This project delivers a deep-dive analysis into urban mobility trends using a large-scale dataset of 150,000+ Uber booking transactions. By leveraging Power BI, I built an interactive dashboard to track revenue operations, understand ride cancellation behaviors, and evaluate driver-customer satisfaction.
Based on the comprehensive dataset analysis, the core performance metrics are:
- Total Bookings Managed: 150,000 rides
- Completed Bookings: 93,000 successful rides
- Lost Bookings (Cancellations/Incomplete): 57,000 rides
- Total Revenue Generated: ₹51.84 Million (₹5,18,46,183)
- Total Distance Covered: 2.51 Million Kilometers
- Average Customer Rating: 4.40 / 5.0
- Average Driver Rating: 4.23 / 5.0
- Business Intelligence: Power BI (Desktop)
- Data Engineering: Power Query (Advanced Data Profiling, handling null values in cancellation columns, and data type casting)
- Data Source:
uber.xlsx(150K records covering booking statuses, vehicle types, pickup/drop locations, and payment modes)
- Power BI Dashboard Development
- Power Query (ETL)
- Data Cleaning & Transformation
- Data Modeling
- DAX Calculations
- KPI Development
- Data Visualization
- Business Intelligence
- Revenue Analysis
- Customer Analytics
- Operational Analytics
- Transportation Analytics
Below is the preview of the comprehensive Uber ride analytics dashboard:
(Note: Ensure your dashboard screenshot is uploaded to this repository and named exactly 'uber_dashboard.png')
- Ride Funnel Analysis: Breaks down the total bookings into
Completed,Cancelled by Customer,Cancelled by Driver, andNo Driver Foundto address revenue leakage. - Lost Booking Deep-Dive: Identifies the top reasons for cancellations (e.g., "Change of plans" by customers or operational issues by drivers) to enhance operational efficiency.
- Fleet Demographics: Segments performance across multiple vehicle types including Auto, Bike, Go Mini, Go Sedan, Premier Sedan, and Uber XL.
- Customer & Driver Feedback Loop: Compares driver ratings against customer ratings to maintain high service-quality standards and detect low-performing zones.
- Financial & Distance Breakdown: Visualizes revenue trends alongside trip distances across popular pickup and drop-off hotspots.
- Reduce Lost Bookings: Implement stricter dynamic-pricing or small cancellation penalties to minimize "Change of plans" cancellations from customers.
- Driver Allocation: Optimize driver dispatch routines in high-demand pickup locations where "No Driver Found" occurrences are frequent.
- Payment Optimization: Streamline cash and digital wallet gateways based on customer payment preferences to accelerate checkout speeds.