Event data extracted from information systems serves as the foundation for process mining, enabling the extraction of insights and identification of improvements. Process discovery focuses on deriving descriptive process models from event logs, which form the basis for conformance checking, performance analysis, and other applications. Traditional process discovery techniques predominantly rely on event logs, often overlooking supplementary information such as domain knowledge and process rules. These rules, which define relationships between activities, can be obtained through automated techniques like declarative process discovery or provided by domain experts based on process specifications. When used as an additional input alongside event logs, such rules have significant potential to guide process discovery. However, leveraging rules to discover high-quality imperative process models, such as BPMN models and Petri nets, remains an underexplored area in the literature. To address this gap, we propose an enhanced framework, IMr, which integrates discovered or user-defined rules into the process discovery workflow via a novel recursive approach. The IMr framework employs a divide-and-conquer strategy, using rules to guide the selection of process structures at each recursion step in combination with the input event log. We evaluate our approach on several real-world event logs and demonstrate that the discovered models better align with the provided rules without compromising their conformance to the event log. Additionally, we show that high-quality rules can improve model quality across well-known conformance metrics. This work highlights the importance of integrating domain knowledge into process discovery, enhancing the quality, interpretability, and applicability of the resulting process models.

This contribution revisits our article titled “A General Process Mining Framework for Correlating, Predicting, and Clustering Dynamic Behavior Based on Event Logs” accepted from the Information Systems journal in 2016. It reflects on how the proposed general framework for process mining has grown in relevance with the rise of AI, emphasizing its value as a extensible approach to transforming event data into analytical and predictive insights. It also discusses how the framework relevance and the underlying message remains valid, including for emerging research directions such as prescriptive analytics, causal and/or object-centric process mining.

Together with Information Systems, we celebrate the journal’s 50th anniversary and the 10th anniversary of our joint work on a systematic framework for compliance monitoring functionalities.

The field of process mining offers a range of techniques for evidence-based improvement of business processes. The quality of the process data used, as stored in so-called event logs, is paramount to the reliability and usefulness of the process mining outcomes. Due to the increased uptake, at scale and for more complex types of applications, the field of process mining has evolved and event logs now need to be object-centric rather than event-centric. To understand and manage the quality problems that can occur in object-centric event logs a systematic approach is required that is different from past investigations into event-centric logs. To this end, we adopt a pattern-based approach, a tried and tested method to characterise problems that are otherwise hard to capture. A new collection of patterns is presented for object-centric logs, where each pattern captures the nature of the problem, how its manifestation can be detected, and how the problem can be remedied. The pattern collection is validated through a multi-prong approach, i.e., evidence-based, literature-based, empirical, and user-based (with the process mining community). The results show that these patterns are perceived as important to identify and that they do occur in practical settings.

Business process management employs process models and event logs to represent the behavior of the information systems under study. Traditional case-centric notions consider the order of activities and events in isolated process instances. The emerging field of object-centric processes challenges this assumption by putting objects in the center. Object-centric process mining and modeling approaches identify the structure of co-evolving data objects that influence the behavior of an information system to provide a comprehensive view of the system behavior. Object-centricity has been investigated independently in process modeling and in process mining, which resulted in the coexistence of seemingly contradictory assumptions and definitions. As a community effort, this research manifesto relates and aligns existing terminologies, definitions, and perspectives to provide a common ground for current and future research in object-centric business process management. Based on the current state of research, we propose a conceptualization that sets process models and event logs in relation to the information system’s behavior and the execution data it generates. The conceptualization aims at aligning different terminologies and, thus, providing a basis to model and analyze behavioral characteristics. Building on this common ground, we identify open research challenges along the most relevant research areas in object-centric process management. For each research area, its current status is investigated and an outline of the most relevant research challenges is presented.

Abstract This paper presents a novel approach for generating actionable recommendations from educational event data collected by Campus Management Systems (CMS) to enhance study planning in higher education. The approach unfolds in three phases: feature identification tailored to the educational context, predictive modeling employing the RuleFit algorithm, and extracting actionable recommendations. We utilize diverse features, encompassing academic histories and course sequences, to capture the multi-dimensional nature of student academic behaviors. The effectiveness of our approach is empirically validated using data from the computer science bachelor’s program at RWTH Aachen University, with the goal of predicting overall GPA and formulating recommendations to enhance academic performance. Our contributions lie in the novel adaptation of behavioral features for the educational domain and the strategic use of the RuleFit algorithm for both predictive modeling and the generation of practical recommendations, offering a data-driven foundation for informed study planning and academic decision-making.

Abstract Local Process Models (LPMs) are an underexplored concept in process mining. LPMs describe patterns in event data considering sequence, choice, concurrency, and loop. In recent years, process mining has proved successful in the analysis and improvement of operational processes. More often than not, surprising findings are found when one does not consider the full process, making LPMs and their discovery highly valuable. However, similar to other pattern mining approaches, LPM discovery algorithms face the problems of model explosion and model repetition, i.e., the algorithms may create hundreds if not thousands of LPMs, and subsets of them are close in structure or behavior. Practically, no analyst would be able to comb through thousands of LPMs leading to using a sample of LPMs that are easily accessible. The current sentiment is that the top-scoring LPMs form the optimal sample to be presented. However, different applications should demand a different optimal sample. With this work, we show that if the goal of the mined LPMs is to understand a process, using the top-scoring LPMs as an optimal sample is a poor choice because of high repetition. We propose a framework for grouping LPMs and creating an optimal sample by taking one representative LPM for each group. We measure similarity between models via established process model similarity measures or by comparing the context in which an LPM appears. The context is formed using data attributes available in the underlying event logs. We demonstrate the usefulness of grouping on multiple event logs by comparing repetition and coverage between samples comprised of the top-scoring models and the representatives of discovered groups.

3835

Process mining techniques are useful for analyzing and optimizing processes. However, processes often exist in many variants that can differ significantly in their execution. These differences within the data can negatively affect the quality of process mining results and, furthermore, indicate disparities within the process. While several approaches exist that characterize the differences between processes, oftentimes the mere existence of differences can be problematic. To this end, techniques to prove or disprove the existence of such differences are required and should do so in a statistically sound manner. However, the literature on process hypothesis testing is sparse and limited in the considered dimensions of difference. In this paper, we propose a hypothesis testing approach that uses the earth mover’s distance in combination with a permutation test to compare event logs in various dimensions. The evaluation shows that the proposed approach achieves better performance than the existing work in detecting control-flow differences and, moreover, detects differences in further dimensions, demonstrated on the time dimension.

