← DoorDash Interview Insights

DoorDash·Data Scientist·Technical Phone Screen·Senior

SeniorPrefer not to say
May 2026Remote

Summary

DoorDash data science case focused entirely on a late delivery problem for a two-sided platform. Five dense sub-questions covering metrics, root cause analysis, causal inference, modality gaps, and experiment design. Technically heavy and left me wishing I'd brushed up on power calculations before walking in.

Questions Asked (5)

Q1

How would you quantify the business impact of rising late deliveries? Walk through the metrics you'd track, a causal model linking lateness to customer behavior, and what data sources and calculation windows you'd use.

Product Analytics & MetricsData Modeling
Author's notes

This is where I spent too long listing metrics without anchoring them to decisions.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Start by framing the problem as a causal chain from late deliveries to customer behavior and financial outcomes, then define metrics for each stage. Propose a causal model (e.g., late delivery → satisfaction → retention → LTV) and specify data sources and calculation windows to quantify the impact. Emphasize experimentation or quasi-experimental methods to isolate causality.

Pro tip: Use a difference-in-differences or propensity score matching approach to compare customers with late deliveries to similar customers without, controlling for confounders. Also, consider segmenting by customer tenure, order value, and delivery region to uncover heterogeneous effects.

1. Define the causal model

Map out the hypothesized causal path: late delivery → customer satisfaction (e.g., ratings, complaints) → behavioral changes (reorder rate, churn, support contacts) → financial impact (lost revenue, increased CAC).

2. Select metrics for each stage

Choose metrics like % late deliveries, average delay time, CSAT/NPS, reorder rate within 30 days, churn rate, customer lifetime value (LTV), and support contact rate. Ensure they are measurable and aligned with business goals.

3. Identify data sources and calculation windows

Specify data sources: delivery timestamps, order logs, customer feedback, CRM, and financial systems. Define windows: e.g., 7-day, 30-day, 90-day post-delivery for behavioral metrics; use rolling windows for trends.

4. Quantify impact with causal inference

Apply methods like A/B testing (if possible), difference-in-differences, or instrumental variables to estimate the effect of lateness on metrics. Calculate incremental impact (e.g., lost orders, revenue) by comparing treated vs. control groups.

5. Translate to business impact and validate

Convert behavioral changes into monetary terms (e.g., LTV reduction, increased support costs). Validate assumptions with sensitivity analysis and segment-level breakdowns to ensure robustness.

Key Points to Mention

  • Causal inference methods (e.g., difference-in-differences, propensity score matching) to isolate the effect of lateness from confounders.
  • Customer segmentation (e.g., new vs. loyal, high-value vs. low-value) to capture heterogeneous impacts.
  • Leading and lagging indicators: late delivery rate (leading) and churn/LTV (lagging).
  • Calculation windows: short-term (7-day reorder), medium-term (30-day retention), long-term (90-day LTV).
  • Data sources: delivery timestamps, order history, customer support tickets, satisfaction surveys, and financial records.
  • Business metrics: incremental revenue loss, increased customer acquisition cost, and support cost per late order.

AI-generated suggestions, not part of the candidate's original notes. May be inaccurate — verify before relying on them.

Q2

List at least five falsifiable root causes of increased delivery lateness and describe the exact data slices, fields, and table joins you'd use to investigate each one.

Root Cause AnalysisProduct Analytics & Metrics
Author's notes

Prep time error was my strongest answer since I knew the formula cold (actual minus quoted).

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Start by framing the problem as a metric decomposition: define delivery lateness precisely (e.g., actual delivery time minus estimated delivery time) and break it into its components (food prep, dasher assignment, travel, etc.). Then propose at least five falsifiable root causes, each with a clear hypothesis and the specific data slices, fields, and table joins needed to test it. Emphasize that each cause must be testable with data and that you would validate using statistical methods like A/B tests or causal inference.

Pro tip: Prioritize causes by potential impact and ease of validation, and mention that you'd check for data quality issues (e.g., missing timestamps) before diving deep. This shows you think like a scientist who balances rigor with pragmatism.

