Dirk Fahland

Urszula Jessen, Michal Sroka, Dirk Fahland

This research investigates the application of Large Language Models (LLMs) to augment conversational agents in process mining, aiming to tackle its inherent complexity and diverse skill requirements. While LLM advancements present novel opportunities for conversational process mining, generating efficient outputs is still a hurdle. We propose an innovative approach that amend many issues in existing solutions, informed by prior research on Natural Language Processing (NLP) for conversational agents. Leveraging LLMs, our framework improves both accessibility and agent performance, as demonstrated by experiments on public question and data sets. Our research sets the stage for future explorations into LLMs' role in process mining and concludes with propositions for enhancing LLM memory, implementing real-time user testing, and examining diverse data sets.

Viara Popova, Dirk Fahland, Marlon Dumas

Artifact-centric modeling is a promising approach for modeling business processes based on the so-called business artifacts - key entities driving the company's operations and whose lifecycles define the overall business process. While artifact-centric modeling shows significant advantages, the overwhelming majority of existing process mining methods cannot be applied (directly) as they are tailored to discover monolithic process models. This paper addresses the problem by proposing a chain of methods that can be applied to discover artifact lifecycle models in Guard-Stage-Milestone notation. We decompose the problem in such a way that a wide range of existing (non-artifact-centric) process discovery and analysis methods can be reused in a flexible manner. The methods presented in this paper are implemented as software plug-ins for ProM, a generic open-source framework and architecture for implementing process mining tools.

Dirk Fahland, Fabiana Fournier, Lior Limonad et al.

Large Language Models (LLMs) are trained on a vast amount of text to interpret and generate human-like textual content. They are becoming a vital vehicle in realizing the vision of the autonomous enterprise, with organizations today actively adopting LLMs to automate many aspects of their operations. LLMs are likely to play a prominent role in future AI-augmented business process management systems, catering functionalities across all system lifecycle stages. One such system's functionality is Situation-Aware eXplainability (SAX), which relates to generating causally sound and human-interpretable explanations. In this paper, we present the SAX4BPM framework developed to generate SAX explanations. The SAX4BPM suite consists of a set of services and a central knowledge repository. The functionality of these services is to elicit the various knowledge ingredients that underlie SAX explanations. A key innovative component among these ingredients is the causal process execution view. In this work, we integrate the framework with an LLM to leverage its power to synthesize the various input ingredients for the sake of improved SAX explanations. Since the use of LLMs for SAX is also accompanied by a certain degree of doubt related to its capacity to adequately fulfill SAX along with its tendency for hallucination and lack of inherent capacity to reason, we pursued a methodological evaluation of the perceived quality of the generated explanations. We developed a designated scale and conducted a rigorous user study. Our findings show that the input presented to the LLMs aided with the guard-railing of its performance, yielding SAX explanations having better-perceived fidelity. This improvement is moderated by the perception of trust and curiosity. More so, this improvement comes at the cost of the perceived interpretability of the explanation.

Marlon Dumas, Fabiana Fournier, Lior Limonad et al.

AI-Augmented Business Process Management Systems (ABPMSs) are an emerging class of process-aware information systems, empowered by trustworthy AI technology. An ABPMS enhances the execution of business processes with the aim of making these processes more adaptable, proactive, explainable, and context-sensitive. This manifesto presents a vision for ABPMSs and discusses research challenges that need to be surmounted to realize this vision. To this end, we define the concept of ABPMS, we outline the lifecycle of processes within an ABPMS, we discuss core characteristics of an ABPMS, and we derive a set of challenges to realize systems with these characteristics.

Dennis Brons, Roeland Scheepens, Dirk Fahland

Numerous process discovery techniques exist for generating process models that describe recorded executions of business processes. The models are meant to generalize executions into human-understandable modeling patterns, notably parallelism, and enable rigorous analysis of process deviations. However, well-defined models with parallelism returned by existing techniques are often too complex or generalize the recorded behavior too strongly to be trusted in a practical business context. We bridge this gap by introducing the Probabilistic Inductive Miner (PIM) based on the Inductive Miner framework. PIM compares in each step the most probable operators and structures based on frequency information in the data, which results in block-structured models with significantly higher accuracy. All design choices in PIM are based on business context requirements obtained through a user study with industrial process mining experts. PIM is evaluated quantitatively and in an novel kind of empirical study comparing users' trust in discovered model structures. The evaluations show that PIM strikes a unique trade-off between model accuracy and model complexity, that is conclusively preferred by users over all state-of-the-art process discovery methods.

