Large-Scale Social Link Prediction System (People You May Know)
Design a high-scale 'People You May Know' (PYMK) recommendation system for a social network with over 1 billion users. Your design should handle massive graph data, addressing the challenges of candidate retrieval (Stage 1) and precision ranking (Stage 2). Detail how you would implement a low-latency serving architecture (P99 < 150ms) and a robust data pipeline that handles real-time friendship updates. Focus on feature engineering for graph-based signals, handling class imbalance in training, and defining the success metrics for business growth and system reliability.
LightGBMXGBoostSpark GraphXApache FlinkKafkaRedisFeastLambdaMART
10