Business processes may span multiple organizations. For instance, cattle may move through several organizations in an agricultural supply chain, or patients may be seen by multiple healthcare providers as part of a treatment process. Optimizing these cross-organizational processes is an aim of process mining, however, process mining efforts may be challenged by commercially sensitive data or privacy laws, which may prevent the involved organizations from sharing recorded process data with one another. Federated process mining aims to perform inter-organizational analyses without information being shared across organizational borders. In this paper, we propose a federated technique to discover directly-follows graphs (DFGs), using homomorphic encryption, while keeping timestamps and activities secret. We evaluate the feasibility of our technique using real-life event logs to discover their DFGs and discuss potential attacks.

In recent years, the industry has been witnessing an extended usage of process mining and automated event data analysis. Consequently, there is a rising significance in addressing privacy apprehensions related to the inclusion of sensitive and private information within event data utilized by process mining algorithms. State-of-the-art research mainly focuses on providing quantifiable privacy guarantees, e.g., via differential privacy, for trace variants that are used by the main process mining techniques, e.g., process discovery. However, privacy preservation techniques designed for the release of trace variants are still insufficient to meet all the demands of industry-scale utilization. Moreover, ensuring privacy guarantees in situations characterized by a high occurrence of infrequent trace variants remains a challenging endeavor. In this paper, we introduce two novel approaches for releasing differentially private trace variants based on trained generative models. With TraVaG, we leverage Generative Adversarial Networks (GANs) to sample from a privatized implicit variant distribution. Our second method employs Denoising Diffusion Probabilistic Models that reconstruct artificial trace variants from noise via trained Markov chains. Both methods offer industry-scale benefits and elevate the degree of privacy assurances, particularly in scenarios featuring a substantial prevalence of infrequent variants. Also, they overcome the shortcomings of conventional privacy preservation techniques, such as bounding the length of variants and introducing fake variants. Experimental results on real-life event data demonstrate that our approaches surpass state-of-the-art techniques in terms of privacy guarantees and utility preservation.

In many real-world scenarios, processes naturally define partial orders over their constituent tasks. Partially ordered representations can be exploited in process discovery as they facilitate modeling such processes. The Partially Ordered Workflow Language (POWL) extends partially ordered representations with control-flow operators to support modeling common process constructs such as choice and loop structures. POWL integrates the hierarchical nature of process trees with the flexibility of partially ordered representations, opening up significant opportunities in process discovery. This paper presents and compares various approaches for the automated discovery of POWL models. We investigate the effects of applying varying validity criteria to partial orders, and we propose methods for incorporating frequency information to improve the quality of the discovered models. Additionally, we propose alternative visualizations for POWL models, offering different approaches that may be useful in various contexts. The discovery approaches are evaluated using various real-life data sets, demonstrating the ability of POWL models to capture complex process structures. • Employing different validity requirements in the discovery of POWL models. • Incorporating frequency-based filtering in the discovery of POWL models. • Enhancing the visualization of the discovered models. • Proving the soundness of the discovered models.

Conformance checking is a crucial aspect of process mining, where the main objective is to compare the actual execution of a process, as recorded in an event log, with a reference process model, e.g., in the form of a Petri net or a BPMN. Conformance checking enables identifying deviations, anomalies, or non-compliance instances. It offers different perspectives on problems in processes, bottlenecks, or process instances that are not compliant with the model. Performing conformance checking in federated (inter-organizational) settings allows organizations to gain insights into the overall process execution and to identify compliance issues across organizational boundaries, which facilitates process improvement efforts among collaborating entities. In this paper, we propose a privacy-aware federated conformance-checking approach that allows for evaluating the correctness of overall cross-organizational process models, identifying miscommunications , and quantifying their costs. For evaluation, we design and simulate a supply chain process with three organizations engaged in purchase-to-pay, order-to-cash, and shipment processes. We generate synthetic event logs for each organization as well as the complete process, and we apply our approach to identify and evaluate the cost of pre-injected miscommunications.

Abstract Process mining aids organisations in improving their operational processes by providing visualisations and algorithms that turn event data into insights. How often behaviour occurs in a process—the stochastic perspective—is important for simulation, recommendation, enhancement and other types of analysis. Although the stochastic perspective is important, the focus is often on control flow. Stochastic conformance checking techniques assess the quality of stochastic process models and/or event logs with one another. In this paper, we address three limitations of existing stochastic conformance checking techniques: inability to handle uncertain event data (e.g. events having only a date), exponential blow-up in computation time due to the analysis of all interleavings of concurrent behaviour and the problem that loops that can be unfolded infinitely often. To address these challenges, we provide bounds for conformance measures and use partial orders to encode behaviour. An open-source implementation is provided, which we use to illustrate and evaluate the practical feasibility of the approach.

Traditional process models like Petri nets effectively describe the control flow of processes but fail to capture stochastic information such as choice likelihoods. To address this, Stochastic Labeled Petri Nets (SPNs) have recently gained attention, extending Petri nets with transition weights that allow to associate executions with probabilities. The language of an SPN thereby becomes a probability distribution over traces (i.e., sequences of activities). To assess an SPN’s quality, Earth Mover’s Stochastic Conformance (EMSC) emerged as a natural metric that measures the similarity of the SPN’s trace distribution to the observed real-world distribution. In this paper, we propose a locally optimal approach for fine-tuning (or finding) transitions weights to maximize an SPN’s EMSC. Leveraging the relationship between EMSC and the Wasserstein distance, which recently gained attention as a loss function in machine learning, we compute subgradients for EMSC to optimize transition weights via subgradient descent. Besides, we propose a straightforward solution to handle models that allow for infinitely many traces. Our optimization approach is broadly applicable for EMSC—that is, for EMSC using arbitrary trace-to-trace distances—unlike existing works that either to not explicitly consider EMSC or only special variants. We demonstrate the applicability of our approach on several real-life event logs and discovery algorithms, comparing it to state-of-the-art stochastic process discovery methods and a recent full automated simulation approach.

