A general process mining framework for correlating, predicting and clustering dynamic behavior based on event logs

Leoni, Massimiliano de; Aalst, Wil M. P. van der; Dees, Marcus

doi:10.1016/j.is.2015.07.003

Cited by 195 publications

(111 citation statements)

References 30 publications

Supporting

Mentioning

109

Contrasting

Unclassified

Order By: Relevance

“…Both classification algorithms have shown to be amongst the top performing classification algorithms on a variety of classification tasks [8,9]. We employ a single classifier approach where the features for a given prefix are obtained using the aggregation encoding [10], which has been shown to perform better than alternative encodings for event logs [3]. We apply the TPE optimization procedure for the alarming mechanism to find the optimal threshold τ .…”

Section: Approaches and Baselinesmentioning

confidence: 99%

Alarm-Based Prescriptive Process Monitoring

Teinemaa

Tax

Leoni

et al. 2018

Lecture Notes in Business Information Processing

Self Cite

View full text Add to dashboard Cite

Predictive process monitoring is concerned with the analysis of events produced during the execution of a process in order to predict the future state of ongoing cases thereof. Existing techniques in this field are able to predict, at each step of a case, the likelihood that the case will end up in an undesired outcome. These techniques, however, do not take into account what process workers may do with the generated predictions in order to decrease the likelihood of undesired outcomes. This paper proposes a framework for prescriptive process monitoring, which extends predictive process monitoring approaches with the concepts of alarms, interventions, compensations, and mitigation effects. The framework incorporates a parameterized cost model to assess the cost-benefit tradeoffs of applying prescriptive process monitoring in a given setting. The paper also outlines an approach to optimize the generation of alarms given a dataset and a set of cost model parameters. The proposed approach is empirically evaluated using a range of real-life event logs. ⋆

show abstract

Section: Approaches and Baselinesmentioning

confidence: 99%

Alarm-Based Prescriptive Process Monitoring

Teinemaa

Tax

Leoni

et al. 2018

Lecture Notes in Business Information Processing

Self Cite

View full text Add to dashboard Cite

show abstract

“…performance measures) from event logs. For example, de Leoni et al [21,22] propose a framework to extract process performance characteristics from event logs and to correlate them in order to discriminate, for example, between the performance of cases that lead to "positive" outcomes versus "negative" outcomes. In [33], the authors present an extensible framework for extracting knowledge from event logs about the behavior of a human resource and for analyzing the dynamics of this behavior over time.…”

Section: Approaches and Tools (Rq3)mentioning

confidence: 99%

“…A business seeking to conduct data-driven performance analysis, should first select the type of technique. Descriptive analysis will show the current state and [34], [23], [5], [6], [32], [3] Process Duration -- [41] Fragment Duration Activity Start and End Time [7], [24], [23], [17], [5] Activity Duration -- [19], [31], [29], [34], [7], [24] Waiting Duration [30], [38], [36], [ [21], [22] Framework to extract process characteristics from event logs discriminating between positive and negative cases [5], [6] Comparing waiting duration of similar process in different installations [11], [15] Collaborative Processes [26] Evolution of performance over time [40] Framework for performance-related analysis with information-poor event logs Type Domain…”

Section: Frameworkmentioning

confidence: 99%

A Comparative Evaluation of Log-Based Process Performance Analysis Techniques

Milani

Maggi

2018

Business Information Systems

View full text Add to dashboard Cite

Process mining has gained traction over the past decade and an impressive body of research has resulted in the introduction of a variety of process mining approaches measuring process performance. Having this set of techniques available, organizations might find it difficult to identify which approach is best suited considering context, performance indicator, and data availability. In light of this challenge, this paper aims at introducing a framework for categorizing and selecting performance analysis approaches based on existing research. We start from a systematic literature review for identifying the existing works discussing how to measure process performance based on information retrieved from event logs. Then, the proposed framework is built starting from the information retrieved from these studies taking into consideration different aspects of performance analysis. accessibility to open source tools has never been easier, in particular for data driven analysis of business processes. Therefore, in a digital era, businesses cannot hope to survive with manually driven methods. The process analysis must also be digitally transformed by tapping into data-driven analysis methods.One group of techniques for data driven performance analysis uses event logs of processes to assess performance. Indeed, nowadays, business processes are often supported by IT systems that log their execution. For instance, an order-to-invoice process might include activities such as register, validate, approve, fill order and send invoice. Each order has a unique id and every activity is recorded in the event log with information about the time when it was executed (timestamp) and other additional data such as the resource (person or device) that executed the activity. As such, the process is inherently captured in the log. With process mining techniques [2], the performance of such processes can be assessed and analyzed in great detail based on event logs.The body of research and tools within the field of process mining has grown significantly during this decade. However, the availability of tools and approaches developed for specific aspects of process performance does not make it easier for businesses to employ them. In fact, it poses a challenge. There is no way for businesses to easily get an overview of what performance indicators can be measured, what input data is required for such analysis, or what industry specific implementations are available. In light of this context, we propose a framework for the selection of log-based performance analysis techniques. We do so by conducting a systematic literature review to identify the body of existing work. We analyze the results and focus on identifying existing process performance indicators, required input data, and approaches available. Based on the results, we build a framework for the selection of suitable performance analysis approaches.The structure of this paper is as follows. Section 2 summarizes the research protocol for the systematic survey. In Section 3, the research que...

show abstract

“…Academic and commercial process mining tools aim to find the root causes of performance or compliance problems in processes. Mainly, a classifier, say a decision tree, is created using the data gathered from the process and then the rule mining is done using that decision tree [14]. However, this approach may lead to diagnoses that are not valuable.…”

Section: Introductionmentioning

confidence: 99%

“…Process mining is the link between model-based process analysis and data-oriented analysis techniques; a set of techniques that support the analysis of business processes based on event logs. In this context, several works have been dedicated to decision mining and finding the correlation among the process data and making predictions [5,13,14,16].…”

Section: Introductionmentioning

confidence: 99%

Fairness-Aware Process Mining

Qafari

Aalst

2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Process mining is a multi-purpose tool enabling organizations to improve their processes. One of the primary purposes of process mining is finding the root causes of performance or compliance problems in processes. The usual way of doing so is by gathering data from the process event log and other sources and then applying some data mining and machine learning techniques. However, the results of applying such techniques are not always acceptable. In many situations, this approach is prone to making obvious or unfair diagnoses and applying them may result in conclusions that are unsurprising or even discriminating (e.g., blaming overloaded employees for delays). In this paper, we present a solution to this problem by creating a fair classifier for such situations. The undesired effects are removed at the expense of reduction on the accuracy of the resulting classifier. We have implemented this method as a plug-in in ProM. Using the implemented plug-in on two real event logs, we decreased the discrimination caused by the classifier, while losing a small fraction of its accuracy.

show abstract

A general process mining framework for correlating, predicting and clustering dynamic behavior based on event logs

Cited by 195 publications

References 30 publications

Alarm-Based Prescriptive Process Monitoring

Alarm-Based Prescriptive Process Monitoring

A Comparative Evaluation of Log-Based Process Performance Analysis Techniques

Fairness-Aware Process Mining

Contact Info

Product

Resources

About