Fraud Detection / Fraud Account Detection

Problem Overview

Case study: design a machine learning model to detect fraud (specifically fraud account detection). You are given an open-ended scenario and must work through the full ML system design pipeline: (1) identify types of fraud that may occur, (2) formulate the ML problem (e.g., binary classification vs. multi-label classification), (3)…

• 5 candidate-reported follow-ups — the exact probes interviewers asked, with the trigger for each
• The rest of the problem statement — full requirements, constraints, and edge cases
• Approach and trade-offs — what passing candidates did, and the mistakes that sink people