Conformance checking focuses on quantifying behavioral differences between desired and observed process behavior. Stochastic conformance checking considers not only the desired control flow of a process but also the relative frequency of each sequence. State-of-the-art stochastic conformance measures either cannot gracefully handle partially matching traces or are prohibitively expensive to compute. This paper bridges this gap by introducing the stochastic Markovian abstraction. The abstraction is defined as the relative occurrences of sub-traces in a stochastic language. Two stochastic languages can be compared via their Markovian abstractions using existing language comparison techniques. We show how to compute this abstraction for bounded, livelock-free stochastic labeled Petri nets. One of its derived measures is qualitatively and quantitatively evaluated on a series of artificial and real-world datasets. The experiments show that the abstraction can be efficiently computed and is successful in handling partially mismatching traces.

Process models describe the desired or observed behaviour of organisations. In stochastic process mining, computational analysis of trace data yields process models which describe process paths and their probability of execution. To understand the quality of these models, and to compare them, quantitative quality measures are used. This research investigates model comparison empirically, using stochastic process models built from real-life logs. The experimental design collects a large number of models generated randomly and using process discovery techniques. Twenty-five different metrics are taken on these models, using both existing process model metrics and new, exploratory ones. The results are analysed quantitatively, making particular use of principal component analysis. Based on this analysis, we suggest three stochastic process model dimensions: adhesion, relevance and simplicity. We also suggest possible metrics for these dimensions, and demonstrate their use on example models.

The execution of operational processes generates event data stored in enterprise information systems. Process mining techniques analyze such event data to obtain insights vital for decision-makers to improve the reviewed process. In this context, event data visualizations are essential. We focus on visualizing variants describing process executions that are control flow equivalent. Such variants are an integral concept for process mining and are used, e.g., for data exploration and filtering. We propose high-level and low-level variants covering different levels of abstraction and present corresponding visualizations. Compared to existing variant visualizations, we support partially ordered event data and allow for heterogeneous temporal information per event, i.e., we support both time intervals and time points. We evaluate our contributions using automated experiments showing practical applicability to real-life event data. Finally, we present a user study indicating significantly improved usefulness and ease of use of the proposed high-level variant visualization compared to existing variant visualizations for typical analysis tasks.

In process discovery, we aim to find a model that describes the underlying process best, given an event log. The eST-Miner is a discovery technique inspired by language-based regions. It discovers precise Petri nets containing exactly one transition for each activity in the event log by efficiently traversing the space of all possible places. It then expands the model iteratively with places. The final model consists of the maximal set of places considered fitting with respect to a user-definable fraction of the behavior in the log evaluated by token-based replay. Therefore, the eST-Miner can derive complex control-flow structures that other approaches fail to discover and handle noise and infrequent behavior. Although the eST-Miner discovers high-quality models, its feasibility has previously been limited by its runtime: When naively inserting places, the discovered models contain many implicit places, i.e., places whose removal does not change its language and is time-consuming. Therefore, we propose an efficient strategy that avoids adding implicit places by exploiting log information while including non-fitting log traces. We extend the discovery with information on the precision of the (expanding) model based on escaping edges. With our extensions, the eST-Miner becomes a competitive choice among other process discovery techniques. We demonstrate the effectiveness of our heuristics using the eST-Miner as an exemplary use case and run various experiments on real-life and artificial event logs.

Process simulation assesses the impact of changing environmental parameters on a process. To obtain realistic simulation models, process mining techniques can be deployed for a log-based discovery. Such discovery techniques usually rely on a fixed case notion, falling short in capturing the entangled nature of real organizational processes as an interplay of objects and subprocesses. Yet there is a need for such methods, given the requirement for information systems to foresee and adapt to changing environments in an online setting and in a holistic manner. In this work, we approach this research need by elaborating a method for simulation model discovery that is based on the object-centricity paradigm. To implement object-centric simulation, some intrinsic challenges have to be overcome. These include, first, the parametrizable generation of sets of objects having predefined interrelations that structure possible behavior. Second, the generated objects have to be synchronized and routed through a control-flow model. We outline these challenges, describe our solution approach, and evaluate the quality of both object generation and behavior.

Many real-life processes naturally define partial orders over the activities they are composed of. Partial orders can be used as a graph-like representation of process behavior, allowing us to model concurrent and sequential dependencies. The Partially Ordered Workflow Language (POWL) combines block-structured modeling notations with partially-ordered graph representations. A POWL model is a hierarchical model where sub-models can be combined into a new model either using a control-flow operator or as a partial order. The application of POWL models in process mining remains a challenge due to a lack of scalable approaches for the discovery of POWL models. In this paper, we address this gap by proposing an approach for the discovery of POWL models that leverages large data sets and ensures high conformity with the input data. Our approach provides formal guarantees on the uniqueness, existence, and quality of discovered partial orders. The evaluation of our approach underscores its scalability with large data sets and its ability to generate high-quality models.

Abstract Process mining provides a collection of techniques to gain insights into business processes by analyzing event logs. Organizations can gain various insights into their business processes by using process mining techniques. Such techniques use event logs extracted from relational databases supporting the business process as input. However, extracting event logs is challenging due to the size of the data, and it remains ad-hoc. Existing commercial tools partly support the extraction of event logs, but they are proprietary and focus on the mainstream processes such as Purchase-To-Pay (P2P) and Order-To-Cash (O2C). Moreover, the extracted event logs suffer from well-known deficiency, convergence, and divergence issues. For example, due to convergence events are unintentionally duplicated causing unreliable or confusing performance diagnostics. In this paper, we propose an approach to extract event logs while avoiding the aforementioned issues. More in detail, we extract object-centric event logs by using an abstraction layer of the database, called Graph of Relationships (GoRs), designing blueprints with domain knowledge, and converting the database and blueprint into object-centric event logs.We fully implemented the proposed approach, which can extract object-centric event logs from SAP ERP systems, and evaluate the utility and scalability of the proposed approach.

