Predictive Monitoring of Business Processes: A Case Study Using a Cumulative Fact Table Model

Predictive Business Process Monitoring (BPPM) is an increasingly used technique to anticipate future events within organizations, based on the analysis of historical and real-time data. This article explores the application of a cumulative fact table model in a data warehouse to improve the accuracy and speed of predictions within the context of BPPM. Through a case study in the logistics sector, the proposed model significantly reduced the error rate in delivery time predictions and enabled faster anomaly detection compared to traditional methods. This approach has proven particularly effective for real-time monitoring of business processes, while also highlighting the need for a robust data infrastructure for its implementation.