Swiggy Data Analyst Interview Questions (2026)

1. 1Problem Solving Screen45 minMedium

   One or two medium DSA problems in a shared editor, judged on working code and complexity analysis.

2. 2Problem Solving / DSA Round 255 minHard

   Harder algorithmic round covering trees, graphs, or DP, often with a follow-up that adds a real-world constraint.

3. 3Design Round (LLD/HLD)60 minHard

   LLD machine-coding of a module (e.g. a splitwise-style ledger or rate limiter) for SDE-1/2, or HLD of a delivery-scale system for SDE-3 and above.

4. 4Data / Analytics Round50 minMedium

   SQL on order and delivery datasets plus a metrics case such as diagnosing a drop in Instamart conversion or designing an experiment.

5. 5Hiring Manager Round50 minMedium

   Deep project walkthrough plus situational behavioral questions on ownership, customer focus, and handling conflicting priorities.

6. 6HR Round30 minEasy

   Offer discussion covering compensation structure, ESOPs, notice period, and team allocation.

1. Q1

   Design an A/B test for a new Food Delivery ranking or recommendation change. Define hypothesis, primary metric, guardrails, randomization unit, and launch decision rule

   MediumStatistics & Experimentation RoundA/B TestingSwiggy-specific

   Context: Context: Swiggy wants to balance demand, restaurant supply, delivery speed, and margin.

   How to answer: A strong answer would define a clear null and alternative hypothesis, such as the new ranking increasing conversion rate. The primary metric should directly reflect the hypothesis, like 'orders per user' or 'revenue per user', chosen for sensitivity and business impact. Guardrail metrics, like 'delivery time' or 'cancellations', are crucial to detect negative side effects. Randomization should typically be at the user ID level to ensure consistent experience, and the launch decision rule should combine statistical significance on the primary metric with acceptable performance on all guardrails over a predefined test duration.

2. Q2

   For Instamart, should randomization happen at customer, session, device, restaurant, or city level? Explain the tradeoffs

   MediumStatistics & Experimentation RoundA/B TestingSwiggy-specific

   Context: Consider cross-device behavior, interference, marketplace effects, and operational feasibility.

   How to answer: For Instamart, randomization should primarily happen at the customer level to ensure consistent user experience and capture individual behavior changes. Session or device level randomization can lead to a single customer being exposed to both control and treatment, contaminating results. Restaurant or city level randomization would introduce significant network effects and make it difficult to isolate the impact of the feature, as well as requiring a much larger sample size and longer experiment duration to achieve statistical significance due to higher variance.

3. Q3

   Choose primary and guardrail metrics for a Swiggy One experiment aimed at improving order conversion rate. What metrics would prevent a harmful launch?

   MediumStatistics & Experimentation RoundA/B TestingSwiggy-specific

   Context: Include user experience, partner health, revenue, reliability, and long-term retention considerations.

   How to answer: For a Swiggy One experiment targeting order conversion, the primary metric would be 'Order Conversion Rate' (orders / sessions or unique users reaching checkout). Guardrail metrics are crucial to prevent negative side effects. Key guardrails would include 'Average Order Value (AOV)', 'Customer Retention Rate' (especially for Swiggy One subscribers), 'Delivery Partner Utilization/Earnings', and 'Customer Support Contact Rate' related to experiment features. These guardrails ensure the conversion uplift isn't achieved at the expense of revenue, customer loyalty, operational efficiency, or user experience.

4. Q4

   During a Genie experiment, the treatment/control split is 52/48 instead of 50/50. How would you diagnose sample ratio mismatch?

   MediumStatistics & Experimentation RoundA/B TestingSwiggy-specific

   Context: Assume assignment logs, exposure logs, and eligibility filters may disagree.

   How to answer: To diagnose sample ratio mismatch (SRM), first verify the randomization unit (e.g., user ID, device ID) and ensure consistent hashing or assignment logic across both groups. Next, check for data pipeline issues, such as partial data ingestion, filtering errors, or delays affecting one group more than the other. Analyze historical SRM rates for similar experiments to identify if this is a recurring issue or an anomaly. Finally, examine pre-experiment metrics for both groups to detect any baseline imbalances that might indicate a problem with the randomization itself.

5. Q5

   The Restaurant Ads experiment is trending positive after two days. A PM wants to stop early and launch. How do you handle peeking and sequential testing?

   MediumStatistics & Experimentation RoundA/B TestingSwiggy-specific

   Context: Discuss pre-specified stopping rules, alpha spending, business urgency, and risk.