Abstract Predictive process monitoring is a subfield of process mining that aims to estimate case or event features for running process instances. Such predictions are of significant interest to the process stakeholders. However, most of the state-of-the-art methods for predictive monitoring require the training of complex machine learning models, which is often inefficient. Moreover, most of these methods require a hyper-parameter optimization that requires several repetitions of the training process which is not feasible in many real-life applications. In this paper, we propose an instance selection procedure that allows sampling training process instances for prediction models. We show that our instance selection procedure allows for a significant increase of training speed for next activity and remaining time prediction methods while maintaining reliable levels of prediction accuracy.

Process mining provides techniques to learn models from event data. These models can be descriptive (e.g., Petri nets) or predictive (e.g., neural networks). The learned models offer operational support to process owners by conformance checking, process enhancement, or predictive monitoring. However, processes are frequently subject to significant changes, making the learned models outdated and less valuable over time. To tackle this problem, Process Concept Drift (PCD) detection techniques are employed. By identifying when the process changes occur, one can replace learned models by relearning, updating, or discounting pre-drift knowledge. Various techniques to detect PCDs have been proposed. However, each technique's evaluation focuses on different evaluation goals out of accuracy, latency, versatility, scalability, parameter sensitivity, and robustness. Furthermore, the employed evaluation techniques and data sets differ. Since many techniques are not evaluated against more than one other technique, this lack of comparability raises one question: How do PCD detection techniques compare against each other? With this paper, we propose, implement, and apply a unified evaluation framework for PCD detection. We do this by collecting evaluation goals and evaluation techniques together with data sets. We derive a representative sample of techniques from a taxonomy for PCD detection. The implemented techniques and proposed evaluation framework are provided in a publicly available repository. We present the results of our experimental evaluation and observe that none of the implemented techniques works well across all evaluation goals. However, the results indicate future improvement points of algorithms and guide practitioners.

Event logs, as considered in process mining, document a large number of individual process executions. Moreover, each process execution consists of various executed activities. To cope with the vast amount of process executions in event logs, the concept of variants exists that group process executions with identical ordering relations among their executed activities. Variants are an integral concept of process mining and help process analysts explore, filter, and manage large amounts of event data. In this paper, we consider concurrency-aware variants that allow activities within a process execution to be partially ordered---the execution of individual activities can overlap in time. However, the number of variants is often vast, making it challenging for process analysts to explore event data. Therefore, we present a novel approach to frequent pattern mining from concurrency-aware variants. We show that mining frequent patterns from concurrency-aware variants can be reduced to the frequent subtree mining problem. Further, we compare our proposed algorithm to a state-of-the-art frequent subtree mining algorithm exhibiting improved performance on real-life event logs.

The execution of processes leaves traces of event data in information systems. These event data can be analyzed through process mining techniques. For traditional process mining techniques, one has to associate each event with exactly one object, e.g., the company’s customer. Events related to one object form an event sequence called a case. A case describes an end-to-end run through a process. The cases contained in event data can be used to discover a process model, detect frequent bottlenecks, or learn predictive models. However, events encountered in real-life information systems, e.g., ERP systems, can often be associated with multiple objects. The traditional sequential case concept falls short of these so-called object-centric event data since these data exhibit a graph structure. One might force object-centric event data into the traditional case concept by flattening it. However, flattening manipulates the data and removes information. Therefore, a concept analogous to the case concept of traditional event logs is necessary to enable the application of different process mining tasks on object-centric event data. In this paper, we introduce the case concept for object-centric process mining: process executions. These are graph-based generalizations of cases as considered in traditional process mining. Furthermore, we provide techniques to extract process executions. Based on these executions, we determine equivalent process behavior with respect to an attribute using graph isomorphism. Equivalent process executions with respect to the event’s activity are object-centric variants, i.e., a generalization of variants in traditional process mining. We provide a visualization technique for object-centric variants. The contribution’s scalability and efficiency are extensively evaluated. Furthermore, we provide a case study showing the most frequent object-centric variants of a real-life event log. Our contributions might be used as a basis to adapt traditional process mining techniques by researchers and to generate initial control-flow insights into object-centric event logs by practitioners.

Process mining methods often analyze processes in terms of the individual end-to-end process runs. Process behavior, however, may materialize as a general state of many involved process components, which can not be captured by looking at the individual process instances. A more holistic state of the process can be determined by looking at the events that occur close in time and share common process capacities. In this work, we conceptualize such behavior using high-level events and propose a new framework for detecting and logging such high-level events. The output of our method is a new high-level event log, which collects all generated high-level events together with the newly assigned event attributes: activity, case, and timestamp. Existing process mining techniques can then be applied on the produced high-level event log to obtain further insights. Experiments on both simulated and real-life event data show that our method is able to automatically discover how system-level patterns such as high traffic and workload emerge, propagate and dissolve throughout the process.

Stochastic process models are a type of model that explicitly include elements of probability in describing an organization, facilitating different modes of analysis and simulation. Having obtained models of an organizational process, say through process mining, using them well depends on understanding their quality, and being able to compare different models. There may not be a single optimal stochastic model for a process, but tradeoffs between models, decided by their intended use. Reasoning about trade-offs in a precise way requires quantitative measures, and an understanding of how these measures relate, including whether they capture independent underlying properties.This paper is an empirical investigation of measures for stochastic process models built from real-life logs. The experimental design assembles a large collection of models built both randomly and by discovery techniques. A wide spectrum of candidate measures, drawn from and inspired by the process mining literature, are applied using these models. Based on this analysis, three stochastic quality dimensions are proposed: adhesion, entropy and simplicity.

Traditional process mining considers only one single case notion and discovers and analyzes models based on this. However, a single case notion is often not a realistic assumption in practice. Multiple case notions might interact and influence each other in a process. Object-centric process mining introduces the techniques and concepts to handle multiple case notions. So far, such event logs have been standardized and novel process model discovery techniques were proposed. However, notions for evaluating the quality of a model are missing. These are necessary to enable future research on improving object-centric discovery and providing an objective evaluation of model quality. In this paper, we introduce a notion for the precision and fitness of an object-centric Petri net with respect to an object-centric event log. We give a formal definition and accompany this with an example. Furthermore, we provide an algorithm to calculate these quality measures. We discuss our precision and fitness notion based on an event log with different models. Our precision and fitness notions are an appropriate way to generalize quality measures to the object-centric setting since we are able to consider multiple case notions, their dependencies and their interactions.

