge, making the results hard to compare. This paper attempts to synthesise the advantages and disadvantages of the procedural decisions in these approaches by conducting a systematic literature review.
Modern and next generation digital infrastructures are technically based on service oriented structures, cloud services, and other architectures that compose large systems from smaller subsystems. The composition of subsystems is particularly challenging, as the subsystems themselves may be represented in different languages, modelling methods, etc. It is quite challenging to precisely conceive, understand, and represent this kind of technology, in particular for a given level of abstraction. To capture refinement and abstraction principles, various forms of "technology stacks" and other semi-formal or natural language based on presentations have been suggested. Generally, useful concepts to compose such systems in a systematic way are even more rare. Heraklit provides means, principles, and unifying techniques to model and to analyze digital infrastructures. Heraklit integrates composition and hierarchies of subsystems, concrete and abstract data structures, as well as descriptions of behaviour. A distinguished set of means supports the modeler to express their ideas. The modeller is free to choose the level of abstraction, as well as the kind of composition. Heraklit integrates new concepts with tried and tested ones. Such a framework provides the foundation for a comprehensive Systems Mining as the next step after Process Mining.
The contemporary process-aware information systems possess the capabilities to record the activities generated during the process execution. To leverage these process specific fine-granular data, process mining has recently emerged as a promising research discipline. As an important branch of process mining, predictive business process management, pursues the objective to generate forward-looking, predictive insights to shape business processes. In this study, we propose a conceptual framework sought to establish and promote understanding of decision-making environment, underlying business processes and nature of the user characteristics for developing explainable business process prediction solutions. Consequently, with regard to the theoretical and practical implications of the framework, this study proposes a novel local post-hoc explanation approach for a deep learning classifier that is expected to facilitate the domain experts in justifying the model decisions. In contrary to alternative popular perturbation-based local explanation approaches, this study defines the local regions from the validation dataset by using the intermediate latent space representations learned by the deep neural networks. To validate the applicability of the proposed explanation method, the real-life process log data delivered by the Volvo IT Belgium's incident management system are used.The adopted deep learning classifier achieves a good performance with the Area Under the ROC Curve of 0.94. The generated local explanations are also visualized and presented with relevant evaluation measures that are expected to increase the users' trust in the black-box-model.
Predicting the next activity of a running process is an important aspect of process management. Recently, artificial neural networks, so called deep-learning approaches, have been proposed to address this challenge. This demo paper describes a software application that applies the Tensorflow deep-learning framework to process prediction. The software application reads industry-standard XES files for training and presents the user with an easy-to-use graphical user interface for both training and prediction. The system provides several improvements over earlier work. This demo paper focuses on the software implementation and describes the architecture and user interface.
Predicting business process behaviour is an important aspect of business process management. Motivated by research in natural language processing, this paper describes an application of deep learning with recurrent neural networks to the problem of predicting the next event in a business process. This is both a novel method in process prediction, which has largely relied on explicit process models, and also a novel application of deep learning methods. The approach is evaluated on two real datasets and our results surpass the state-of-the-art in prediction precision.