   How to answer: Explain that peeking early in an A/B test increases the Type I error rate (false positive) due to multiple comparisons. Discuss the need for a pre-determined sample size and test duration based on power analysis to ensure statistical validity. Propose methods like Bonferroni correction or O'Brien-Fleming boundaries for sequential testing if early stopping is truly necessary and planned. Emphasize communicating the risks of early stopping to the PM and advocating for completing the planned experiment duration.

6. Q6

   A new Delivery Partner App feature shows a large week-1 lift in order conversion rate, but the effect fades by week 4. What could explain this and how would you design the test duration?

   MediumStatistics & Experimentation RoundA/B TestingSwiggy-specific

   Context: Discuss novelty, learning effects, seasonality, and durable impact.

   How to answer: The fading effect could be due to novelty bias, where users initially engage more with a new feature, but their behavior normalizes over time. Another explanation is a learning curve, where initial friction or confusion leads to lower usage, which then improves as users learn the feature. External factors like seasonality or concurrent marketing campaigns could also confound results. To design test duration, consider the user's typical learning curve for similar features, the natural cycle of the business (e.g., weekly, monthly), and ensure sufficient time to observe stabilization and capture long-term impact, not just short-term novelty.

7. Q7

   In a marketplace-like Food Delivery feature, treatment users may affect control users. How would network effects or interference bias the experiment?

   MediumStatistics & Experimentation RoundA/B TestingSwiggy-specific

   Context: Examples include restaurant supply, content inventory, delivery capacity, or pricing pressure.

   How to answer: Network effects in a food delivery marketplace can lead to interference, where the treatment group's actions impact the control group, biasing A/B test results. This typically manifests as 'spillover effects,' where, for example, increased demand from treatment users might reduce driver availability or increase delivery times for control users, making the control group perform worse than it would in isolation. Conversely, if the treatment reduces demand, control users might see improved service. This interference violates the Stable Unit Treatment Value Assumption (SUTVA), making it difficult to accurately measure the true causal effect of the treatment.

8. Q8

   order conversion rate is a low-frequency event for Instamart. How would you set up an experiment with enough power without waiting too long?

   MediumStatistics & Experimentation RoundA/B TestingSwiggy-specific

   Context: Discuss proxy metrics, variance reduction, larger samples, longer windows, and risk of metric gaming.

   How to answer: To set up an A/B test for a low-frequency event like Instamart order conversion without excessive wait times, focus on selecting a suitable primary metric and potentially leveraging proxy metrics. The primary metric should ideally be a higher-frequency event that correlates strongly with order conversion, such as 'add-to-cart rate' or 'time spent browsing Instamart'. Additionally, consider increasing the sample size significantly by expanding the user base exposed to the experiment, and utilize sequential testing methodologies to allow for early stopping if a clear winner emerges, or if the experiment is unlikely to reach significance.

9. Q9

   Design a geo or city-level experiment for Swiggy One. When is this better than user-level randomization, and what are the analytical downsides?

   MediumStatistics & Experimentation RoundA/B TestingSwiggy-specific

   Context: Use matched markets, pre-period balancing, spillover checks, and fewer experimental units.

   How to answer: A strong candidate would outline an experiment design for Swiggy One using geo-level randomization, specifying control and treatment cities/geos, and key metrics like subscription rate, order frequency, and GMV. They would explain that geo-level randomization is superior when there's a risk of network effects (e.g., word-of-mouth, shared accounts) or when the intervention itself is inherently geo-specific (e.g., marketing campaigns, delivery logistics changes). The analytical downsides include lower statistical power due to fewer experimental units, increased risk of selection bias if geo-level units aren't well-matched, and potential for spillover effects between adjacent geos.

10. Q10

    The Genie experiment lifts order conversion rate overall, but only for new users and only in one meal_slot. How would you evaluate heterogeneous treatment effects?

    HardStatistics & Experimentation RoundA/B TestingSwiggy-specific

    Context: Balance pre-planned segments with exploratory slicing and multiple testing risk.

    How to answer: To evaluate heterogeneous treatment effects (HTE), I would first define the specific subgroups (new users, specific meal_slot) and re-run the A/B test analysis, segmenting the results by these dimensions. I would then use statistical methods like interaction terms in regression models (e.g., OLS or logistic regression, depending on the outcome variable) to formally test if the treatment effect significantly differs across these subgroups. Additionally, I would consider uplift modeling or Causal Forest algorithms for more complex HTE detection and personalization. Finally, I'd visualize these subgroup-specific effects to clearly communicate the findings and inform targeted rollout strategies.

