Swiggy Business 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 candidate would first define a clear, testable hypothesis, such as 'The new ranking algorithm will increase user engagement and order conversion.' They would then identify a primary metric like 'Orders per user' or 'Conversion Rate (view to order)' and critical guardrail metrics such as 'Average Order Value' and 'Delivery Time' to monitor for negative impacts. The randomization unit should be the 'User ID' to ensure consistent experience, and the launch decision rule would involve statistically significant positive movement in the primary metric without significant negative movement in guardrails over a predefined period.

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: Randomization for Instamart A/B tests should primarily happen at the customer level to ensure independent observations and minimize contamination, especially for features impacting user behavior over time. Session or device level randomization can be considered for very short-term, isolated UI/UX changes, but risk user confusion if they experience different versions. Restaurant or city level randomization is suitable for supply-side experiments (e.g., pricing, delivery time algorithms) or market-specific interventions, but requires careful consideration of network effects and sufficient sample size across many units to achieve statistical significance. The choice depends on the experiment's goal, potential for contamination, and the need to capture long-term user impact versus immediate, localized effects.

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: The primary metric for a Swiggy One experiment aimed at improving order conversion rate should be 'Swiggy One Order Conversion Rate' (orders placed by Swiggy One users / Swiggy One user sessions). Key guardrail metrics to prevent a harmful launch include 'Average Order Value (AOV) for Swiggy One users' to ensure revenue isn't cannibalized, 'Number of Swiggy One Subscriptions' to monitor impact on membership growth, and 'Customer Support Tickets related to Swiggy One' to catch negative user experience issues. Additionally, 'Delivery Partner Earnings per Order' could be a guardrail to ensure the experiment doesn't inadvertently harm the supply side.

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 a 52/48 split instead of 50/50 in a Genie A/B test, I would first check the randomization logic and implementation for any biases, such as user ID hashing issues or sequential assignment. Next, I'd analyze the traffic distribution over time, looking for sudden shifts or specific user segments disproportionately assigned to one group. I would also investigate any pre-experiment filters, targeting rules, or concurrent experiments that might interfere with the sample assignment. Finally, I'd verify the data logging and aggregation process to ensure accurate counting of users in each group.

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 stopping an A/B test early due to positive trends (peeking) inflates the Type I error rate, leading to false positives. Discuss the need to pre-define sample size and test duration based on desired statistical power and significance level. Mention methods like Sequential Testing (e.g., using AGI or SPRT methods) or Bonferroni correction if multiple peeks are unavoidable, to maintain the integrity of the experiment. Emphasize communicating the risks of early stopping to the PM and advocating for letting the test run its course.

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 suggests a novelty effect or a change in user behavior that isn't sustained. Possible explanations include initial curiosity driving engagement, a learning curve that eventually normalizes behavior, or a temporary incentive that expired. To design the test duration, one should consider the typical user habit formation period for delivery partners, the lifecycle of similar features, and potential seasonality. A minimum duration of 4-6 weeks is often recommended to capture stabilization, with an eye towards longer periods (8-12 weeks) if habit formation or long-term behavioral shifts are critical to the feature's success.

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 bias A/B tests by causing treatment users to influence control users (spillover effect) or vice-versa. This interference leads to an underestimation or overestimation of the true treatment effect, as the control group is no longer a pure baseline. For example, if a treatment reduces delivery times for some users, it might indirectly free up delivery executives, benefiting control users and diluting the observed impact. Conversely, if a treatment increases demand, it could strain resources and negatively impact control users, making the treatment appear worse than it is.

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 Instamart's low-frequency order conversion rate, I would first identify a suitable proxy metric that is high-frequency and highly correlated with the ultimate conversion. This could be 'add-to-cart rate,' 'view-product-details rate,' or 'time spent on app.' Next, I would calculate the required sample size and experiment duration based on the proxy metric's baseline, expected lift, and desired statistical power and significance. Finally, I would ensure robust tracking for both the proxy and primary metrics, acknowledging the proxy's limitations while using it to make quicker interim decisions or to optimize the experiment's design before a full rollout.

