Ride-Hailing Operations Intelligence: A Comprehensive Business Intelligence Study of Booking Patterns, Revenue Distribution, Cancellation Drivers, and Payment Analytics Using Microsoft Power BI

Authors:

Varun Jariwala

Department of Computer Science and Engineering Parul University, Vadodara, India varunjariwala98@gmail.com

Guide: Suraj Singh

Department of Computer Science and Engineering Parul University, Vadodara, India suraj.singh34612@paruluniversity.ac.in

Abstract:

The urban ride-hailing industry now generates massive transactional datasets that, when subjected to rigorous analytical scrutiny, reveal actionable intelligence across pricing, fleet management, and demand planning. This paper presents a multi- dimensional business intelligence study conducted on a ride-hailing transaction corpus of 148,767 booking records spanning six vehicle categories — Auto, Bike, Go Mini, Go Sedan, Premier Sedan, and Uber XL — processed and visualised through an interactive four-page Microsoft Power BI dashboard. The analysis examines booking completion and cancellation dynamics (92,551 completed rides, 56,817 loss bookings, overall cancellation rate of 38.2%), disaggregated revenue contribution across vehicle tiers (total booking value INR 51,846,183), monthly demand seasonality across a full calendar year, customer payment instrument preferences across five channels, and structured cancellation attribution by party and reason. The dashboard architecture employs a persistent vehicle-type slicer, DAX-driven dynamic measures including the core Booking_value = SUM(uber[Booking Value]) formula, and four thematically distinct report pages delivering segment-level drill-down without requiring machine learning infrastructure. Key findings establish that Auto and Bike collectively account for 46.94% of total platform revenue, that UPI leads all payment channels, that February records the sharpest demand trough of the year, and that the predominance of blank cancellation reason records (approximately 55% of loss bookings) represents a critical data collection gap warranting structural remediation. The study demonstrates that well-structured Power BI analytics pipelines can surface decision-relevant operational insight from ride-hailing transaction logs in a form immediately consumable by fleet managers, operations analysts, and strategic stakeholders.

Keywords — Ride-Hailing Analytics, Power BI, Business Intelligence, DAX, Booking Cancellation Analysis, Fleet Management, Revenue Distribution, Urban Mobility, Payment Method Analysis, Demand Seasonality, Data Visualization.