Assess Adding Bicycle Dashers

Quick Overview

This question evaluates competency in experimental design, causal inference, marketplace analytics, metric definition, and handling network effects within a two-sided delivery platform.

Assess Adding Bicycle Dashers

Company: DoorDash

Role: Data Scientist

Category: Analytics & Experimentation

Difficulty: medium

Interview Round: Technical Screen

DoorDash is considering allowing **bicycle couriers (bike dashers)** to fulfill deliveries in a city that is currently served mostly by car/scooter dashers. How would you evaluate whether adding bike dashers is a good idea? Please address all of the following: 1. **Historical analysis:** What historical marketplace data would you use to decide whether this city or specific zones are suitable for bike dashers? 2. **Success criteria:** What primary metrics, secondary metrics, and guardrail metrics would you track? Consider consumer experience, merchant experience, dasher experience, and unit economics. 3. **Experiment design:** How would you run an A/B test or marketplace experiment to estimate the causal impact of enabling bike dashers? 4. **Network effects / interference:** Adding bike dashers can affect dispatching and matching for all orders, not just treated ones. How would you handle these spillover effects in the experiment design and analysis? 5. **Decision-making:** What results would convince you to launch, limit, or roll back the change? Assume you have access to order-level, merchant-level, dasher-level, zone-level, dispatch, weather, and geography data.

Quick Answer: This question evaluates competency in experimental design, causal inference, marketplace analytics, metric definition, and handling network effects within a two-sided delivery platform.

|Home/Analytics & Experimentation/DoorDash
DoorDash logo
DoorDash
Feb 2, 2026, 12:00 AM
mediumData ScientistTechnical ScreenAnalytics & Experimentation
5
0

DoorDash is considering allowing bicycle couriers (bike dashers) to fulfill deliveries in a city that is currently served mostly by car/scooter dashers.

How would you evaluate whether adding bike dashers is a good idea?

Please address all of the following:

  1. Historical analysis: What historical marketplace data would you use to decide whether this city or specific zones are suitable for bike dashers?
  2. Success criteria: What primary metrics, secondary metrics, and guardrail metrics would you track? Consider consumer experience, merchant experience, dasher experience, and unit economics.
  3. Experiment design: How would you run an A/B test or marketplace experiment to estimate the causal impact of enabling bike dashers?
  4. Network effects / interference: Adding bike dashers can affect dispatching and matching for all orders, not just treated ones. How would you handle these spillover effects in the experiment design and analysis?
  5. Decision-making: What results would convince you to launch, limit, or roll back the change?

Assume you have access to order-level, merchant-level, dasher-level, zone-level, dispatch, weather, and geography data.

Loading comments...