Practice — Case Study: Search Ranking (Airbnb / E-commerce Marketplace Search) (5 questions)

You are asked to design search ranking for a home-rental marketplace. A product manager proposes: "Rank listings by predicted click-through rate — clicks are plentiful, so the model will train fast." A finance stakeholder counters: "Rank by expected revenue, price times booking probability."

1. Explain what goes wrong with each proposal in a two-sided booking marketplace, and state the objective you would actually optimise.
2. Write the utility of showing a listing so that host behaviour is included, and say how you would obtain each term.
3. Where in the system would you place revenue, diversity and cold-start considerations, and why not in the model's loss function?