{"blocks": [{"key": "501687bc", "text": "Scenario", "type": "header-two", "depth": 0, "inlineStyleRanges": [], "entityRanges": [], "data": {}}, {"key": "7b084745", "text": "A/B test for a new ad-ranking algorithm shows a 5% overall CTR lift but 100% lift for Indian males aged 18-24.", "type": "unstyled", "depth": 0, "inlineStyleRanges": [], "entityRanges": [], "data": {}}, {"key": "0dc9941e", "text": "Question", "type": "header-two", "depth": 0, "inlineStyleRanges": [], "entityRanges": [], "data": {}}, {"key": "9633a86a", "text": "The experiment yields a 5% overall CTR increase but 100% for Indian males 18-24. What analyses would you run to decide whether to launch the algorithm? List possible root-causes for this heterogeneous effect and how you would validate them. What additional data or follow-up experiments are needed before rollout?", "type": "unstyled", "depth": 0, "inlineStyleRanges": [], "entityRanges": [], "data": {}}, {"key": "cd930621", "text": "Hints", "type": "header-two", "depth": 0, "inlineStyleRanges": [], "entityRanges": [], "data": {}}, {"key": "38fe07f9", "text": "Think heterogeneous treatment effects, sampling bias, guardrails, segmentation, and long-term business impact.", "type": "unstyled", "depth": 0, "inlineStyleRanges": [], "entityRanges": [], "data": {}}], "entityMap": {}}