University of Qom Journal of Data Analytics and Intelligent Decision-making 3115-8161 2 3 2026 07 01 Predicting Remaining Time in Object-Centric Process Executions Using Machine Learning Models 154 166 4877 10.22091/jdaid.2026.16354.1075 EN Mohsen Mohammadi Corresponding Author, Department of Computer engineering, Esfarayen University of Technology, Esfarayen, Iran. Email: mohsen@esfarayen.ac.ir 0000-0003-0532-1236 Journal Article 2026 06 12 Objective: Predictive process monitoring is critical for effective business process management; however, current approaches relying on case-centric logs often fail to capture the dynamics of complex, multi-object interactions. This study proposes a framework for object-centric remaining time prediction, facilitating proactive operational decisions, including systematic delay reduction, optimized resource allocation, and enhanced service quality.<br />Method: We developed a prediction methodology leveraging object-centric event data from real-world logs. Our feature engineering captured multidimensional information, including temporal dynamics, elapsed execution time, sequential activity history, and intricate interactions between interrelated process objects. These features were used to train and compare three machine learning architectures: a Linear Regression baseline, Random Forest, and the Gradient Boosting algorithm.<br />Results: Empirical analysis reveals that ensemble tree-based methods consistently outperform the linear baseline. Specifically, the Gradient Boosting model demonstrated superior prediction accuracy, successfully mitigating the noise inherent in complex process data. Feature importance analysis confirmed that elapsed time, activity histories, and object-centric interaction features serve as the most influential predictors for remaining time.<br />Conclusion: This research confirms that synthesizing object-centric feature extraction with ensemble learning provides a practical solution for time prediction in complex, multi-object environments. By addressing the limitations of case-centric assumptions, this approach enables more reliable forecasting and enhances operational decision-making in diverse real-world process management contexts, thereby bridging a significant research gap. https://jdaid.qom.ac.ir/article_4877_f9332a2faa1d6e1d5a1498e53a5dbca0.pdf