A Deep Learning Approach for Repairing Missing Activity Labels in Event Logs for Process Mining

TL;DR

This paper introduces an LSTM-based model that predicts missing activity labels in event logs, improving process discovery accuracy when data is incomplete.

Contribution

The paper presents a novel LSTM-based approach that leverages prefix, suffix, and additional attributes to accurately repair missing activity labels in event logs.

Findings

Outperforms existing methods in repairing missing labels

Consistent improvement across multiple datasets

Effective use of prefix, suffix, and attribute data

Abstract

Process mining is a relatively new subject that builds a bridge between traditional process modeling and data mining. Process discovery is one of the most critical parts of process mining, which aims at discovering process models automatically from event logs. The performance of existing process discovery algorithms can be affected when there are missing activity labels in event logs. Several methods have been proposed to repair missing activity labels, but their accuracy can drop when a large number of activity labels are missing. In this paper, we propose an LSTM-based prediction model to predict the missing activity labels in event logs. The proposed model takes both the prefix and suffix sequences of the events with missing activity labels as input. Additional attributes of event logs are also utilized to improve the performance. Our evaluation of several publicly available datasets shows that the proposed method performed consistently better than existing methods in terms of repairing missing activity labels in event logs.