<![CDATA[This study aims to develop a Business Intelligence system based on Data Mining and Predictive Analytics to analyze the behavioral patterns of online transportation drivers, predict potential driver churn, and improve the operational efficiency of transportation companies through an interactive dashboard. The research employs a quantitative approach involving the development of a Data Warehouse, the implementation of the Extract, Transform, Load (ETL) process, the application of the Random Forest algorithm for driver Churn Prediction, clustering analysis to classify drivers based on their operational behavior, and the visualization of analytical results using an interactive Business Intelligence dashboard for real-time monitoring. The dataset includes drivers' daily activities, number of completed orders, income levels, customer ratings, order cancellation rates, operating hours, and driver activity status history. The results demonstrate that the proposed system improves operational reporting efficiency by up to 92% and achieves a driver Churn Prediction accuracy of 89%. Furthermore, the system provides analytical insights that assist management in identifying the key factors influencing driver performance decline and the likelihood of driver attrition. The interactive dashboard also facilitates real-time performance monitoring, order distribution evaluation, identification of high-churn regions, and the formulation of data-driven driver retention strategies. The novelty of this research lies in the integration of Business Intelligence, Data Mining, Predictive Analytics, and an interactive dashboard into a unified analytical platform that supports comprehensive strategic decision-making for online transportation companies. This integrated approach contributes to improved resource management, enhanced operational efficiency, and better service quality through evidence-based decision support.]]>
Copyrights © 2026
