Recommendations
Personalizing Airbnb search by learning from the guest journey
Our short summary of Airbnb’s engineering write-up. The full story, with all the detail, is on their blog.
Read the full write-up on medium.com (opens in a new tab)Problem
Hand‑crafted search features couldn't keep up with growing data and limited personalization.
Solution
Created a Transformer‑based sequence model that encodes guests' view and booking events, using caps and sampling to handle huge event logs and improve ranking.
Research behind this, on AI Papers DailyThink Globally, Generate Personally: Multi-View Thinking with Adaptive Generation for Generative Recommendation
Want the architecture, code and numbers? They’re in the original post.
Read the full write-up on medium.com (opens in a new tab)