Process mining allows one to analyze and extract knowledge from event data, i.e., records of process executions stored in information systems. Most process mining techniques are directly applied to the data as recorded in the system. Applying automated process discovery techniques, i.e., a core process mining technology, directly on such data yields complex process models describing millions of different execution paths. Other techniques applied to such discovered process models and system-level data, e.g., conformance checking or performance analysis techniques, often generate complex and over-detailed results. The results obtained by directly applying process mining techniques on system-level data are, therefore, hard to interpret by a human analyst and greatly differ from the business level. Therefore, in this paper, we propose a generic hierarchical framework for event abstraction. We formalize the framework, which uses the notion of activity instances as an input and allows for hierarchical abstraction of event data. In addition, we propose an instantiation of the framework, which describes two key functions of the framework, i.e., abstract concept identification and abstract entity extraction. The framework, together with the instantiation, is evaluated both quantitatively and qualitatively. The experiments show that, without compromising the quality of results, the abstraction allows users to easier analyze a process.

A Digital Twin of an Organization (DTO) is a mirrored representation of an organization, aiming to improve the business process of the organization by providing a transparent view over the process and automating management actions to deal with existing and potential risks. Unlike wide applications of digital twins to product design and predictive maintenance, no concrete realizations of DTOs for business process improvement have been studied. In this work, we aim to realize DTOs using action-oriented process mining, a collection of techniques to evaluate violations of constraints and produce the required actions. To this end, we suggest a digital twin interface model as a transparent representation of an organization describing the current state of business processes and possible configurations in underlying information systems. By interacting with the representation, process analysts can elicit constraints and actions that will be continuously monitored and triggered by an action engine to improve business processes. We have implemented a web service to support it and evaluated the feasibility of the proposed approach by conducting a case study using an artificial information system supporting an order handling process.

Process mining techniques help to improve processes using event data. Such data are widely available in information systems. However, they often contain highly sensitive information. For example, healthcare information systems record event data that can be utilized by process mining techniques to improve the treatment process, reduce patient’s waiting times, improve resource productivity, etc. However, the recorded event data include highly sensitive information related to treatment activities. Responsible process mining should provide insights about the underlying processes, yet, at the same time, it should not reveal sensitive information. In this paper, we discuss the challenges regarding directly applying existing well-known group-based privacy preservation techniques, e.g., k-anonymity, l-diversity, etc, to event data. We provide formal definitions of attack models and introduce an effective group-based privacy preservation technique for process mining. Our technique covers the main perspectives of process mining including control-flow, time, case, and organizational perspectives. The proposed technique provides interpretable and adjustable parameters to handle different privacy aspects. We employ real-life event data and evaluate both data utility and result utility to show the effectiveness of the privacy preservation technique. We also compare this approach with other group-based approaches for privacy-preserving event data publishing.

Modern business processes are embedded in a complex environment and, thus, subjected to continuous changes. While current approaches focus on the control flow only, additional perspectives, such as time, are neglected. In this paper, we investigate a more general concept drift detection framework that is based on the Earth Mover's Distance. Our approach is flexible in terms of incorporating additional perspectives thanks to the capability of defining custom feature representations, as well as expressive feature similarity measures. We demonstrate the former by incorporating the time perspective using both a time-binning-based trace descriptor and a suitable similarity measure that considers time and control flow. We evaluate the resulting sliding window detector on different types of control-flow and time drifts, and holistic drifts involving multiple perspectives.

Business process models can be (re)constructed using event data recorded during the process' execution. Similarly, event data can be used to verify conformance to prescribed behavior and to analyze and improve the underlying processes. However, not all events that are related to a process necessarily relate to its control-flow. Some events occur in the context of the process. In this work, we introduce the concept of context events to deal with these types of events. We show how distinguishing between contextual and control-flow events aids process discovery to obtain less complex process models. We demonstrate how visualizing context events on top of process models helps identify points in the process where context events occur often, aiding understanding. We analyze these benefits using two case studies involving real-life processes and event data.

Conformance checking techniques are used to compute to what degree a process model and real execution data correspond to each other. In recent years, alignments have proven to be useful for calculating conformance statistics. Most alignment techniques provide an exact conformance value. However, in many applications, it suffices to have an approximated alignment value. Specifically, for large event data and using standard hardware, current alignment techniques are time-consuming and sometimes intractable. This paper proposes to use simulated behaviors of process models to approximate the conformance checking value. To simulate a process model, we exploit the behavior in the given event data. This method is independent from the process model notation and provides upper and lower bounds for the approximated alignment value. We assess the quality of our approximations and compare it to existing approximation techniques. The experiments on real event data show that using the proposed method, it is possible to achieve significant performance improvements.

Dynamic bottlenecks occur when some cases in a particular part of the process are temporarily delayed. In performance-optimized systems such as production systems, warehouse automation systems, and baggage handling systems, such bottlenecks are rare, bounded in time and location, but costly when they occur and propagate through the system. Detecting and understanding the situations that cause such bottlenecks is crucial for mitigating and preventing processing delays. Classical process mining techniques that analyze performance along individual cases cannot detect these phenomena and their causes. We show that undesired system-level behavior can be detected when identifying temporal event patterns across different cases in the same process step. Conceptualizing these patterns as system-level events allows us to correlate them into cascades of system-level behavior using spatio-temporal conditions. We discover classes of frequent patterns in these cascades that describe behaviors that precede bottlenecks. Applied on event data of a major European airport, our approach could fully automatically detect cascades of undesired system-level behavior leading to dynamic bottlenecks. Each detected cascade was verified as a correct causal explanation for a dynamic bottleneck due to the physical system layout and its processing.

Abstract Process mining techniques use event logs as input. When analyzing complex databases, these event logs can be built in many ways. Events need to be grouped into traces corresponding to a case. Different groupings provide different views on the data. Building event logs is usually a time-consuming, manual task. This paper provides a precise view on the case notion on databases, which enables the automatic computation of event logs. Also, it provides a way to assess event log quality, used to rank event logs with respect to their interestingness. The computational cost of building an event log can be avoided by predicting the interestingness of a case notion, before the corresponding event log is computed. This makes it possible to give recommendations to users, so they can focus on the analysis of the most promising process views. Finally, the accuracy of the predictions and the quality of the rankings generated by our unsupervised technique are evaluated in comparison to the existing regression techniques as well as to state-of-the-art learning to rank algorithms from the information retrieval field. The results show that our prediction technique succeeds at discovering interesting event logs and provides valuable recommendations to users about the perspectives on which to focus the efforts during the analysis.

