Data Analyst Interview Questions & Answers

Sample Answer

SELECT customer_id, SUM(order_value) AS total_spend FROM orders GROUP BY customer_id ORDER BY total_spend DESC LIMIT 5; Key concepts tested: GROUP BY for aggregation, SUM() aggregate function, ORDER BY with DESC for descending sort, LIMIT to restrict results. In an interview, also mention edge cases: should NULL order values be excluded? Should you use RANK() instead of LIMIT to handle ties?

Sample Answer

An INNER JOIN returns only rows where there is a match in both tables. A LEFT JOIN returns all rows from the left table, and matching rows from the right table — where there's no match, NULLs are returned for the right table's columns. Use INNER JOIN when you only want records with matches in both tables. Use LEFT JOIN when you want to keep all left-table records regardless of whether they have a match — e.g., listing all users and any orders they may have.

Sample Answer

Start by checking if it's a data issue — pipeline errors, tracking bugs, timezone anomalies. If the data is valid, segment the drop: by device, geography, traffic source, user type, signup method. Look for the segment where the drop is concentrated. Then check for correlated changes: did a marketing campaign end? Did we deploy a code change? Did a competitor launch something? Use this to form a hypothesis, then validate with additional data.

Sample Answer

Lead with the business implication, not the method. Instead of 'Our regression model with an R² of 0.78 shows...', say 'We found that customers who use feature X within their first week are 3x more likely to still be active at month 6.' Then show the visual simply. Address the 'so what': what should we do with this finding? Anticipate questions and prepare a one-slide backup with the underlying methodology for those who want it.