Analyze Causes for 10% Decline in LA Deliveries

Q: Analyze Causes for 10% Decline in LA Deliveries

This question evaluates a data scientist's marketplace analytics, root-cause diagnostic, and causal-inference skills by requiring hypothesis generation across supply, demand, merchant, product, external factors, and measurement error; it is categorized under Analytics & Experimentation and is commonly asked to assess analytical reasoning, statistical rigor, and the ability to attribute metric changes when immediate A/B testing is unavailable. It tests domain knowledge in marketplace metrics, segmentation, experiment design and observational methods at a practical-application level with an expectation of conceptual understanding of causal inference, required data cuts, and robustness checks.

Q: How do I approach Analytics & Experimentation interview questions?

Analytics & Experimentation questions require understanding of core concepts and practice. PracHub provides solutions with explanations to help you master analytics & experimentation interviews.

Q: What difficulty level is this interview question?

This is a medium difficulty Analytics & Experimentation question, commonly asked during Technical Screen rounds at DoorDash.

Q: What role is this question designed for?

This question is commonly asked for Data Scientist candidates at DoorDash during technical interviews.

Question

Marketplace Analytics Case: 10% Delivery Decline in Los Angeles

Background

A food-delivery marketplace observes that completed deliveries in Los Angeles fell by 10% week-over-week (WoW). The metric refers to completed orders in the LA market during the most recent full week relative to the prior full week.

Task

List plausible root causes for a 10% WoW decline in LA deliveries. Organize them by supply, demand, merchant, marketplace/product, and external factors (plus measurement error).
For each hypothesis, outline a concrete analytical plan to test it: key cuts, metrics, data needed, and the statistical/causal approach.
If controlled experiments are infeasible, describe how you would validate and attribute impact using observational methods (e.g., difference-in-differences, synthetic controls), including guardrails and robustness checks.

Notes

Assume access to standard marketplace data: demand funnel (traffic → sessions → checkouts → orders placed), supply metrics (active couriers, online hours, acceptance/assignment/ETA), merchant availability (open hours, outages, item stockouts, prep times), pricing/fees/promotions, operations incidents, and external data (weather, traffic, events, gas prices).
Segment by time-of-day and sub-region within LA (e.g., ZIPs/neighborhoods). Cohort new vs. returning users and merchant types.
You cannot run an immediate A/B test in LA this week.

Analyze Causes for 10% Decline in LA Deliveries

Quick Overview

Marketplace Analytics Case: 10% Delivery Decline in Los Angeles

Background

Task

Notes

Solution

Comments (0)