Predictive performance analysis is crucial for supporting operational processes. Prediction is challenging when cases are not isolated but influence each other by competing for resources (spaces, machines, operators). The so-called performance spectrum maps a variety of performance-related measures within and across cases over time. We propose a novel prediction approach that uses the performance spectrum for feature selection and extraction to pose machine learning problems used for performance prediction in non-isolated cases. Although the approach is general, we focus on material handling systems as a primary example. We report on a feasibility study conducted for the material handling systems of a major European airport. The results show that the use of the performance spectrum enables much better predictions than baseline approaches.

Nowadays, more and more process data are automatically recorded by information systems, and made available in the form of event logs. Process mining techniques enable process-centric analysis of data, including automatically discovering process models and checking if event data conform to a certain model. In this paper we analyze the previously unexplored setting of uncertain event logs: logs where quantified uncertainty is recorded together with the corresponding data. We define a taxonomy of uncertain event logs and models, and we examine the challenges that uncertainty poses on process discovery and conformance checking. Finally, we show how upper and lower bounds for conformance can be obtained aligning an uncertain trace onto a regular process model.

Process Discovery is concerned with the automatic generation of a process model that describes a business process from execution data of that business process. Real life event logs can contain chaotic activities . These activities are independent of the state of the process and can, therefore, happen at rather arbitrary points in time. We show that the presence of such chaotic activities in an event log heavily impacts the quality of the process models that can be discovered with process discovery techniques. The current modus operandi for filtering activities from event logs is to simply filter out infrequent activities. We show that frequency-based filtering of activities does not solve the problems that are caused by chaotic activities. Moreover, we propose a novel technique to filter out chaotic activities from event logs. We evaluate this technique on a collection of seventeen real-life event logs that originate from both the business process management domain and the smart home environment domain. As demonstrated, the developed activity filtering methods enable the discovery of process models that are more behaviorally specific compared to process models that are discovered using standard frequency-based filtering.

The aim of process discovery, originating from the area of process mining, is to discover a process model based on business process execution data. A majority of process discovery techniques relies on an event log as an input. An event log is a static source of historical data capturing the execution of a business process. In this paper, we focus on process discovery relying on online streams of business process execution events. Learning process models from event streams poses both challenges and opportunities, i.e. we need to handle unlimited amounts of data using finite memory and, preferably, constant time. We propose a generic architecture that allows for adopting several classes of existing process discovery techniques in context of event streams. Moreover, we provide several instantiations of the architecture, accompanied by implementations in the process mining toolkit ProM ( http://promtools.org ). Using these instantiations, we evaluate several dimensions of stream-based process discovery. The evaluation shows that the proposed architecture allows us to lift process discovery to the streaming domain.

In recent years, monitoring the compliance of business processes with relevant regulations, constraints, and rules during runtime has evolved as major concern in literature and practice. Monitoring not only refers to continuously observing possible compliance violations, but also includes the ability to provide fine-grained feedback and to predict possible compliance violations in the future. The body of literature on business process compliance is large and approaches specifically addressing process monitoring are hard to identify. Moreover, proper means for the systematic comparison of these approaches are missing. Hence, it is unclear which approaches are suitable for particular scenarios. The goal of this paper is to define a framework for Compliance Monitoring Functionalities (CMF) that enables the systematic comparison of existing and new approaches for monitoring compliance rules over business processes during runtime. To define the scope of the framework, at first, related areas are identified and discussed. The CMFs are harvested based on a systematic literature review and five selected case studies. The appropriateness of the selection of CMFs is demonstrated in two ways: (a) a systematic comparison with pattern-based compliance approaches and (b) a classification of existing compliance monitoring approaches using the CMFs. Moreover, the application of the CMFs is showcased using three existing tools that are applied to two realistic data sets. Overall, the CMF framework provides powerful means to position existing and future compliance monitoring approaches.

Process discovery algorithms typically aim at discovering process models from event logs that best describe the recorded behavior. Often, the quality of a process discovery algorithm is measured by quantifying to what extent the resulting model can reproduce the behavior in the log, i.e. replay fitness. At the same time, there are other measures that compare a model with recorded behavior in terms of the precision of the model and the extent to which the model generalizes the behavior in the log. Furthermore, many measures exist to express the complexity of a model irrespective of the log. In this paper, we first discuss several quality dimensions related to process discovery. We further show that existing process discovery algorithms typically consider at most two out of the four main quality dimensions: replay fitness, precision, generalization and simplicity. Moreover, existing approaches cannot steer the discovery process based on user-defined weights for the four quality dimensions. This paper presents the ETM algorithm which allows the user to seamlessly steer the discovery process based on preferences with respect to the four quality dimensions. We show that all dimensions are important for process discovery. However, it only makes sense to consider precision, generalization and simplicity if the replay fitness is acceptable.

More and more information about processes is recorded in the form of so-called 'event logs'. High-tech systems such as X-ray machines and high-end copiers provide their manufacturers and services organizations with detailed event data. Larger organizations record relevant business events for process improvement, auditing, and fraud detection. Traces in such event logs can be classified as desirable or undesirable (e.g., faulty or fraudulent behavior). In this paper, we present a comprehensive framework for discovering signatures that can be used to explain or predict the class of seen or unseen traces. These signatures are characteristic patterns that can be used to discriminate between desirable and undesirable behavior. As shown, these patterns can, for example, be used to predict remotely whether a particular component in an X-ray machine is broken or not. Moreover, the signatures also help to improve systems and organizational processes. Our framework for signature discovery is fully implemented in ProM and supports class labeling, feature extraction and selection, pattern discovery, pattern evaluation and cross-validation, reporting, and visualization. A real-life case study is used to demonstrate the applicability and scalability of the approach. Keywords: Discriminatory Patterns; Event Log; Process Mining; Signature Patterns

The growing interest in process mining is fueled by the increasing availability of event data. Process mining techniques use event logs to automatically discover process models, check conformance, identify bottlenecks and deviations, suggest improvements, and predict processing times. Lion's share of process mining research has been devoted to analysis techniques. However, the proper handling of problems and challenges arising in analyzing event logs used as input is critical for the success of any process mining effort. In this paper, we identify four categories of process characteristics issues that may manifest in an event log (e.g. process problems related to event granularity and case heterogeneity) and 27 classes of event log quality issues (e.g., problems related to timestamps in event logs, imprecise activity names, and missing events). The systematic identification and analysis of these issues calls for a consolidated effort from the process mining community. Five real-life event logs are analyzed to illustrate the omnipresence of process and event log issues. We hope that these findings will encourage systematic logging approaches (to prevent event log issues), repair techniques (to alleviate event log issues) and analysis techniques (to deal with the manifestation of process characteristics in event logs).

