Erp Project Failure Prediction using Machine Learning Algorithms

Enterprise Resource Planning (ERP) systems streamline business operations, yet many projects fail due to complexity. This research aims to predict ERP project outcomes using machine learning to identify key success and failure factors. The dataset initially contained 1,000 rows and 9 columns, but it was preprocessed to enhance data quality for machine learning analysis. It includes ERP project data from various industries, covering industry type, project scale, budget and time overruns, team experience, and technical challenges. The study applies logistic regression, decision trees, support vector machine and random forests to evaluate predictor significance. Findings reveal patterns that help forecast high-risk projects, providing project managers with a proactive decision-making framework. The results of this research offer insights into ERP project risk assessment and mitigation, enhancing strategic planning in enterprise environments.