What Time Is It? Finding Which Temporal Features is More Useful for Next Activity Prediction

作     者：Aversano, Lerina Iammarino, Martina Madau, Antonella Pirlo, Giuseppe Semeraro, Gianfranco 

作者机构：Univ Foggia Dept Agr Sci Food Nat Resources & Engn I-71122 Foggia Italy European Digital Innovat Hub Digital Transformat E I-70124 Bari Italy Pegaso Univ Dept Informat Sci & Technol I-80143 Naples Italy Univ Sannio Dept Engn I-82100 Benevento Italy Univ Bari Aldo Moro Dept Comp Sci I-70121 Bari Italy Univ Sch Adv Studies IUSS Pavia I-27100 Pavia Italy 

出 版 物：《IEEE OPEN JOURNAL OF THE COMPUTER SOCIETY》 (IEEE Open J. Comput. Soc.)

年 卷 期：2025年第6卷第1期

页      面：261-271页

核心收录：

基　　金：European Digital Innovation Hub for Digital Transformation- EDIH4DT  Bari  Italy [B97H22004910008] 

主　　题：Predictive models Feature extraction Process monitoring Process mining Accuracy Machine learning algorithms Distance measurement Deep learning Data science Context modeling next activity prediction temporal information classification predictive process monitoring 

摘      要：Process Mining merges data science and process science that allows for the analysis of recorded process data by capturing activities within event-logs. It finds more and more applications for the optimization of the production and administrative processes of private companies and public administrations. This field consists of several areas: process discovery, compliance monitoring, process improvement, and predictive process monitoring. Considering predictive process monitoring, the subarea of next activity prediction helps to obtain a prediction about the next activity performed using control flow data, event data with no attributes other than the timestamp, activity label, and case identifier. A popular approach in this subarea is to use sub-sequences of events, called prefixes and extracted with a sliding window, to predict the next activity. In the literature, several features are added to increase performance. Specifically, this article addresses the problem of predicting the next activity in predictive process monitoring, focusing on the usefulness of temporal features. While past research has explored a variety of features to improve prediction accuracy, the contribution of temporal information remains unclear. In this article it is proposed a comparative analysis of temporal features, such as differences in timestamp, time of day, and day of week, extracted for each event in a prefix. Using both k-fold cross-validation for robust benchmarking and a 75/25 split to simulate real scenarios in which new process events are predicted based on past data, it is shown that timestamp differences within the same prefix consistently outperform other temporal features. Our results are further validated by Shapley s value analysis, highlighting the importance of timestamp differences in improving the accuracy of next activity prediction.