Quant interview questions

53 questions · page 1 of 2 · Clear filters

• You are asked to "predict demand" for a bike-share operator. What do you say first?Research case studies · Foundation · Free solution
• Ten observations: nine average 2 and one is 100.Research case studies · Foundation
• Your evaluation metric is mean absolute error and the target is heavily skewed.Research case studies · Foundation
• A model’s errors on five cases are 1,−1,2,−2,6.Research case studies · Foundation
• The best bid has 300 lots and the best offer 100.Research case studies · Foundation
• You buy 100 shares at $10.00, 300 at $10.20 and 100 at $10.50.Research case studies · Foundation
• You buy at $100.03 when the mid-quote is $100.00.Research case studies · Foundation
• Reading the top of the book, part 1 of 4Research case studies · Foundation
• Pricing houses in logs, part 1 of 3Research case studies · Foundation
• A backtest too good to be true, part 1 of 3Research case studies · Foundation
• An execution algorithm that looks worse, part 1 of 3Research case studies · Foundation
• Why does an interviewer ask for a baseline before you describe your model?Research case studies · Applied · Free solution
• A feature is missing for 20% of rows. What do you establish first?Research case studies · Applied
• You are asked to build a five-minute return predictor from order book data.Research case studies · Applied
• You have finished describing your approach and have two minutes left.Research case studies · Applied
• Your churn model feeds a retention offer with a fixed budget.Research case studies · Applied
• You forecast demand to decide inventory, where being short costs four times as…Research case studies · Applied
• You are asked how to validate a demand forecasting model built on three years…Research case studies · Applied
• A short-horizon signal earns 8 basis points a trade before costs of 3 basis…Research case studies · Applied
• You must present a forecast whose confidence interval is wide enough to include…Research case studies · Applied
• You are asked to predict house prices, which range from tens of thousands to…Research case studies · Applied
• A target takes values 1,2,3,4,100.Research case studies · Applied
• An opera house expects ticket demand q = 1000−10p at price p and has 800 seats.Research case studies · Applied
• A customer churns with probability 0.3 and is worth $200 if retained.Research case studies · Applied
• Your churn model’s most predictive feature is "number of support calls in the…Research case studies · Applied
• Control converts 5.0% of 10,000 users and treatment 5.6% of 10,000.Research case studies · Applied
• You need to classify trades as buyer- or seller-initiated from trades and quotes.Research case studies · Applied
• A series has median 10 and median absolute deviation 2.Research case studies · Applied
• Small companies are much likelier to leave a financial field blank when their…Research case studies · Applied
• Ten features are each missing in 5% of rows, independently.Research case studies · Applied
• Midway through your case answer the interviewer says one of your key…Research case studies · Applied
• Reading the top of the book, part 2 of 4Research case studies · Applied
• Pricing houses in logs, part 2 of 3Research case studies · Applied
• A backtest too good to be true, part 2 of 3Research case studies · Applied
• An execution algorithm that looks worse, part 2 of 3Research case studies · Applied
• A retention programme is offered to customers whose usage has just dropped…Research case studies · Advanced
• You build a factor from quarterly fundamentals downloaded from a vendor today.Research case studies · Advanced
• You run a difference-in-differences study.Research case studies · Advanced
• Your model assigns a 10% probability to 1,000 cases and 150 of them occur.Research case studies · Advanced
• You join trades to quotes using the exchange timestamp on both. What can still go wrong?Research case studies · Advanced