Capital One Data Scientist interview questions

1. Hackerrank screen (4 basic questions timed) 2. Technical phone interview that went over credit card fraud case. Asked about what kind of model, features to engineer, false positive/false negative, regularization, and potential issues 3. Data challenge- NYC taxi data. Basic summary info, describe a distribution, derive a variable, build a model to predict tips, and a problem of your choice (viz, anomaly detection, optimization, and a couple other options) 4. Onsite- stats interview- they give you an analysis with a regression/CART model and 15 minutes to analyze, explain, and provide recommendations. They asked about correlations, multicollinearity, p-values, ANOVA table, and improvements. Behavioral- STAR questions 2 consulting case studies- one was the P&L on a credit card product. break even, profit, and how to improve profit. Job fit- met with a manager and they talked about the department, challenges, etc. This guy talked for an hour and may have asked one question about me Technical- asked some machine learning questions about random forest, regularization, map reduce, and derive some equations by hand. This was the only interesting part. I would not have wasted my time going through all this stuff had I known more about the actual position. They provided no information about the actual position and did not answer any questions about the actual work until the onsite. The projects they described didn't seem very interesting - some fraud detection, a search problem that matches logos to a billing statement, and gathering data on small businesses.