Business Analytics for Ride-Hailing Platforms: Demand Forecasting and Ride-Completion Modeling

Digital ride-hailing platforms operate in dynamic environments characterized by fluctuating demand and variable user behavior. Business analytics plays a key role in supporting data-driven decision-making and operational planning in such systems. This study examines the application of descriptive and predictive analytics to analyze ride demand and ride completion behavior on a digital transportation platform. The empirical analysis is based on a dataset containing ride-level and user-related information. Descriptive analytics is used to preprocess the data, generate summary statistics, and identify temporal demand patterns. Predictive analytics is applied to forecast short-term ride demand using time-series methods and to model ride completion as a binary outcome using logistic regression. The results indicate that ride demand exhibits recurring temporal patterns suitable for short-horizon forecasting, with exponential smoothing achieving improved accuracy compared to a naïve approach. In addition, waiting time is identified as a key factor influencing ride completion probability. The findings demonstrate that business analytics can support proactive demand management, improved resource allocation, and enhanced understanding of user behavior in ride-hailing services.