arXiv subjects

Jana-Rebecca Rehse

Publications and source records attributed to Jana-Rebecca Rehse.

13 recordsLinked to original sources

arXiv2025

Remaining Time Prediction in Outbound Warehouse Processes: A Case Study (Short Paper)

Predictive process monitoring is a sub-domain of process mining which aims to forecast the future of ongoing process executions. One common prediction target is the remaining time, meaning the time that will elapse until a process execution is completed. In this paper, we compare four different remaining time prediction approaches in a real-life outbound warehouse process of a logistics company in the aviation business. For this process, the company provided us with a novel and original event log with 169,523 traces, which we can make publicly available. Unsurprisingly, we find that deep learning models achieve the highest accuracy, but shallow methods like conventional boosting techniques achieve competitive accuracy and require significantly fewer computational resources.

cs.AI↗

arXiv2025

A Task Taxonomy for Conformance Checking

Conformance checking is a sub-discipline of process mining, which compares observed process traces with a process model to analyze whether the process execution conforms with or deviates from the process design. Organizations can leverage this analysis, for example to check whether their processes comply with internal or external regulations or to identify potential improvements. Gaining these insights requires suitable visualizations, which make complex results accessible and actionable. So far, however, the development of conformance checking visualizations has largely been left to tool vendors. As a result, current tools offer a wide variety of visual representations for conformance checking, but the analytical purposes they serve often remain unclear. However, without a systematic understanding of these purposes, it is difficult to evaluate the visualizations' usefulness. Such an evaluation hence requires a deeper understanding of conformance checking as an analysis domain. To this end, we propose a task taxonomy, which categorizes the tasks that can occur when conducting conformance checking analyses. This taxonomy supports researchers in determining the purpose of visualizations, specifying relevant conformance checking tasks in terms of their goal, means, constraint type, data characteristics, data target, and data cardinality. Combining concepts from process mining and visual analytics, we address researchers from both disciplines to enable and support closer collaborations.

cs.SE↗

arXiv2025

A Procedural Framework for Assessing the Desirability of Process Deviations

Conformance checking techniques help process analysts to identify where and how process executions deviate from a process model. However, they cannot determine the desirability of these deviations, i.e., whether they are problematic, acceptable or even beneficial for the process. Such desirability assessments are crucial to derive actions, but process analysts typically conduct them in a manual, ad-hoc way, which can be time-consuming, subjective, and irreplicable. To address this problem, this paper presents a procedural framework to guide process analysts in systematically assessing deviation desirability. It provides a step-by-step approach for identifying which input factors to consider in what order to categorize deviations into mutually exclusive desirability categories, each linked to action recommendations. The framework is based on a review and conceptualization of existing literature on deviation desirability, which is complemented by empirical insights from interviews with process analysis practitioners and researchers. We evaluate the framework through a desirability assessment task conducted with practitioners, indicating that the framework effectively enables them to streamline the assessment for a thorough yet concise evaluation.

cs.SE↗

arXiv2025

Detecting Undesired Process Behavior by Means of Retrieval Augmented Generation

Conformance checking techniques detect undesired process behavior by comparing process executions that are recorded in event logs to desired behavior that is captured in a dedicated process model. If such models are not available, conformance checking techniques are not applicable, but organizations might still be interested in detecting undesired behavior in their processes. To enable this, existing approaches use Large Language Models (LLMs), assuming that they can learn to distinguish desired from undesired behavior through fine-tuning. However, fine-tuning is highly resource-intensive and the fine-tuned LLMs often do not generalize well. To address these limitations, we propose an approach that requires neither a dedicated process model nor resource-intensive fine-tuning to detect undesired process behavior. Instead, we use Retrieval Augmented Generation (RAG) to provide an LLM with direct access to a knowledge base that contains both desired and undesired process behavior from other processes, assuming that the LLM can transfer this knowledge to the process at hand. Our evaluation shows that our approach outperforms fine-tuned LLMs in detecting undesired behavior, demonstrating that RAG is a viable alternative to resource-intensive fine-tuning, particularly when enriched with relevant context from the event log, such as frequent traces and activities.

cs.LG↗

arXiv2025

Identifying Process Improvement Opportunities through Process Execution Benchmarking

Benchmarking functionalities in current commercial process mining tools allow organizations to contextualize their process performance through high-level performance indicators, such as completion rate or throughput time. However, they do not suggest any measures to close potential performance gaps. To address this limitation, we propose a prescriptive technique for process execution benchmarking that recommends targeted process changes to improve process performance. The technique compares an event log from an ``own'' process to one from a selected benchmark process to identify potential activity replacements, based on behavioral similarity. It then evaluates each proposed change in terms of its feasibility and its estimated performance impact. The result is a list of potential process modifications that can serve as evidence-based decision support for process improvement initiatives.