Today, large business processes are composed of smaller, autonomous, interconnected subsystems, achieving modularity and robustness. Quite often, these large processes comprise software components as well as human actors, they face highly dynamic environments and their subsystems are updated and evolve independently of each other. Due to their dynamic nature and complexity, it might be difficult, if not impossible, to ensure at design-time that such systems will always exhibit the desired/expected behaviors. This, in turn, triggers the need for runtime verification and monitoring facilities. These are needed to check whether the actual behavior complies with expected business constraints, internal/external regulations and desired best practices. In this work, we present Mobucon EC, a novel monitoring framework that tracks streams of events and continuously determines the state of business constraints. In Mobucon EC, business constraints are defined using the declarative language Declare. For the purpose of this work, Declare has been suitably extended to support quantitative time constraints and non-atomic, durative activities. The logic-based language Event Calculus (EC) has been adopted to provide a formal specification and semantics to Declare constraints, while a light-weight, logic programming-based EC tool supports dynamically reasoning about partial, evolving execution traces. To demonstrate the applicability of our approach, we describe a case study about maritime safety and security and provide a synthetic benchmark to evaluate its scalability.

Process mining techniques can be used to effectively discover process models from logs with example behaviour. Cross-correlating a discovered model with information in the log can be used to improve the underlying process. However, existing process discovery techniques have two important drawbacks. The produced models tend to be large and complex, especially in flexible environments where process executions involve multiple alternatives. This “overload” of information is caused by the fact that traditional discovery techniques construct procedural models explicitly showing all possible behaviours. Moreover, existing techniques offer limited possibilities to guide the mining process towards specific properties of interest. These problems can be solved by discovering declarative models. Using a declarative model, the discovered process behaviour is described as a (compact) set of rules. Moreover, the discovery of such models can easily be guided in terms of rule templates. This paper uses DECLARE, a declarative language that provides more flexibility than conventional procedural notations such as BPMN, Petri nets, UML ADs, EPCs and BPEL. We present an approach to automatically discover DECLARE models. This has been implemented in the process mining tool ProM. Our approach and toolset have been applied to a case study provided by the company Thales in the domain of maritime safety and security.

A supply chain comprises several different kinds of actors that interact either in an ad hoc fashion (e.g. an eventual deal) or in a previously well-planned way. In the latter, how the interactions develop is described in contracts that are agreed on before the interactions start. This agreement may involve several partners, thus a multi-party contract is better suited than a set of bi-lateral contracts. If one is willing to negotiate automatically such kind of contracts, an appropriate negotiation protocol should be at hand. However, the ones for bi-lateral contracts are not suitable for multi-party contracts, e.g. the way to achieve consensus when only two negotiators are haggling over some issues is quite different if there are several negotiators involved. In the first case, a simple bargain would suffice, but in the latter a ballot process is needed. This paper briefly presents our negotiation protocol for electronic multi-party contracts which seamlessly combines several negotiation styles. It also elaborates on the main negotiation patterns the protocol allows for: bargain (for peer-to-peer negotiation), auction (when there is competition among the negotiators) and ballot (when the negotiation aims at consensus) and presents other patterns that can be built on these basic ones. Finally, it describes an implementation of this protocol based on Web services, and built on the YAWL Workflow Management System.

Service-oriented computing, an emerging paradigm for architecting and implementing business collaborations within and across organizational boundaries, is currently of interest to both software vendors and scientists. While the technologies for implementing and interconnecting basic services are reaching a good level of maturity, modeling service interaction from a global viewpoint, that is, representing service choreographies, is still an open challenge. The main problem is that, although declarativeness has been identified as a key feature, several proposed approaches specify choreographies by focusing on procedural aspects, leading to over-constrained and over-specified models. To overcome these limits, we propose to adopt DecSerFlow, a truly declarative language, to model choreographies. Thanks to its declarative nature, DecSerFlow semantics can be given in terms of logic-based languages. In particular, we present how DecSerFlow can be mapped ontoLinear Temporal Logicand ontoAbductive Logic Programming. We show how the mappings onto both formalisms can be concretely exploited to address the enactment of DecSerFlow models, to enrich its expressiveness and to perform a variety of different verification tasks. We illustrate the advantages of using a declarative language in conjunction with logic-based semantics by applying our approach to a running example.

Process Mining refers to the extraction of process models from event logs. Real-life processes tend to be less structured and more flexible. Traditional process mining algorithms have problems dealing with such unstructured processes and generate spaghetti-like process models that are hard to comprehend. An approach to overcome this is to cluster process instances (a process instance is manifested as a trace and an event log corresponds to a multi-set of traces) such that each of the resulting clusters correspond to a coherent set of process instances that can be adequately represented by a process model. In this paper, we propose a context aware approach to trace clustering based on generic edit distance. It is well known that the generic edit distance framework is highly sensitive to the costs of edit operations. We define an automated approach to derive the costs of edit operations. The method proposed in this paper outperforms contemporary approaches to trace clustering in process mining. We evaluate the goodness of the formed clusters using established fitness and comprehensibility metrics defined in the context of process mining. The proposed approach is able to generate clusters such that the process models mined from the clustered traces show a high degree of fitness and comprehensibility when compared to contemporary approaches.

