Machine Learning Advanced Pro

Case Study: Search Ranking (Airbnb / E-commerce Marketplace Search)

Deliver a complete ML system design answer for two-sided marketplace search in 45 minutes

30 min read 7 views

Model interview answer for marketplace search ranking: two-sided objectives, retrieval vs learned ranking, position-bias-corrected labels, LambdaMART vs neural rankers, NDCG worked example, cold start, diversity re-ranking, serving architecture and monitoring.

Preview Subscribe to unlock

Practice questions (5)

Choosing the Ranking Objective for a Two-Sided Marketplace

Advanced · Free

View →
Correcting Position Bias in Click Logs

Advanced

View →
Computing and Interpreting NDCG@5 for Two Rankers

Intermediate

View →
Fitting Retrieval and Ranking Into a 200 ms Budget

Advanced

View →
New-Listing Exposure and Diversity Without Killing Conversion

Advanced

View →

Quizzes (1)

Case Study: Search Ranking Quiz

0 attempts · 10 min · Pass 70% · Advanced

Take quiz →