Design
Dynamic Pricing Optimization for a Ride-Hailing Platform
Overview
What this challenge is about.
You are a data scientist at CityRide. Using 6 months of historical trip data (pickup/dropoff, time, fare, surge multiplier), weather data, and local events calendar, you must build a pricing model that sets fares in real-time. The model should maximize a weighted objective of revenue, rider satisfaction (measured by acceptance rate), and driver utilization. You need to prototype the model in Python, simulate its performance against the current surge policy, and provide a dashboard showing trade-offs. Success is a working prototype with clear performance improvements and a roadmap for production deployment.
The Brief
What you'll do, and what you'll demonstrate.
Design a dynamic pricing algorithm that optimizes a multi-objective function (revenue, rider satisfaction, driver utilization) using historical data and real-time signals.
Earning criteria — what you'll demonstrate
- Apply reinforcement learning or contextual bandits for dynamic pricing decisions
- Design a multi-objective optimization framework with trade-off analysis
- Build a simulation to evaluate pricing policies using historical data
- Incorporate external data (weather, events) as features in a time-series model
- Communicate complex algorithmic trade-offs to business stakeholders
Program Fit
Where this fits in your program.
Sharpens the same skills your degree expects you to demonstrate.
Skills
Skills you'll demonstrate.
Each one shows up on your verified credential.
Careers
Roles this prepares you for.
Real titles. Real skill bridges. Pick the one closest to your trajectory.
Career mappings coming soon.