An Improved Way for Measuring Simplicity During Process Discovery

Lieben, Jonas; Jouck, Toon; Depaire, Benoît; Jans, Mieke

doi:10.1007/978-3-030-00787-4_4

Cited by 4 publications

(6 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Analysis techniques should be expanded beyond a 'single focus' perspective, and be able to automatically include domain knowledge that enable analysts to interpret the results in their context (de Medeiros et al 2007). Furthermore, more efficient or even simpler visualization of the results is needed to ease the access of the analysis outcome not only for specialized consultants but also for process participants (Buijs et al 2014;Lieben et al 2018).…”

Section: Discussionmentioning

confidence: 99%

Seven Paradoxes of Business Process Management in a Hyper-Connected World

et al. 2020

View full text Add to dashboard Cite

Business Process Management is a boundaryspanning discipline that aligns operational capabilities and technology to design and manage business processes. The Digital Transformation has enabled human actors, information systems, and smart products to interact with each other via multiple digital channels. The emergence of this hyper-connected world greatly leverages the prospects of business processes -but also boosts their complexity to a new level. We need to discuss how the BPM discipline can find new ways for identifying, analyzing, designing, implementing, executing, and monitoring business processes. In this research note, selected transformative trends are explored and their impact on current theories and IT artifacts in the BPM discipline is discussed to stimulate transformative thinking and prospective research in this field.

show abstract

Section: Discussionmentioning

confidence: 99%

Seven Paradoxes of Business Process Management in a Hyper-Connected World

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Complexity is measured by ten metrics in total. These are cognitive weight, token split, connector heterogeneity, control flow complexity, sequentiality, cyclicity, diameter, depth, density and coefficient of network connectivity [13]. From these ten, token split, connector heterogeneity, control flow complexity, sequentiality, cyclicity and the coefficient of network connectivity did not improve on average due to event abstraction for any activity pattern miner, regardless of the process model miner.…”

Section: The Effect Of Abstraction On Model Complexitymentioning

confidence: 95%

“…To evaluate the comprehensibility of the model discovered from the transformed log, we use complexity as a proxy, which has been shown to be inversely related to the model understandability [17]. In total, ten complexity metrics were used, covering the four complexity dimensions identified in [13] 1 . These complexity metrics are computed for the process models discovered from the transformed event logs.…”

Section: Evaluation Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Unsupervised Event Abstraction in a Process Mining Context: A Benchmark Study

Houdt

Depaire

Martin

2021

Lecture Notes in Business Information Processing

Self Cite

View full text Add to dashboard Cite

Due to the rise of IoT, event data becomes increasingly finegrained. Faced with such data, process discovery often produces incomprehensible spaghetti-models expressed at a granularity level that doesn't match the mental model of a business user. One approach is to use event abstraction patterns to transform the event log towards a more coarsegrained level and to discover process models from this transformed log. Recent literature has produced various (partial) implementations of this approach, but insights how these techniques compare against each other is still limited.This paper focuses on the use of Local Process Models and Combination based Behavioural Pattern Mining to discover event abstraction patterns in combination with the approach of Mannhardt et al. [15] to transform the event log. Experiments are conducted to gain insights into the performance of these techniques. Results are very limited with a general decrease in fitness and precision and only a minimal improvement of complexity. Results also show that the combination of the process discovery algorithm and the event abstraction pattern miner matters. In particular, the combination of Local Process Models with Split Miner seems to improve precision.

show abstract

“…1, and describes all the traces in the log (has perfect fitness of 1.0); the measures take values on the interval [0, 1] with larger values showing better precision and fitness. To assess the simplicity of discovered process models, measures of their structural complexity [4,9,15,17], such as the number of nodes and/or edges, density, depth, coefficients of network connectivity, and control flow complexity, can be employed. If one relies on the number of nodes to establish the simplicity of the two example models, then they will derive at the conclusion that they are equally simple, as both contain ten nodes.…”

Section: Motivating Examplementioning

confidence: 99%

A Framework for Estimating Simplicity of Automatically Discovered Process Models Based on Structural and Behavioral Characteristics

Kalenkova

Polyvyanyy

Rosa

2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

A plethora of algorithms for automatically discovering process models from event logs has emerged. The discovered models are used for analysis and come with a graphical flowchart-like representation that supports their comprehension by analysts. According to the Occam's Razor principle, a model should encode the process behavior with as few constructs as possible, that is, it should not be overcomplicated without necessity. The simpler the graphical representation, the easier the described behavior can be understood by a stakeholder. Conversely, and intuitively, a complex representation should be harder to understand. Although various conformance checking techniques that relate the behavior of discovered models to the behavior recorded in event logs have been proposed, there are no methods for evaluating whether this behavior is represented in the simplest possible way. Existing techniques for measuring the simplicity of discovered models focus on their structural characteristics such as size or density, and ignore the behavior these models encoded. In this paper, we present a conceptual framework that can be instantiated into a concrete approach for estimating the simplicity of a model, considering the behavior the model describes, thus allowing a more holistic analysis. The reported evaluation over real-life event logs for several instantiations of the framework demonstrates its feasibility in practice.

show abstract

An Improved Way for Measuring Simplicity During Process Discovery

Cited by 4 publications

References 16 publications

Seven Paradoxes of Business Process Management in a Hyper-Connected World

Seven Paradoxes of Business Process Management in a Hyper-Connected World

Unsupervised Event Abstraction in a Process Mining Context: A Benchmark Study

A Framework for Estimating Simplicity of Automatically Discovered Process Models Based on Structural and Behavioral Characteristics

Contact Info

Product

Resources

About