{"blocks": [{"key": "9bba4899", "text": "Scenario", "type": "header-two", "depth": 0, "inlineStyleRanges": [], "entityRanges": [], "data": {}}, {"key": "ad80c97e", "text": "First-iteration machine-learning model for restaurant recommendations on Facebook.", "type": "unstyled", "depth": 0, "inlineStyleRanges": [], "entityRanges": [], "data": {}}, {"key": "b533292b", "text": "Question", "type": "header-two", "depth": 0, "inlineStyleRanges": [], "entityRanges": [], "data": {}}, {"key": "f710d9e7", "text": "Describe how you would design an initial recommendation model for restaurants. How would you validate whether the model is working? If one performance metric rises while another drops, how do you interpret and act?", "type": "unstyled", "depth": 0, "inlineStyleRanges": [], "entityRanges": [], "data": {}}, {"key": "50aec218", "text": "Hints", "type": "header-two", "depth": 0, "inlineStyleRanges": [], "entityRanges": [], "data": {}}, {"key": "70b45cb3", "text": "Cold-start, features, offline vs online validation, multi-objective optimisation.", "type": "unstyled", "depth": 0, "inlineStyleRanges": [], "entityRanges": [], "data": {}}], "entityMap": {}}