Zomato Data Analyst Interview Questions (2026)

1. 1Coding Screen45 minMedium

   Medium DSA problems focused on arrays, strings, and hashmaps with working code expected quickly.

2. 2Technical Round 250 minMedium

   A harder DSA problem plus practical engineering discussion drawn from your projects and real Zomato features.

3. 3Design / Product-Thinking Round55 minHard

   Design a Zomato or Blinkit feature end to end (e.g. live order tracking or dark-store picker flow), balancing tech design with product judgment.

4. 4Hiring Manager / Culture Round45 minMedium

   Blunt conversation on hunger, ownership, why Zomato, and how you handle chaos and hard feedback.

5. 5HR Round25 minEasy

   Compensation, ESOPs, notice period, and setting expectations on pace and in-office work.

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 TestingZomato-specific

   Context: Context: Zomato wants to improve discovery and restaurant monetization without hurting customer experience.

   How to answer: To design an A/B test for a new food delivery ranking, the hypothesis would be that the new algorithm increases conversion (orders placed) or average order value (AOV). The primary metric would be 'Orders per User' or 'Revenue per User,' while guardrail metrics include 'App Crashes,' 'Latency,' and 'Uninstalls.' Randomization should occur at the 'User ID' level to ensure consistent experience. The launch decision rule would involve statistically significant improvement in the primary metric without significant negative impact on guardrails over a predefined test duration.

2. Q2

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

   MediumStatistics & Experimentation RoundA/B TestingZomato-specific

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

   How to answer: Randomization for Zomato Dining A/B tests should ideally happen at the customer level to ensure independent observations and minimize contamination, especially for features impacting individual user behavior like recommendations or discounts. However, session or device level might be considered if the feature is highly transient or device-specific, accepting some customer-level contamination. Restaurant or city level randomization introduces significant practical challenges due to network effects, spillover, and the difficulty of achieving statistical power with fewer, larger units, making it suitable only for very specific, large-scale infrastructure or policy changes where customer-level randomization is infeasible. The key trade-off is between minimizing contamination and achieving statistical power versus practical implementation complexity and potential for indirect effects.

3. Q3

   Choose primary and guardrail metrics for a Zomato Gold experiment aimed at improving menu-to-order conversion. What metrics would prevent a harmful launch?

   MediumStatistics & Experimentation RoundA/B TestingZomato-specific

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

   How to answer: The primary metric should directly measure menu-to-order conversion, such as 'Orders per Menu View' or 'Conversion Rate from Menu Page to Order Confirmation'. Guardrail metrics are crucial to prevent negative side effects. Key guardrails would include 'Average Order Value (AOV)', 'Number of Orders', 'User Retention Rate (e.g., 7-day or 30-day)', and 'Customer Support Ticket Volume related to Zomato Gold'. These guardrails ensure the experiment doesn't cannibalize revenue, reduce overall orders, decrease user loyalty, or increase operational costs.

4. Q4

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

   MediumStatistics & Experimentation RoundA/B TestingZomato-specific

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

   How to answer: First, verify the data pipeline and logging for any obvious errors in how users are assigned or recorded. Then, perform a chi-squared test (or z-test for large samples) on the observed treatment/control counts against the expected 50/50 split to statistically confirm the SRM. Next, segment the data by various dimensions like device type, user location, app version, or time of day to identify if the mismatch is localized to a specific subgroup. Finally, investigate potential causes such as buggy assignment logic, caching issues, or external factors influencing user behavior.

5. Q5

   The Hyperpure 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 TestingZomato-specific

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

   How to answer: A strong candidate would first explain that peeking early can lead to false positives due to increased Type I error rates, especially after only two days. They would then discuss the importance of pre-determining sample size and experiment duration based on statistical power and minimum detectable effect. To address the PM's urgency, they might suggest using sequential testing methods like Always Valid p-values (AVP) or Sequential Probability Ratio Test (SPRT) if the experiment was designed for it, but emphasize that retroactively applying these without prior design is problematic. Finally, they would recommend continuing the experiment for the planned duration or re-evaluating the statistical design if there's a strong business need to stop early, while acknowledging the risks.

6. Q6

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

   MediumStatistics & Experimentation RoundA/B TestingZomato-specific

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

   How to answer: The fading effect suggests novelty bias or a 'Hawthorne effect' where users initially engage more due to the newness, but revert to baseline behavior once the novelty wears off. Alternatively, it could be a 'selection bias' if early adopters, who are more engaged, were disproportionately in the treatment group initially. Another explanation could be 'seasonal effects' or 'external factors' that coincided with the initial launch. To design the test duration, I would recommend a minimum of 4-6 weeks to capture a full user cycle and account for novelty effects, potentially extending to 8-12 weeks for more robust long-term impact assessment, ensuring the test period covers typical user behavior patterns and potential seasonality.

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 TestingZomato-specific

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

   How to answer: Network effects or interference bias an A/B test by violating the Stable Unit Treatment Value Assumption (SUTVA), meaning a user's outcome is not independent of other users' treatment assignments. In a food delivery marketplace, treatment users (e.g., with a new feature for faster delivery) might indirectly affect control users by consuming more shared resources like delivery drivers or restaurant capacity. This can lead to an underestimation or overestimation of the true treatment effect, as the control group's performance is not a true baseline of 'no treatment' but rather 'treatment in the presence of other treated users'. The observed difference might not reflect the actual impact if the feature were rolled out to 100% of users.