1. Define the metric and decompose

Clearly define what 'delivery lateness' means (e.g., actual delivery time > estimated delivery time) and decompose it into stages: order placement, restaurant prep, dasher assignment, pickup, and drop-off. This ensures each root cause maps to a specific stage.

2. Generate falsifiable hypotheses

List at least five root causes that are falsifiable (e.g., increased restaurant prep time, fewer available dashers, longer dasher travel distances, higher order volume, changes in estimated delivery time algorithm). For each, state a clear hypothesis that can be tested with data.

3. Identify data slices and fields

For each hypothesis, specify the exact data slices (e.g., time of day, region, restaurant type) and fields (e.g., order_id, dasher_id, restaurant_id, timestamps, distance) needed to investigate. This demonstrates attention to detail and data intuition.

4. Describe table joins and analysis

Explain how you would join tables (e.g., orders, deliveries, dashers, restaurants) to create a unified dataset for analysis. Mention specific join keys (e.g., order_id, dasher_id) and any aggregations or filters.

5. Validate and prioritize

Outline how you would validate each cause (e.g., regression, difference-in-differences, A/B test) and prioritize based on effect size and business impact. This shows you can move from analysis to actionable insights.

Key Points to Mention

  • Falsifiability: Each root cause must be testable and potentially disproven with data.
  • Data slices: Consider dimensions like time (hour, day of week), geography (region, city), restaurant (cuisine, prep time), and dasher (experience, vehicle type).
  • Specific fields: Timestamps (order_placed, dasher_assigned, pickup, dropoff), distances, estimated vs actual times, dasher availability, order volume.
  • Table joins: Join orders with deliveries on order_id, deliveries with dashers on dasher_id, orders with restaurants on restaurant_id, and possibly with a time dimension table.
  • Statistical methods: Use regression, causal inference (e.g., difference-in-differences), or A/B tests to validate causes.
  • Data quality: Check for missing or inaccurate timestamps and outliers before analysis.

AI-generated suggestions, not part of the candidate's original notes. May be inaccurate — verify before relying on them.

Q3

How would you prioritize the root causes you identified? Describe a scoring framework and an analysis approach that controls for confounding, including how you'd handle simultaneity between supply and demand.

Root Cause AnalysisA/B Testing & Experimentation
Author's notes

I went with impact times confidence times inverse effort, which felt reasonable.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Start by framing prioritization as a function of impact and confidence, then introduce a scoring framework that quantifies both. Explain how you'd control for confounding using causal inference techniques like instrumental variables or regression discontinuity, and address simultaneity by using simultaneous equation models or natural experiments.

Pro tip: Emphasize that in marketplace settings like DoorDash, simultaneity is the norm, so you'd leverage exogenous shocks (e.g., weather, policy changes) as instruments to disentangle supply and demand effects.

1. Define and Score Root Causes

List potential root causes and score each on impact (e.g., estimated effect size) and confidence (e.g., strength of evidence). Use a weighted scoring formula like Impact * Confidence to prioritize.

2. Control for Confounding

Identify confounders and apply methods like stratification, regression adjustment, or propensity score matching. Consider using causal graphs (DAGs) to guide variable selection.

3. Address Simultaneity

Use instrumental variables (IV) or two-stage least squares (2SLS) with exogenous shocks as instruments. Alternatively, employ natural experiments or panel data methods like fixed effects.

4. Validate and Iterate

Test assumptions (e.g., instrument relevance and exogeneity) and sensitivity analyses. Refine scores based on new evidence and re-prioritize.

Key Points to Mention

  • Impact vs. confidence scoring matrix
  • Causal inference techniques: DAGs, propensity scores, IV
  • Simultaneity bias and solutions: 2SLS, natural experiments
  • Use of exogenous shocks as instruments
  • Sensitivity analysis and robustness checks
  • Business context: marketplace dynamics at DoorDash

AI-generated suggestions, not part of the candidate's original notes. May be inaccurate — verify before relying on them.

Q4

Data shows food deliveries take longer than parcel deliveries even after controlling for distance. Come up with at least three competing hypotheses and describe a concrete test with an acceptance criterion for each.