Dominique Sommers, Vlado Menkovski, Dirk Fahland

Automatically discovering a process model from an event log is the prime problem in process mining. This task is so far approached as an unsupervised learning problem through graph synthesis algorithms. Algorithmic design decisions and heuristics allow for efficiently finding models in a reduced search space. However, design decisions and heuristics are derived from assumptions about how a given behavioral description - an event log - translates into a process model and were not learned from actual models which introduce biases in the solutions. In this paper, we explore the problem of supervised learning of a process discovery technique D. We introduce a technique for training an ML-based model D using graph convolutional neural networks; D translates a given input event log into a sound Petri net. We show that training D on synthetically generated pairs of input logs and output models allows D to translate previously unseen synthetic and several real-life event logs into sound, arbitrarily structured models of comparable accuracy and simplicity as existing state of the art techniques for discovering imperative process models. We analyze the limitations of the proposed technique and outline alleys for future work.

Dirk Fahland, Vadim Denisov, Wil. M. P. van der Aalst

To identify the causes of performance problems or to predict process behavior, it is essential to have correct and complete event data. This is particularly important for distributed systems with shared resources, e.g., one case can block another case competing for the same machine, leading to inter-case dependencies in performance. However, due to a variety of reasons, real-life systems often record only a subset of all events taking place. To understand and analyze the behavior and performance of processes with shared resources, we aim to reconstruct bounds for timestamps of events in a case that must have happened but were not recorded by inference over events in other cases in the system. We formulate and solve the problem by systematically introducing multi-entity concepts in event logs and process models. We introduce a partial-order based model of a multi-entity event log and a corresponding compositional model for multi-entity processes. We define PQR-systems as a special class of multi-entity processes with shared resources and queues. We then study the problem of inferring from an incomplete event log unobserved events and their timestamps that are globally consistent with a PQR-system. We solve the problem by reconstructing unobserved traces of resources and queues according to the PQR-model and derive bounds for their timestamps using a linear program. While the problem is illustrated for material handling systems like baggage handling systems in airports, the approach can be applied to other settings where recording is incomplete. The ideas have been implemented in ProM and were evaluated using both synthetic and real-life event logs.

Daniel Reißner, Abel Armas-Cervantes, Raffaele Conforti et al.

Given a model of the expected behavior of a business process and an event log recording its observed behavior, the problem of business process conformance checking is that of identifying and describing the differences between the model and the log. A desirable feature of a conformance checking technique is to identify a minimal yet complete set of differences. Existing conformance checking techniques that fulfil this property exhibit limited scalability when confronted to large and complex models and logs. This paper presents two complementary techniques to address these shortcomings. The first technique transforms the model and log into two automata. These automata are compared using an error-correcting synchronized product, computed via an A* that guarantees the resulting automaton captures all differences with a minimal amount of error corrections. The synchronized product is used to extract minimal-length alignments between each trace of the log and the closest corresponding trace of the model. A limitation of the first technique is that as the level of concurrency in the model increases, the size of the automaton of the model grows exponentially, thus hampering scalability. To address this limitation, the paper proposes a second technique wherein the process model is first decomposed into a set of automata, known as S-components, such that the product of these automata is equal to the automaton of the whole process model. An error-correcting product is computed for each S-component separately and the resulting automata are recomposed into a single product automaton capturing all differences without minimality guarantees. An empirical evaluation shows that the proposed techniques outperform state-of-the-art baselines in terms of computational efficiency. Moreover, the decomposition-based technique is optimal for the vast majority of datasets and quasi-optimal for the remaining ones.

Niek Tax, Xixi Lu, Natalia Sidorova et al.

In process mining, precision measures are used to quantify how much a process model overapproximates the behavior seen in an event log. Although several measures have been proposed throughout the years, no research has been done to validate whether these measures achieve the intended aim of quantifying over-approximation in a consistent way for all models and logs. This paper fills this gap by postulating a number of axioms for quantifying precision consistently for any log and any model. Further, we show through counter-examples that none of the existing measures consistently quantifies precision.

Jan Claes, Irene Vanderfeesten, Hajo A. Reijers et al.

In an investigation into the process of process modeling, we examined how modeling behavior relates to the quality of the process model that emerges from that. Specifically, we considered whether (i) a modeler's structured modeling style, (ii) the frequency of moving existing objects over the modeling canvas, and (iii) the overall modeling speed is in any way connected to the ease with which the resulting process model can be understood. In this paper, we describe the exploratory study to build these three conjectures, clarify the experimental set-up and infrastructure that was used to collect data, and explain the used metrics for the various concepts to test the conjectures empirically. We discuss various implications for research and practice from the conjectures, all of which were confirmed by the experiment.

Jakob Pinggera, Pnina Soffer, Stefan Zugal et al.

Research on quality issues of business process models has recently begun to explore the process of creating process models. As a consequence, the question arises whether different ways of creating process models exist. In this vein, we observed 115 students engaged in the act of modeling, recording all their interactions with the modeling environment using a specialized tool. The recordings of process modeling were subsequently clustered. Results presented in this paper suggest the existence of three distinct modeling styles, exhibiting significantly different characteristics. We believe that this finding constitutes another building block toward a more comprehensive understanding of the process of process modeling that will ultimately enable us to support modelers in creating better business process models.