Workflow languages offer constructs for coordinating tasks. Among these constructs are various types of splits and joins. One type of join, which shows up in various incarnations, is the OR-join. Different approaches assign a different (often only intuitive) semantics to this type of join, though they do share the common theme that branches that cannot complete will not be waited for. Many systems and languages struggle with the semantics and implementation of the OR-join because its non-local semantics require a synchronization depending on the analysis of future execution paths. The presence of cancelation features, potentially unbounded behavior, and other OR-joins in a workflow further complicates the formal semantics of the OR-join. In this paper, the concept of the OR-join is examined in detail in the context of the workflow language YAWL, a powerful workflow language designed to support a collection of workflow patterns and inspired by Petri nets. The paper provides a suitable (non-local) semantics for an OR-join and gives a concrete algorithm with two optimization techniques to support the implementation. This approach exploits a link that is proposed between YAWL and reset nets, a variant of Petri nets with a special type of arc that can remove all tokens from a place when its transition fires. Through the behavior of reset arcs, the behavior of cancelation regions can be captured in a natural manner.

Workflow modeling languages allow for the specification of executable business processes. They, however, typically do not provide any guidance for the adaptation of workflow models, i.e. they do not offer any methods or tools explaining and highlighting which adaptations of the models are feasible and which are not. Therefore, an approach to identify so-called configurable elements of a workflow modeling language and to add configuration opportunities to workflow models is presented in this paper. Configurable elements are the elements of a workflow model that can be modified such that the behavior represented by the model is restricted. More precisely, a configurable element can be either set to enabled, to blocked, or to hidden. To ensure that such configurations lead only to desirable models, our approach allows for imposing so-called requirements on the model's configuration. They have to be fulfilled by any configuration, and limit therefore the freedom of configuration choices. The identification of configurable elements within the workflow modeling language of YAWL and the derivation of the new "configurable YAWL" language provide a concrete example for a rather generic approach. A transformation of configured models into lawful YAWL models demonstrates its applicability.

One of the aims of process mining is to retrieve a process model from an event log. The discovered models can be used as objective starting points during the deployment of process-aware information systems (Dumas et al., eds., Process-Aware Information Systems: Bridging People and Software Through Process Technology. Wiley, New York, 2005) and/or as a feedback mechanism to check prescribed models against enacted ones. However, current techniques have problems when mining processes that contain non-trivial constructs and/or when dealing with the presence of noise in the logs. Most of the problems happen because many current techniques are based on local information in the event log. To overcome these problems, we try to use genetic algorithms to mine process models. The main motivation is to benefit from the global search performed by this kind of algorithms. The non-trivial constructs are tackled by choosing an internal representation that supports them. The problem of noise is naturally tackled by the genetic algorithm because, per definition, these algorithms are robust to noise. The main challenge in a genetic approach is the definition of a good fitness measure because it guides the global search performed by the genetic algorithm. This paper explains how the genetic algorithm works. Experiments with synthetic and real-life logs show that the fitness measure indeed leads to the mining of process models that are complete (can reproduce all the behavior in the log) and precise (do not allow for extra behavior that cannot be derived from the event log). The genetic algorithm is implemented as a plug-in in the ProM framework.

The common presupposition of enterprise systems (ES) is that they lead to significant efficiency gains. However, this is only the case for well-implemented ES that are well-aligned with the organisation. The list of ES implementation failures is significant which is partly attributable to the insufficiently addressed fundamental problem of adapting an ES efficiently. As long as it is not intuitively possible to configure an ES, this problem will prevail because organisations have a non-generic character. A solution to this problem consists in re-thinking current practices of ES provision. This paper proposes a new approach based on configurable process models, which reflect ES functionalities. We provide in this paper a taxonomy of situations that can occur from a business perspective during process model configuration. This taxonomy is represented via so-called semantic configuration patterns. In the next step, we discuss so-called syntactic configuration patterns. This second type of configuration patterns implements the semantic configuration patterns for specific modelling techniques. We chose two popular process modelling languages in order to illustrate our approach.

This paper presents a methodology to bridge the gap between business process modeling and workflow specification. While the first is concerned with intuitive descriptions that are mainly used for communication, the second is concerned with configuring a process-aware information system, thus requiring a more rigorous language less suitable for communication. Unlike existing approaches the gap is not bridged by providing formal semantics for an informal language. Instead it is assumed that the desired behavior is just a subset of the full behavior obtained using a liberal interpretation of the informal business process modeling language. Using a new correctness criterion (relaxed soundness), it is verified whether a selection of suitable behavior is possible. The methodology consists of five steps and is illustrated using event-driven process chains as a business process modeling language and Petri nets as the workflow specification language.

Contemporary workflow management systems are driven by explicit process models, i.e., a completely specified workflow design is required in order to enact a given workflow process. Creating a workflow design is a complicated time-consuming process and, typically, there are discrepancies between the actual workflow processes and the processes as perceived by the management. Therefore, we have developed techniques for discovering workflow models. The starting point for such techniques is a so-called "workflow log" containing information about the workflow process as it is actually being executed. We present a new algorithm to extract a process model from such a log and represent it in terms of a Petri net. However, we also demonstrate that it is not possible to discover arbitrary workflow processes. We explore a class of workflow processes that can be discovered. We show that the /spl alpha/-algorithm can successfully mine any workflow represented by a so-called SWF-net.

On the Dutch workflow market, a new and interesting paradigm named "case handling" is emerging. The goal of case handling is to overcome the limitations of existing workflow management systems. By using a data-driven approach combined with implicit routing and carefully avoiding context tunneling, awareness and flexibility are improved. Currently, many organizations are considering case handling systems such as FLOWer (Pallas Athena) rather than the more traditional workflow management systems. This paper provides a critical assessment of this development. The goal is to show the pro's and con's of case handling. Moreover, based on this assessment, an alternative approach using slightly extended workflow management systems is proposed. This approach is being pursued by the Dutch government in a project involving the workflow management system Staffware. Based on our experiences thus far, we provide guidelines for selecting the proper technology.

The focus of traditional workflow management systems is on control flow within one process definition. The process definition describes how a single case (i.e. workflow instance) in isolation is handled. For many applications this paradigm is inadequate. Interaction between cases to support communication and collaboration is at least as important. This paper introduces and advocates the use of interacting proclets, i.e. lightweight workflow processes. By promoting interactions to first-class citizens it is possible to model complex workflows in a more natural manner. In addition, the expressive power and flexibility are improved compared to the more traditional workflow modeling languages.