Root Cause AnalysisProduct Analytics & Metrics
Author's notes

Favorite question of the whole thing.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Start by clarifying the metric definitions and the control variables, then brainstorm hypotheses that cover different stages of the delivery process (e.g., order preparation, courier assignment, routing, handoff). For each hypothesis, propose a test that uses available data and define a clear acceptance criterion (e.g., a statistically significant difference or a threshold effect size).

Pro tip: Focus on hypotheses that are actionable and testable with existing data; avoid vague explanations. Also, consider that food delivery often involves multiple items and special handling, which can be a key differentiator.

1. Clarify the metric and controls

Define what 'delivery time' includes (e.g., from order placement to delivery) and confirm that distance is controlled. Ask about other variables like time of day, location, and order size.

2. Brainstorm hypotheses

Generate at least three distinct hypotheses that could explain the difference. Consider factors like food preparation time, courier behavior, order complexity, and customer interaction.

3. Design concrete tests

For each hypothesis, specify a test using historical data or an experiment. Include the data sources, method (e.g., regression, A/B test), and how you would isolate the effect.

4. Define acceptance criteria

For each test, state what result would support the hypothesis (e.g., p-value < 0.05, effect size > X minutes). Also consider practical significance.

5. Prioritize and iterate

Discuss which hypothesis is most likely or impactful, and how you would validate further. Mention potential confounders and next steps.

Key Points to Mention

  • Food preparation time at restaurants is variable and often not included in parcel delivery.
  • Couriers may need to wait for food, handle multiple orders, or navigate complex pickups.
  • Food delivery often involves handoff to customer, which can add time (e.g., finding parking, waiting).
  • Order characteristics: food orders may have multiple items, special instructions, or higher value, leading to more careful handling.
  • Data considerations: need to control for restaurant prep time, courier experience, and time of day.
  • Use of natural experiments or instrumental variables to establish causality.

AI-generated suggestions, not part of the candidate's original notes. May be inaccurate — verify before relying on them.

Q5

Design an experiment to reduce delivery lateness. Cover the experimental unit, randomization and stratification, power calculation for a 12% baseline lateness rate, primary metrics and guardrails, ramp plan, and your decision rule to ship or roll back.

A/B Testing & ExperimentationProduct Analytics & Metrics
Author's notes

I chose earlier driver dispatch as the intervention since it felt tractable.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Start by clarifying the business goal and defining the experimental unit (e.g., delivery or dasher) and randomization strategy. Then outline the power calculation for a 12% baseline lateness rate, specify primary and guardrail metrics, and propose a ramp plan with a clear decision rule for shipping or rolling back.

Pro tip: Consider using a switchback or cluster randomization if delivery-level randomization risks contamination, and always pre-register your analysis plan to avoid p-hacking.

1. Define the Experiment

Clarify the hypothesis, experimental unit (e.g., delivery, dasher, or region), and randomization method. Discuss stratification by key covariates like market, time of day, and dasher experience.

2. Power Analysis

Calculate sample size needed to detect a meaningful reduction in lateness from a 12% baseline, specifying power (e.g., 80%) and significance level (e.g., 5%). Mention minimum detectable effect (MDE) and how it affects sample size.

3. Metrics and Guardrails

Choose primary metrics (e.g., lateness rate, delivery time) and guardrail metrics (e.g., dasher satisfaction, customer ratings, order volume) to monitor unintended consequences.

4. Ramp Plan and Decision Rule

Propose a phased rollout (e.g., 1%, 5%, 50%) with stopping rules for safety and efficacy. Define decision criteria: ship if primary metric improves significantly without guardrail degradation, roll back otherwise.

Key Points to Mention

  • Experimental unit: delivery vs. dasher vs. region; implications for randomization and analysis
  • Stratification by market, time of day, and dasher tenure to reduce variance
  • Power calculation: baseline 12%, MDE (e.g., 2 percentage points), alpha=0.05, power=0.80
  • Primary metric: lateness rate; guardrails: customer satisfaction, dasher efficiency, order completion rate
  • Ramp plan: start small, monitor guardrails, use sequential testing or Bayesian methods for early stopping
  • Decision rule: ship if statistically significant improvement and no guardrail violations; otherwise iterate or roll back

AI-generated suggestions, not part of the candidate's original notes. May be inaccurate — verify before relying on them.