arXiv subjects

Wil van der Aalst

Publications and source records attributed to Wil van der Aalst.

At least 19 recordsLinked to original sources

arXiv2025

Discriminative Rule Learning for Outcome-Guided Process Model Discovery

Event logs extracted from information systems offer a rich foundation for understanding and improving business processes. In many real-world applications, it is possible to distinguish between desirable and undesirable process executions, where desirable traces reflect efficient or compliant behavior, and undesirable ones may involve inefficiencies, rule violations, delays, or resource waste. This distinction presents an opportunity to guide process discovery in a more outcome-aware manner. Discovering a single process model without considering outcomes can yield representations poorly suited for conformance checking and performance analysis, as they fail to capture critical behavioral differences. Moreover, prioritizing one behavior over the other may obscure structural distinctions vital for understanding process outcomes. By learning interpretable discriminative rules over control-flow features, we group traces with similar desirability profiles and apply process discovery separately within each group. This results in focused and interpretable models that reveal the drivers of both desirable and undesirable executions. The approach is implemented as a publicly available tool and it is evaluated on multiple real-life event logs, demonstrating its effectiveness in isolating and visualizing critical process patterns.

cs.AI↗

arXiv2025

Integrating Domain Knowledge into Process Discovery Using Large Language Models

Process discovery aims to derive process models from event logs, providing insights into operational behavior and forming a foundation for conformance checking and process improvement. However, models derived solely from event data may not accurately reflect the real process, as event logs are often incomplete or affected by noise, and domain knowledge, an important complementary resource, is typically disregarded. As a result, the discovered models may lack reliability for downstream tasks. We propose an interactive framework that incorporates domain knowledge, expressed in natural language, into the process discovery pipeline using Large Language Models (LLMs). Our approach leverages LLMs to extract declarative rules from textual descriptions provided by domain experts. These rules are used to guide the IMr discovery algorithm, which recursively constructs process models by combining insights from both the event log and the extracted rules, helping to avoid problematic process structures that contradict domain knowledge. The framework coordinates interactions among the LLM, domain experts, and a set of backend services. We present a fully implemented tool that supports this workflow and conduct an extensive evaluation of multiple LLMs and prompt engineering strategies. Our empirical study includes a case study based on a real-life event log with the involvement of domain experts, who assessed the usability and effectiveness of the framework.

cs.AI↗

arXiv2025

Online Discovery of Simulation Models for Evolving Business Processes (Extended Version)

Business Process Simulation (BPS) refers to techniques designed to replicate the dynamic behavior of a business process. Many approaches have been proposed to automatically discover simulation models from historical event logs, reducing the cost and time to manually design them. However, in dynamic business environments, organizations continuously refine their processes to enhance efficiency, reduce costs, and improve customer satisfaction. Existing techniques to process simulation discovery lack adaptability to real-time operational changes. In this paper, we propose a streaming process simulation discovery technique that integrates Incremental Process Discovery with Online Machine Learning methods. This technique prioritizes recent data while preserving historical information, ensuring adaptation to evolving process dynamics. Experiments conducted on four different event logs demonstrate the importance in simulation of giving more weight to recent data while retaining historical knowledge. Our technique not only produces more stable simulations but also exhibits robustness in handling concept drift, as highlighted in one of the use cases.

cs.SE↗

arXiv2025

eST$^2$ Miner -- Process Discovery Based on Firing Partial Orders

Process discovery generates process models from event logs. Traditionally, an event log is defined as a multiset of traces, where each trace is a sequence of events. The total order of the events in a sequential trace is typically based on their temporal occurrence. However, real-life processes are partially ordered by nature. Different activities can occur in different parts of the process and, thus, independently of each other. Therefore, the temporal total order of events does not necessarily reflect their causal order, as also causally unrelated events may be ordered in time. Only partial orders allow to express concurrency, duration, overlap, and uncertainty of events. Consequently, there is a growing need for process mining algorithms that can directly handle partially ordered input. In this paper, we combine two well-established and efficient algorithms, the eST Miner from the process mining community and the Firing LPO algorithm from the Petri net community, to introduce the eST$^2$ Miner. The eST$^2$ Miner is a process discovery algorithm that can directly handle partially ordered input, gives strong formal guarantees, offers good runtime and excellent space complexity, and can, thus, be used in real-life applications.

