Joos C. A. M. Buijs

Process Mining Manifesto

Process mining techniques are able to extract knowledge from event logs commonly available in today’s information systems. These techniques provide new means to discover, monitor, and improve processes in a variety of application domains. There are two main drivers for the growing interest in process mining. On the one hand, more and more events are being recorded, thus, providing detailed information about the history of processes. On the other hand, there is a need to improve and support business processes in competitive and rapidly changing environments. This manifesto is created by the IEEE Task Force on Process Mining and aims to promote the topic of process mining. Moreover, by defining a set of guiding principles and listing important challenges, this manifesto hopes to serve as a guide for software developers, scientists, consultants, business managers, and end-users. The goal is to increase the maturity of process mining as a new tool to improve the (re)design, control, and support of operational business processes.

A Generic Framework for Context-Aware Process Performance Analysis

Process mining combines model-based process analysis with data-driven analysis techniques. The role of process mining is to extract knowledge and gain insights from event logs. Most existing techniques focus on process discovery (the automated extraction of process models) and conformance checking (aligning observed and modeled behavior). Relatively little research has been performed on the analysis of business process performance. Cooperative business processes often exhibit a high degree of variability and depend on many factors. Finding root causes for inefficiencies such as delays and long waiting times in such flexible processes remains an interesting challenge. This paper introduces a novel approach to analyze key process performance indicators by considering the process context. A generic context-aware analysis framework is presented that analyzes performance characteristics from multiple perspectives. A statistical approach is then utilized to evaluate and find significant differences in the results. Insights obtained can be used for finding high-impact points for optimization, prediction, and monitoring. The practical relevance of the approach is shown in a case study using real-life data.

Detection and Interactive Repair of Event Ordering Imperfection in Process Logs

Many forms of data analysis require timestamp information to order the occurrences of events. The process mining discipline uses historical records of process executions, called event logs, to derive insights into business process behaviours and performance. Events in event logs must be ordered, typically achieved using timestamps. The importance of timestamp information means that it needs to be of high quality. To the best of our knowledge, no(semi-)automated support exists for detecting and repairing ordering-related imperfection issues in event logs. We describe a set of timestamp-based indicators for detecting event ordering imperfection issues in a log and our approach to repairing identified issues using domain knowledge. Lastly, we evaluate our approach implemented in the open-source process mining framework, ProM, using two publicly available logs.

Discovering Causal Factors Explaining Business Process Performance Variation

Business process performance may be affected by a range of factors, such as the volume and characteristics of ongoing cases or the performance and availability of individual resources. Event logs collected by modern information systems provide a wealth of data about the execution of business processes. However, extracting root causes for performance issues from these event logs is a major challenge. Processes may change continuously due to internal and external factors. Moreover, there may be many resources and case attributes influencing performance. This paper introduces a novel approach based on time series analysis to detect cause-effect relations between a range of business process characteristics and process performance indicators. The scalability and practical relevance of the approach has been validated by a case study involving a real-life insurance claims handling process.

Repairing Alignments: Striking the Right Nerve

Process Mining is concerned with the analysis, understanding and improvement of business processes. One of the most important branches of process mining is conformance checking, i.e. assessing to what extent a business process model conforms to observed business process execution data. Alignments are the de facto standard instrument to compute conformance statistics. Alignments map elements of an event log onto activities present in a business process model. However, computing them is a combinatorial problem and hence, extremely costly. In this paper we show how to compute an alignment for a given process model, using an existing alignment and an existing process model as a basis. We show that we are able to effectively repair the existing alignment by updating those parts that no longer fit the given process model. Thus, computation time decreases significantly. Moreover, we show that the potential loss of optimality is limited and stays within acceptable bounds.

Enabling interactive process analysis with process mining and visual analytics

In a typical healthcare setting, specific clinical care pathways can be defined by the hospitals. Process mining provides a way of analyzing the care pathways by analyzing the event data extracted from the hospital information systems. Process mining can be used to optimize the overall care pathway, and gain interesting insights into the actual execution of the process, as well as to compare the expectations versus the reality. In this paper, a generic novel tool called InterPretA, is introduced which builds upon pre-existing process mining and visual analytics techniques to enable the user to perform such process oriented analysis. InterPretA contains a set of options to provide high level conformance analysis of a process from different perspectives. Furthermore, InterPretA enables detailed investigative analysis by letting the user interactively analyze, visualize and explore the execution of the processes from the data perspective.

Detecting Changes in Process Behavior Using Comparative Case Clustering

Real-life business processes are complex and often exhibit a high degree of variability. Additionally, due to changing conditions and circumstances, these processes continuously evolve over time. For example, in the healthcare domain, advances in medicine trigger changes in diagnoses and treatment processes. Case data (e.g. treating physician, patient age) also influence how processes are executed. Existing process mining techniques assume processes to be static and therefore are less suited for the analysis of contemporary, flexible business processes. This paper presents a novel comparative case clustering approach that is able to expose changes in behavior. Valuable insights can be gained and process improvements can be made by finding those points in time where behavior changed and the reasons why. Evaluation using both synthetic and real-life event data shows our technique can provide these insights.

Using Domain Knowledge to Enhance Process Mining Results

Process discovery algorithms typically aim at discovering process models from event logs. Most algorithms achieve this by solely using an event log, without allowing the domain expert to influence the discovery in any way. However, the user may have certain domain expertise which should be exploited to create better process models. In this paper, we address this issue of incorporating domain knowledge to improve the discovered process model. First, we present a verification algorithm to verify the presence of certain constraints in a process model. Then, we present three modification algorithms to modify the process model. The outcome of our approach is a Pareto front of process models based on the constraints specified by the domain expert and common quality dimensions of process mining.

Fast Incremental Conformance Analysis for Interactive Process Discovery

Interactive process discovery allows users to specify domain knowledge while discovering process models with the help of event logs. Typically the coherence of an event log and a process model is calculated using conformance analysis. Many state-of-the-art conformance techniques emphasize on the correctness of the results, and hence can be slow, impractical and undesirable in interactive process discovery setting, especially when the process models are complex. In this paper, we present a framework (and its application) to calculate conformance fast enough to guide the user in interactive process discovery. The proposed framework exploits the underlying techniques used for interactive process discovery in order to incrementally update the conformance results. We trade the accuracy of conformance for performance. However, the user is also provided with some diagnostic information, which can be useful for decision making in an interactive process discovery setting. The results show that our approach can be considerably faster than the traditional approaches and hence better suited in an interactive setting.

Interactive Data-Driven Process Model Construction

Process discovery algorithms address the problem of learning process models from event logs. Typically, in such settings a user’s activity is limited to configuring the parameters of the discovery algorithm, and hence the user expertise/domain knowledge can not be incorporated during traditional process discovery. In a setting where the event logs are noisy, incomplete and/or contain uninteresting activities, the process models discovered by discovery algorithms are often inaccurate and/or incomprehensible. Furthermore, many of these automated techniques can produce unsound models and/or cannot discover duplicate activities, silent activities etc. To overcome such shortcomings, we introduce a new concept to interactively discover a process model, by combining a user’s domain knowledge with the information from the event log. The discovered models are always sound and can have duplicate activities, silent activities etc. An objective evaluation and a case study shows that the proposed approach can outperform traditional discovery techniques.