11. Q11

    Treatment improves order conversion rate but worsens delivery SLA breach rate for Restaurant Ads. Walk through a launch recommendation

    HardStatistics & Experimentation RoundA/B TestingSwiggy-specific

    Context: Make a decision under conflicting metrics and quantify tradeoffs for stakeholders.

    How to answer: A strong recommendation would involve quantifying the trade-off between improved conversion and worsened SLA breach. This requires estimating the monetary value of increased orders versus the cost of SLA breaches (e.g., refunds, customer churn, operational overhead). If the net value is positive, a phased rollout with close monitoring and potential mitigation strategies for SLA breaches (e.g., dynamic ad throttling, improved delivery partner allocation) should be recommended. If negative, the treatment should be rejected, and further investigation into the root cause of SLA impact is needed.

12. Q12

    How would you design ramp-up, holdback, and post-launch monitoring for a successful Delivery Partner App A/B test?

    HardStatistics & Experimentation RoundA/B TestingSwiggy-specific

    Context: Include ramp stages, persistent holdback, alert thresholds, rollback criteria, and owner accountability.

    How to answer: For ramp-up, I'd start with a small percentage (e.g., 1-5%) of the target Delivery Partner population, monitoring key operational metrics like app crashes, login failures, and order acceptance rates for stability before gradually increasing exposure. Holdback involves reserving a small, unexposed control group (e.g., 1-2%) for an extended period post-launch to detect long-term novelty effects or sustained behavioral changes. Post-launch monitoring requires continuous tracking of primary metrics (e.g., delivery time, partner earnings, cancellations) and guardrail metrics (e.g., app stability, support contacts) via dashboards with clear alerts, coupled with periodic re-evaluation of the holdback group's performance against the fully launched experience.

13. Q13

    Midway through the Food Delivery test, tracking for Swiggy One changed. How would you decide whether the experiment results are still usable?

    HardStatistics & Experimentation RoundA/B TestingSwiggy-specific

    Context: Compare instrumentation versions, affected traffic share, raw logs, and sensitivity analyses.

    How to answer: A strong candidate would first identify the nature of the tracking change for Swiggy One (e.g., bug fix, new metric, altered definition). They would then analyze the impact of this change on both the control and treatment groups, specifically looking for differential effects or a significant shift in baseline metrics. The decision hinges on whether the change introduced bias or increased variance to an extent that invalidates the comparison, possibly requiring a re-run or advanced statistical adjustments if the impact is uniform and quantifiable. Finally, they would propose a clear go/no-go decision based on the severity and nature of the tracking alteration.

14. Q14

    Two overlapping experiments on Instamart both affect contribution margin per order. How would you detect and manage interaction effects?

    HardStatistics & Experimentation RoundA/B TestingSwiggy-specific

    Context: Discuss experiment registry, factorial design, exclusion rules, and interaction terms.

    How to answer: A strong candidate would first emphasize pre-experiment design to minimize overlap, but acknowledge it's not always possible. They would then propose statistical methods like ANCOVA or regression analysis with interaction terms to detect significant interaction effects between the two experiments. Managing these effects involves either sequential rollout, re-designing one or both experiments, or interpreting results with the interaction effect quantified. Finally, they would discuss the importance of clear documentation and communication regarding overlapping experiments and their potential interactions.

15. Q15

    Swiggy's Food Delivery revenue suddenly drops 10% week over week. Structure a business case to diagnose the issue and identify the most likely drivers

    MediumProduct Analytics & Business CaseBusiness CasesSwiggy-specific

    Context: Consider traffic, conversion, pricing, mix, supply/inventory, outages, marketing, and seasonality.

    How to answer: A strong answer would begin by structuring the problem into external and internal factors, then breaking down Swiggy's revenue formula (Orders x AOV x Commission Rate). The diagnostic approach should prioritize data analysis, starting with high-level metrics (total orders, active users, AOV) and segmenting by key dimensions like geography, customer cohorts, restaurant categories, and time of day. The candidate should then propose potential drivers for each factor (e.g., competitor promotions, app outages, menu pricing changes, delivery partner availability) and outline a data-driven investigation plan to validate or invalidate these hypotheses, concluding with potential mitigation strategies.

Practice these with instant AI feedback in a live mock interview → Start a Swiggy Data Analyst mock

Prepare coding/SQL and analytical cases; show product/data sense; quantify impact

Indicative Data Analyst pay in India: ~₹6–22 LPA (role-level range, not a Swiggy-specific figure).

Other roles at Swiggy

Data Analyst interviews at other companies