This chapter covers:
- Using machine learning to build generalizable search systems
- Ranking within the search engine using machine learning models
- How learning to rank is different from other machine learning methods
- Building a robust and generalizable ranking model
It’s a random Tuesday. You review your search logs. The searches range from the frustrated runner’s - polar m430 running watch charger - to the worried hypochondriac’s - weird bump on nose - cancer? - to the curious cinephile’s - william shatner first film. Despite the fact that many are one-off queries, you know each user expects nothing less than amazing search results.
You feel hopeless. You know many query strings, by themselves, are distressingly rare. You have very little click data to know what’s relevant for these searches. Every day gets more challenging: trends, use cases, products, user interfaces, and even languages evolve. How can anyone hope to build search that amazes when users seem to constantly surprise us with new ways of searching?