cs.DB↗

arXiv2025

Translating Workflow Nets into the Partially Ordered Workflow Language

The Partially Ordered Workflow Language (POWL) has recently emerged as a process modeling notation, offering strong quality guarantees and high expressiveness. However, its adoption is hindered by the prevalence of standard notations like workflow nets (WF-nets) and BPMN in practice. This paper presents a novel algorithm for transforming safe and sound WF-net into equivalent POWL models. The algorithm recursively identifies structural patterns within the WF-net and translates them into their POWL representation. We formally prove the correctness of our approach, showing that the generated POWL model preserves the language of the input WF-net. Furthermore, we demonstrate the high scalability of our algorithm, and we show its completeness on a subclass of WF-nets that encompasses equivalent representations for all POWL models. This work bridges the gap between the theoretical advantages of POWL and the practical need for compatibility with established notations, paving the way for broader adoption of POWL in process analysis and improvement applications.

cs.LO↗

arXiv2024

Evaluation of Study Plans using Partial Orders

In higher education, data is collected that indicate the term(s) that a course is taken and when it is passed. Often, study plans propose a suggested course order to students. Study planners can adjust these based on detected deviations between the proposed and actual order of the courses being taken. In this work, we detect deviations by combining (1) the deviation between the proposed and actual course order with (2) the temporal difference between the expected and actual course-taking term(s). Partially ordered alignments identify the deviations between the proposed and actual order. We compute a partial order alignment by modeling a study plan as a process model and a student's course-taking behavior as a partial order. Using partial orders in such use cases allows one to relax the constraints of strictly ordered traces. This makes our approach less prone to the order in which courses are offered. Further, when modeling course-taking behavior as partial orders, we propose distinguishing intended course-taking behavior from actual course-passing behavior of students by including either all terms in which a course is attempted or only the term that a course is passed, respectively. This provides more perspectives when comparing the proposed and actual course-taking behavior. The proposed deviation measuring approach is evaluated on real-life data from RWTH Aachen University.

cs.CY↗

arXiv2024

Bridging Domain Knowledge and Process Discovery Using Large Language Models

Discovering good process models is essential for different process analysis tasks such as conformance checking and process improvements. Automated process discovery methods often overlook valuable domain knowledge. This knowledge, including insights from domain experts and detailed process documentation, remains largely untapped during process discovery. This paper leverages Large Language Models (LLMs) to integrate such knowledge directly into process discovery. We use rules derived from LLMs to guide model construction, ensuring alignment with both domain knowledge and actual process executions. By integrating LLMs, we create a bridge between process knowledge expressed in natural language and the discovery of robust process models, advancing process discovery methodologies significantly. To showcase the usability of our framework, we conducted a case study with the UWV employee insurance agency, demonstrating its practical benefits and effectiveness.

cs.AI↗

arXiv2024

Imposing Rules in Process Discovery: an Inductive Mining Approach

Process discovery aims to discover descriptive process models from event logs. These discovered process models depict the actual execution of a process and serve as a foundational element for conformance checking, performance analyses, and many other applications. While most of the current process discovery algorithms primarily rely on a single event log for model discovery, additional sources of information, such as process documentation and domain experts' knowledge, remain untapped. This valuable information is often overlooked in traditional process discovery approaches. In this paper, we propose a discovery technique incorporating such knowledge in a novel inductive mining approach. This method takes a set of user-defined or discovered rules as input and utilizes them to discover enhanced process models. Our proposed framework has been implemented and tested using several publicly available real-life event logs. Furthermore, to showcase the framework's effectiveness in a practical setting, we conducted a case study in collaboration with UWV, the Dutch employee insurance agency.

