Unsupervised Event Abstraction using Pattern Abstraction and Local Process Models

TL;DR

This paper introduces an unsupervised method for event abstraction in process mining, using local process models to improve the quality of discovered process models by reducing overgeneralization.

Contribution

It proposes a novel approach that first discovers local process models and then uses them to elevate event logs to a higher abstraction level, enhancing process model quality.

Findings

Higher quality process models with better fitness and precision.

Preliminary results on real-life logs support the approach.

Method reduces overgeneralization in process discovery.

Abstract

Process mining analyzes business processes based on events stored in event logs. However, some recorded events may correspond to activities on a very low level of abstraction. When events are recorded on a too low level of granularity, process discovery methods tend to generate overgeneralizing process models. Grouping low-level events to higher level activities, i.e., event abstraction, can be used to discover better process models. Existing event abstraction methods are mainly based on common sub-sequences and clustering techniques. In this paper, we propose to first discover local process models and then use those models to lift the event log to a higher level of abstraction. Our conjecture is that process models discovered on the obtained high-level event log return process models of higher quality: their fitness and precision scores are more balanced. We show this with preliminary results on several real-life event logs.