Explainable Machine Learning and Process Mining for ERP-Enabled Business Process Improvement: Evidence from Steel Manufacturing

Abstract

Enterprise Resource Planning (ERP) systems generate transactional data, but their value for process improvement depends on converting these records into reliable event logs and useful predictions. This study evaluated a framework combining event-log readiness assessment, process mining, predictive process monitoring, transparent machine learning, and domain validation in an Ecuadorian steel manufacturer. The analysis used 3740 production orders and 31,791 ERP-recorded events, split chronologically into training, validation, and out-of-time test samples. Process discovery identified execution heterogeneity; rework, accumulated waiting, route deviations, and resource congestion were positively associated with deadline violation. At production start, the process-aware ridge logistic model achieved a PR-AUC of 0.839, compared with 0.419 for the static representation and 0.683 for the remaining-slack benchmark, with an ROC-AUC of 0.893, a Brier score of 0.123, and a sensitivity of 0.804. The first material transaction was the earliest operationally useful checkpoint, preserving a median intervention window of 98.7 h before the committed completion date among predicted-positive cases. Additive model decomposition highlighted material-related waiting, queue waiting, partial material issues, and accumulated deviations as contributors to fitted risk. A nine-expert panel translated the evidence into six operational and tactical improvement opportunities. Findings support ERP-based early-warning process intelligence when readiness, temporal validation, calibration, transparency, and actionability are addressed jointly.