cs.FL↗

arXiv2024

Process Variant Analysis Across Continuous Features: A Novel Framework

Extracted event data from information systems often contain a variety of process executions making the data complex and difficult to comprehend. Unlike current research which only identifies the variability over time, we focus on other dimensions that may play a role in the performance of the process. This research addresses the challenge of effectively segmenting cases within operational processes based on continuous features, such as duration of cases, and evaluated risk score of cases, which are often overlooked in traditional process analysis. We present a novel approach employing a sliding window technique combined with the earth mover's distance to detect changes in control flow behavior over continuous dimensions. This approach enables case segmentation, hierarchical merging of similar segments, and pairwise comparison of them, providing a comprehensive perspective on process behavior. We validate our methodology through a real-life case study in collaboration with UWV, the Dutch employee insurance agency, demonstrating its practical applicability. This research contributes to the field by aiding organizations in improving process efficiency, pinpointing abnormal behaviors, and providing valuable inputs for process comparison, and outcome prediction.

cs.SE↗

arXiv2024

People Make Better Edits: Measuring the Efficacy of LLM-Generated Counterfactually Augmented Data for Harmful Language Detection

NLP models are used in a variety of critical social computing tasks, such as detecting sexist, racist, or otherwise hateful content. Therefore, it is imperative that these models are robust to spurious features. Past work has attempted to tackle such spurious features using training data augmentation, including Counterfactually Augmented Data (CADs). CADs introduce minimal changes to existing training data points and flip their labels; training on them may reduce model dependency on spurious features. However, manually generating CADs can be time-consuming and expensive. Hence in this work, we assess if this task can be automated using generative NLP models. We automatically generate CADs using Polyjuice, ChatGPT, and Flan-T5, and evaluate their usefulness in improving model robustness compared to manually-generated CADs. By testing both model performance on multiple out-of-domain test sets and individual data point efficacy, our results show that while manual CADs are still the most effective, CADs generated by ChatGPT come a close second. One key reason for the lower performance of automated methods is that the changes they introduce are often insufficient to flip the original label.

cs.CL↗

arXiv2023

Tailoring Machine Learning for Process Mining

Machine learning models are routinely integrated into process mining pipelines to carry out tasks like data transformation, noise reduction, anomaly detection, classification, and prediction. Often, the design of such models is based on some ad-hoc assumptions about the corresponding data distributions, which are not necessarily in accordance with the non-parametric distributions typically observed with process data. Moreover, the learning procedure they follow ignores the constraints concurrency imposes to process data. Data encoding is a key element to smooth the mismatch between these assumptions but its potential is poorly exploited. In this paper, we argue that a deeper insight into the issues raised by training machine learning models with process data is crucial to ground a sound integration of process mining and machine learning. Our analysis of such issues is aimed at laying the foundation for a methodology aimed at correctly aligning machine learning with process mining requirements and stimulating the research to elaborate in this direction.

cs.LG↗

arXiv2023

Discovering Process Models that Support Desired Behavior and Avoid Undesired Behavior

Process discovery is one of the primary process mining tasks and starting point for process improvements using event data. Existing process discovery techniques aim to find process models that best describe the observed behavior. The focus can be on recall (i.e., replay fitness) or precision. Here, we take a different perspective. We aim to discover a process model that allows for the good behavior observed, and does not allow for the bad behavior. In order to do this, we assume that we have a desirable event log ($L^+$) and an undesirable event log ($L^-$). For example, the desirable event log consists of the cases that were handled within two weeks, and the undesirable event log consists of the cases that took longer. Our discovery approach explores the tradeoff between supporting the cases in the desirable event log and avoiding the cases in the undesirable event log. The proposed framework uses a new inductive mining approach that has been implemented and tested on several real-life event logs. Experimental results show that our approach outperforms other approaches that use only the desirable event log ($L^+$). This supports the intuitive understanding that problematic cases can and should be used to improve processes.

cs.DB↗

arXiv2022

Interactive Process Identification and Selection from SAP ERP

SAP ERP is one of the most popular information systems supporting various organizational processes, e.g., O2C and P2P. However, the amount of processes and data contained in SAP ERP is enormous. Thus, the identification of the processes that are contained in a specific SAP instance, and the creation of a list of related tables is a significant challenge. Eventually, one needs to extract an event log for process mining purposes from SAP ERP. This demo paper shows the tool Interactive SAP Explorer that tackles the process identification and selection problem by encoding the relational structure of SAP ERP in a labeled property graph. Our approach allows asking complex process-related queries along with advanced representations of the relational structure.

