{"blocks": [{"key": "0bb5669b", "text": "Scenario", "type": "header-two", "depth": 0, "inlineStyleRanges": [], "entityRanges": [], "data": {}}, {"key": "4faf1889", "text": "You are tasked with building a fraud-detection model for an online payments product.", "type": "unstyled", "depth": 0, "inlineStyleRanges": [], "entityRanges": [], "data": {}}, {"key": "ecdc9e61", "text": "Question", "type": "header-two", "depth": 0, "inlineStyleRanges": [], "entityRanges": [], "data": {}}, {"key": "c517a674", "text": "Outline the end-to-end ML workflow: data collection, feature engineering, model selection, validation, deployment, and monitoring. How would you handle severe class imbalance and concept drift in this context?", "type": "unstyled", "depth": 0, "inlineStyleRanges": [], "entityRanges": [], "data": {}}, {"key": "6c86ccdf", "text": "Hints", "type": "header-two", "depth": 0, "inlineStyleRanges": [], "entityRanges": [], "data": {}}, {"key": "665f2a47", "text": "Discuss resampling, cost-sensitive learning, ROC-AUC, sliding windows, and automated retraining triggers.", "type": "unstyled", "depth": 0, "inlineStyleRanges": [], "entityRanges": [], "data": {}}], "entityMap": {}}