"Analyzing Ride Patterns & Pricing Strategies in Uber"
Summary Website:Link
| 🧾 Detail | 📍 Information |
|---|---|
| Project Title | 🚖 Analyzing Ride Patterns & Pricing Strategies in Uber |
| Course | 📚 Business Data Management (BDM) - IIT Madras |
| Project Type | 🎓 Academic Capstone |
| Team Member | Achal Deep (22F3000694) |
- Investigating Ride Demand Fluctuations and Peak-Hour Congestion
- Assessing Ride Cancellations and Driver Availability Gaps
- Optimizing Route Planning for Efficiency
- Data Type: Secondary (publicly available)
- Source: Kaggle verified repositories
1. Uber NYC Enriched Pickups - Dataset Link
- Hourly Uber pickups across NYC boroughs
- Attributes: Borough, Date & Hour, Number of Pickups, Weather factors (temperature, wind speed, visibility, precipitation), Holiday indicator, Month & Day
- Records: ~29,101 pickups
2. City-Airport Request Data - Dataset Link
- Ride requests between city and airport pickup points
- Attributes: Request status, Demand vs. Supply, Cancellation patterns
- Records: ~6,745 total requests
- Descriptive Statistics: Summarizes the data to identify basic patterns and trends in ride demand.
- Correlation Analysis: Finds relationships between variables to identify key factors influencing demand.
- Temporal Analysis: Analyzes how demand changes over time to forecast peaks and troughs.
- Spatial-Temporal Patterns: Shows how demand varies by location and time to optimize driver deployment.
- Operational Gap Analysis: Identifies reasons for service failures to target specific operational issues.
- ⚡ Implement dynamic pricing during evening rush hours (6 PM–midnight)
- 🎯 Launch promotions for low-demand periods
- 🚦 Partner with traffic authorities for congestion management
✈️ Create guaranteed earnings for airport drivers to address shortages- 📱 Deploy real-time tracking with accurate ETAs to reduce city cancellations
- 🔄 Integrate backup transport during peak demand at airports
- 🤖 Build ML models for intelligent route planning
- 🧪 Test new routing algorithms via pilot studies
- 📋 Establish driver feedback system for navigation improvements
- Analysis & Visualization: 🐍 Python · 📦 Pandas · 🔢 NumPy · 📈 Matplotlib · 🌊 Seaborn
- Reporting & Documentation: 📝 Google Docs · 📓 Jupyter Notebooks · 🎨 Canva
- Frontend: 🖥️ HTML · 🎨 Tailwind CSS · ⚡ JavaScript (Chart.js)
Achal Deep
- 🎓 Roll No: 22F3000694
- 🏫 IIT Madras · BS Degree Program (Data Science & Applications)
📄 Licensed under the MIT License – see the LICENSE file for details.