8. Q8

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

   MediumStatistics & Experimentation RoundA/B TestingZomato-specific

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

   How to answer: To address low-frequency events like menu-to-order conversion for Dining, focus on identifying suitable proxy metrics that occur more frequently earlier in the funnel. This could involve metrics like 'views of menu item details', 'adding items to cart (even if not ordered)', or 'time spent browsing menu'. Ensure these proxy metrics are highly correlated with the ultimate conversion goal. Additionally, consider increasing the sample size or duration if feasible, but prioritize finding a sensitive, earlier-stage metric to detect impact faster.

9. Q9

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

   MediumStatistics & Experimentation RoundA/B TestingZomato-specific

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

   How to answer: A strong answer would propose a geo-level experiment design, such as randomizing entire cities or specific geographic zones within larger cities (e.g., neighborhoods) into Zomato Gold treatment and control groups. It would explain that geo-level randomization is superior when there's a risk of network effects, contamination between users, or when the feature inherently requires a market-wide rollout (e.g., changes to restaurant commissions or delivery logistics). The candidate should then detail the analytical downsides, including increased variance due to smaller sample size (fewer 'units' of cities/geos), potential for imbalance in key city characteristics, and longer experiment durations to achieve statistical significance.

10. Q10

    The Restaurant Ads experiment lifts menu-to-order conversion overall, but only for new users and only in one cuisine. How would you evaluate heterogeneous treatment effects?

    HardStatistics & Experimentation RoundA/B TestingZomato-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 relevant subgroups (e.g., new vs. existing users, specific cuisines, geographic regions). Then, I would perform subgroup analysis, running the A/B test analysis separately for each subgroup, focusing on the menu-to-order conversion metric. Statistical significance testing (e.g., t-tests, chi-squared tests) within each subgroup would identify where the treatment effect is significant. Finally, I would consider interaction terms in a regression model to formally test for HTE and understand the magnitude and direction of effects across different user segments and conditions.

11. Q11

    Treatment improves menu-to-order conversion but worsens order cancellation rate for Hyperpure. Walk through a launch recommendation

    HardStatistics & Experimentation RoundA/B TestingZomato-specific

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

    How to answer: A strong candidate would first clarify the business goals and relative importance of menu-to-order conversion versus order cancellation rate, especially for Hyperpure. They would then propose a deeper dive into the segments most affected by the trade-off, looking for root causes for the increased cancellations. Finally, they would recommend a phased rollout or a modified treatment, potentially with a holdback group, while continuously monitoring key metrics and considering the overall long-term impact on Hyperpure's operational efficiency and customer lifetime value.

12. Q12

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

    HardStatistics & Experimentation RoundA/B TestingZomato-specific

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

    How to answer: A strong candidate would outline ramp-up by gradually increasing traffic to the experiment, starting with a small percentage (e.g., 1-5%) and monitoring key metrics for stability and technical issues before scaling up. For holdback, they would propose reserving a small, untouched control group (e.g., 1-2%) from the overall experiment population to serve as a long-term baseline for novelty effects and sustained impact. Post-launch monitoring involves continuous tracking of primary and secondary metrics, setting up alerts for significant deviations, and conducting deep dives into user behavior and segment performance to ensure the feature's health and identify any unforeseen negative impacts.

13. Q13

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

    HardStatistics & Experimentation RoundA/B TestingZomato-specific

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

    How to answer: First, identify the exact date and nature of the tracking change for Zomato Gold. Then, analyze the pre-change data for both control and experiment groups to establish a baseline and confirm initial validity. Compare key metrics related to Zomato Gold (e.g., Gold order frequency, Gold user conversion) before and after the change for both groups. If the change introduced a significant, differential impact between groups or a substantial shift in Gold-related metrics across both groups, the results are likely compromised. Consider segmenting the experiment into 'pre-change' and 'post-change' periods and analyzing them separately, or potentially restarting the experiment if the impact is too severe.

14. Q14

    Two overlapping experiments on Dining both affect commission revenue per order. How would you detect and manage interaction effects?

    HardStatistics & Experimentation RoundA/B TestingZomato-specific

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

    How to answer: A strong candidate would first emphasize the importance of pre-experiment planning, including defining clear metrics and potential interaction hypotheses. They would then discuss statistical methods like ANCOVA or regression analysis with interaction terms to detect significant interactions between the two experiment variables on commission revenue. For management, they would suggest either sequential experimentation, mutually exclusive user segmentation for future tests, or a multivariate testing approach if interactions are expected and can be modeled. Finally, they would highlight the need for careful interpretation of results, considering both statistical significance and practical business impact.

15. Q15

    Zomato'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 CasesZomato-specific

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

    How to answer: A strong answer would begin by clarifying the scope (e.g., specific regions, user segments, product types) and timeframes to narrow down the problem. Then, it would propose a structured diagnostic approach, starting with internal factors (e.g., app issues, delivery logistics, pricing changes, promotions) and then moving to external factors (e.g., competitor activity, seasonality, economic shifts, regulatory changes). The candidate should prioritize data sources and metrics for each area, such as order volume, average order value, conversion rates, driver availability, and customer feedback. Finally, they should suggest a framework for hypothesis testing and root cause analysis, leading to actionable recommendations.

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

Practise DSA and system design for scale; prepare product-thinking; expect a strong culture-fit round

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

Other roles at Zomato

Data Analyst interviews at other companies