cs.SE↗

arXiv2023

A Discussion on Generalization in Next-Activity Prediction

Next activity prediction aims to forecast the future behavior of running process instances. Recent publications in this field predominantly employ deep learning techniques and evaluate their prediction performance using publicly available event logs. This paper presents empirical evidence that calls into question the effectiveness of these current evaluation approaches. We show that there is an enormous amount of example leakage in all of the commonly used event logs, so that rather trivial prediction approaches perform almost as well as ones that leverage deep learning. We further argue that designing robust evaluations requires a more profound conceptual engagement with the topic of next-activity prediction, and specifically with the notion of generalization to new data. To this end, we present various prediction scenarios that necessitate different types of generalization to guide future research.

cs.LG↗

arXiv2023

Large Language Models can accomplish Business Process Management Tasks

Business Process Management (BPM) aims to improve organizational activities and their outcomes by managing the underlying processes. To achieve this, it is often necessary to consider information from various sources, including unstructured textual documents. Therefore, researchers have developed several BPM-specific solutions that extract information from textual documents using Natural Language Processing techniques. These solutions are specific to their respective tasks and cannot accomplish multiple process-related problems as a general-purpose instrument. However, in light of the recent emergence of Large Language Models (LLMs) with remarkable reasoning capabilities, such a general-purpose instrument with multiple applications now appears attainable. In this paper, we illustrate how LLMs can accomplish text-related BPM tasks by applying a specific LLM to three exemplary tasks: mining imperative process models from textual descriptions, mining declarative process models from textual descriptions, and assessing the suitability of process tasks from textual descriptions for robotic process automation. We show that, without extensive configuration or prompt engineering, LLMs perform comparably to or better than existing solutions and discuss implications for future BPM research as well as practical usage.

cs.CL↗

arXiv2022

AI-Augmented Business Process Management Systems: A Research Manifesto

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.

cs.AI↗

arXiv2022

Process Mining Meets Visual Analytics: The Case of Conformance Checking

Conformance checking is a major function of process mining, which allows organizations to identify and alleviate potential deviations from the intended process behavior. To fully leverage its benefits, it is important that conformance checking results are visualized in a way that is approachable and understandable for non-expert users. However, the visualization of conformance checking results has so far not been widely considered in research. Therefore, the goal of this paper is to develop an understanding of how conformance checking results are visualized by process mining tools to provide a foundation for further research on this topic. We conduct a systematic study, where we analyze the visualization capabilities of nine academic and seven commercial tools by means of a visual analytics framework. In this study, we find that the ''Why?'' aspect of conformance checking visualization seems already be well-defined, but the ''What?'' and ''How?'' aspects require future research.

cs.SE↗

arXiv2022

SAP Signavio Academic Models: A Large Process Model Dataset

In this paper, we introduce the SAP Signavio Academic Models (SAP-SAM) dataset, a collection of hundreds of thousands of business models, mainly process models in BPMN notation. The model collection is a subset of the models that were created over the course of roughly a decade on academic.signavio.com, a free-of-charge software-as-a-service platform that researchers, teachers, and students can use to create business (process) models. We provide a preliminary analysis of the model collection, as well as recommendations on how to work with it. In addition, we discuss potential use cases and limitations of the model collection from academic and industry perspectives.

cs.OH↗

arXiv2022

A Reference Data Model for Process-Related User Interaction Logs

User interaction (UI) logs are high-resolution event logs that record low-level activities performed by a user during the execution of a task in an information system. Each event in a UI log corresponds to a single interaction between the user and the interface, such as clicking a button or entering a string into a text field. UI logs are used for purposes like task mining or robotic process automation (RPA), but each study and tool relies on a different conceptualization and implementation of the elements and attributes that constitute user interactions. This lack of standardization makes it difficult to integrate UI logs from different sources and to combine tools for UI data collection with downstream analytics or automation solutions. To address this, we propose a universally applicable reference data model for process-related UI logs. Based on a review of scientific literature and industry solutions, this model includes the core attributes of UI logs, but remains flexible with regard to the scope, level of abstraction, and case notion. We provide an implementation of the model as an extension to the XES interchange standard for event logs and demonstrate its practical applicability in a real-life RPA scenario.

cs.AI↗

arXiv2017

XES Tensorflow - Process Prediction using the Tensorflow Deep-Learning Framework

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.

cs.LG↗

arXiv2017

Predicting Process Behaviour using Deep Learning

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.

cs.LG↗