Design a Fair Driver-Performance Framework

Context: Amazon currently tracks only two measures per driver: (1) number of packages delivered and (2) total delivery time. Design a robust, fair framework to evaluate delivery-driver performance that accounts for factors outside the driver’s control and yields actionable insights.

Tasks

1. Identify additional data to collect (e.g., route characteristics, weather, traffic, package weight/volume, customer feedback, vehicle type, stop density, promised delivery windows).
2. Explain why each data point matters and how you would gather it.
3. Propose quantitative metrics or a scoring model that fairly compares drivers operating under different conditions.
4. Outline how to surface insights to drivers and managers and how to iterate on the system over time.

Hints:

• Normalize for outside-control factors (distance, urban vs. rural, real-time weather/traffic, peak season).
• Include leading (process) and lagging (outcome) indicators: safety incidents, on-time rate, customer satisfaction, fuel efficiency.
• Use statistical/ML techniques (e.g., regression, clustering) to isolate driver impact from external noise.