New publication for the International Conference on Process Mining: “Time-Aware LSTMs for Predictive Business Process Monitoring”

Symbolbild zum Artikel. Der Link öffnet das Bild in einer großen Anzeige.

In the anticipation of the second International Conference on Process Mining (ICPM) our chair is delighted to introduce a new publication, which was written in cooperation with Machine Learning and Data Analytics Lab from FAU: “Time Matters: Time-Aware LSTMs for Predictive Business Process Monitoring”. In this paper An Nguyen, Srijeet Chatterjee, Sven Weinzierl, Leo Schwinn, Martin Matzner and Björn Eskofier propose a new predictive business process monitoring (PBPM) technique based on time-aware long short-term memory (T-LSTM) cells, which allows for better modelling of time dependencies between events. Furthermore, they introduce cost-sensitive learning to account for the common class imbalance in event logs.