Ranking
ranking
Practice Problems
Lexical and Dense Ranking
Rank help articles by shared words and by cosine similarity with a deterministic tie rule, then score each ranking with precision@k and recall@k.
System Design
Design Typeahead / Autocomplete
Design a typeahead/autocomplete service like Google Search's suggestion bar that returns the top 10 ranked completions for a query prefix in under 100ms p99, scaling to 5B searches per day with a multi-billion-entry suggestion index. The interview centerpiece is the data structure choice (trie vs sorted strings vs ngram index) and the offline pipeline that ranks suggestions by frequency, recency, personalization, and click-through rate. We cover the trie with precomputed top-K per node, edge n-gram indexes for typo tolerance, the MapReduce/Spark batch pipeline that rebuilds suggestions nightly, and the per-region edge cache that absorbs 99% of traffic.
Recommendation Systems Architecture
A recommendation system at scale is a multi-stage funnel: candidate generation narrows millions of items to a few thousand, light ranking trims to a few hundred, heavy ranking scores those, and a re-ranking stage applies business and policy constraints. Each stage has a different latency budget, a different model, and a different operational profile. This lesson covers the canonical architecture (retrieval + ranking + re-ranking), the core algorithmic families (collaborative filtering, content-based, two-tower neural retrieval, sequential models), the embedding store and vector ANN serving stack, the cold-start problem, ranking objectives and the metrics that measure them, and the rollout / monitoring discipline that keeps the system honest. The goal is to leave you able to design the recommendation system for any consumer product and defend every layer's choices.