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 geo-level experiment for Swiggy One would involve selecting specific cities or localities (e.g., Bangalore vs. Hyderabad) as control and treatment groups, where the treatment group receives the Swiggy One offering (e.g., discounted subscription, free delivery). This is preferable when there are network effects, spillover effects, or when the feature fundamentally changes market dynamics, making user-level randomization impractical or biased. Analytical downsides include lower statistical power due to fewer experimental units, increased susceptibility to confounding variables unique to each geo, and longer experiment durations to detect significant effects.

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: A strong candidate would first identify the need for subgroup analysis, specifically segmenting by 'user_type' (new vs. existing) and 'meal_slot'. They would then propose statistical methods to test for significant differences in treatment effects across these subgroups, such as interaction terms in a regression model or separate t-tests/chi-squared tests for each segment. The candidate should also discuss the practical implications of these heterogeneous effects, suggesting targeted rollout strategies or further investigation into the underlying causes for the observed differences. Finally, they would touch upon the importance of pre-registration of subgroups or adjusting for multiple comparisons if subgroup analysis was not pre-planned.

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 calculating the monetary impact of both metrics, considering customer lifetime value, churn risk, and potential refunds/penalties from SLA breaches. The recommendation should then propose a phased rollout or targeted launch, perhaps to specific restaurant types or customer segments, while continuously monitoring key metrics. Finally, it should suggest further investigation into the root cause of the SLA breach and potential mitigation strategies before a full-scale launch.

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 Delivery Partners (DPs) in a specific geo, closely monitoring key operational metrics like login rates, crash rates, and order acceptance rates for stability before gradually increasing exposure. Holdback would involve reserving a small, representative control group (e.g., 5-10% of the original population not exposed to the test) for an extended period post-launch to measure long-term impact and guard against novelty effects or seasonal changes. Post-launch monitoring requires a comprehensive dashboard tracking primary metrics (e.g., DP earnings, efficiency), secondary metrics (e.g., app stability, support tickets), and guardrail metrics (e.g., customer complaints related to delivery) with automated alerts for significant deviations, ensuring continuous performance and identifying any unforeseen negative impacts.

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: First, identify the exact nature and timing of the tracking change for Swiggy One relative to the Food Delivery test's start and end. Then, assess if the Swiggy One tracking change directly impacts the primary or secondary metrics of the Food Delivery test, or if Swiggy One users are a significant segment of the Food Delivery test population. Analyze pre- and post-change data for both control and experiment groups to detect any sudden shifts or discrepancies in key metrics, especially for Swiggy One users. Finally, determine if the observed impact is significant enough to invalidate the experiment's core assumptions or introduce bias, potentially requiring a restart or a segmented analysis.

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: To detect interaction effects between two overlapping Instamart experiments affecting contribution margin, first ensure proper randomization and segmentation (e.g., using a CUPED approach or orthogonalization if possible). Then, analyze the combined effect by segmenting users into control, Experiment A only, Experiment B only, and Experiment A+B groups, comparing the contribution margin per order across these segments. Statistical methods like ANOVA or regression analysis with interaction terms will be crucial to quantify the magnitude and significance of the interaction. If a significant interaction is found, the experiments should ideally be re-run sequentially or redesigned to be mutually exclusive, or the combined treatment group's results should be used for decision-making, acknowledging the non-additive effect.

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 business case would begin by segmenting the revenue drop (e.g., by city, user segment, restaurant type, order value, payment method) to localize the problem. Next, it would formulate hypotheses across key areas like demand (user acquisition/retention, competitor activity), supply (restaurant availability, delivery executive capacity), operations (delivery time, order accuracy), and product/pricing (app issues, promo effectiveness). The candidate should then outline data points needed to test these hypotheses, prioritizing based on potential impact and ease of access. Finally, they should propose a structured approach for root cause analysis and potential solutions.

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

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

Indicative Business Analyst pay in India: ~₹7–26 LPA (role-level range, not a Swiggy-specific figure).

Other roles at Swiggy

Business Analyst interviews at other companies