Large-Scale Online Ads Ranking and Auction System
Design a high-throughput ads ranking system for a social media platform with 500M DAU. The system must select the most relevant ads from a corpus of 10M candidates within a 100ms P99 latency budget. Focus on the end-to-end ML lifecycle: from real-time feature engineering (handling user signals) and multi-stage funnel architecture (retrieval and ranking), to specialized ad-tech challenges like position bias, click/conversion calibration for auctions, and handling delayed feedback loops in conversion data. Discuss the trade-offs between model complexity and serving constraints, and how to ensure the system maximizes long-term revenue (eCPM) while maintaining advertiser trust through accurate ROI predictions.
Wide & DeepDeepFMTwo-Tower ModelFAISSHNSWKafkaFlinkSparkRedisPlatt ScalingIsotonic RegressionMulti-Task Learning
00