cs.DB↗

arXiv2022

Enhancing Data-Awareness of Object-Centric Event Logs

When multiple objects are involved in a process, there is an opportunity for processes to be discovered from different angles with new information that previously might not have been analyzed from a single object point of view. This does require that all the information of event/object attributes and their values are stored within logs including attributes that have a list of values or attributes with values that change over time. It also requires that attributes can unambiguously be linked to an object, an event or both. As such, object-centric event logs are an interesting development in process mining as they support the presence of multiple types of objects. First, this paper shows that the current object-centric event log formats do not support the aforementioned aspects to their full potential since the possibility to support dynamic object attributes (attributes with changing values) is not supported by existing formats. Next, this paper introduces a novel enriched object-centric event log format tackling the aforementioned issues alongside an algorithm that automatically translates XES logs to this Data-aware OCEL (DOCEL) format.

cs.DB↗

arXiv2022

A Combined Approach of Process Mining and Rule-based AI for Study Planning and Monitoring in Higher Education

This paper presents an approach of using methods of process mining and rule-based artificial intelligence to analyze and understand study paths of students based on campus management system data and study program models. Process mining techniques are used to characterize successful study paths, as well as to detect and visualize deviations from expected plans. These insights are combined with recommendations and requirements of the corresponding study programs extracted from examination regulations. Here, event calculus and answer set programming are used to provide models of the study programs which support planning and conformance checking while providing feedback on possible study plan violations. In its combination, process mining and rule-based artificial intelligence are used to support study planning and monitoring by deriving rules and recommendations for guiding students to more suitable study paths with higher success rates. Two applications will be implemented, one for students and one for study program designers.

cs.AI↗

arXiv2022

OC-PM: Analyzing Object-Centric Event Logs and Process Models

Object-centric process mining is a novel branch of process mining that aims to analyze event data from mainstream information systems (such as SAP) more naturally, without being forced to form mutually exclusive groups of events with the specification of a case notion. The development of object-centric process mining is related to exploiting object-centric event logs, which includes exploring and filtering the behavior contained in the logs and constructing process models which can encode the behavior of different classes of objects and their interactions (which can be discovered from object-centric event logs). This paper aims to provide a broad look at the exploration and processing of object-centric event logs to discover information related to the lifecycle of the different objects composing the event log. Also, comprehensive tool support (OC-PM) implementing the proposed techniques is described in the paper.

cs.DB↗

arXiv2022

Six Levels of Autonomous Process Execution Management (APEM)

Terms such as the Digital Twin of an Organization (DTO) and Hyperautomation (HA) illustrate the desire to autonomously manage and orchestrate processes, just like we aim for autonomously driving cars. Autonomous driving and Autonomous Process Execution Management (APEM) have in common that the goals are pretty straightforward and that each year progress is made, but fully autonomous driving and fully autonomous process execution are more a dream than a reality. For cars, the Society of Automotive Engineers (SAE) identified six levels (0-5), ranging from no driving automation (SAE, Level 0) to full driving automation (SAE, Level 5). This short article defines six levels of Autonomous Process Execution Management (APEM). The goal is to show that the transition from one level to the next will be gradual, just like for self-driving cars.

cs.CY↗

arXiv2021

Case Level Counterfactual Reasoning in Process Mining

Process mining is widely used to diagnose processes and uncover performance and compliance problems. It is also possible to see relations between different behavioral aspects, e.g., cases that deviate more at the beginning of the process tend to get delayed in the later part of the process. However, correlations do not necessarily reveal causalities. Moreover, standard process mining diagnostics do not indicate how to improve the process. This is the reason we advocate the use of structural equation models and counterfactual reasoning. We use results from causal inference and adapt these to be able to reason over event logs and process interventions. We have implemented the approach as a ProM plug-in and have evaluated it on several data sets.

cs.AI↗