Airbnb 2022 release introduced Categories, a browse focused product that allows the user to seek inspiration by browsing collections of homes revolving around a common theme, such as Lakefront, Countryside, Golf, Desert, National Parks, Surfing, etc. In Part I of our Categories Blog Series we covered the high level approach to creating Categories and showcasing them in the product. In this Part II we will describe the ML Categorization work in more detail.
Throughout the post we use the Lakefront category as a running example to showcase the ML-powered category development process. Similar process was applied for other categories, with category specific nuances. For example, some categories rely more on points of interests, while others more on structured listing signals, image data, etc.
Category development starts with a product-driven category definition: “Lakefront category should include listings that are less than 100 meters from the lake”. While this may sound like an easy task at first, it is very delicate and complex as it involves leveraging multiple structured and unstructured listing attributes, points of interest (POIs), etc. It also involves training ML models that combine them, since none of the signals captures the entire space of possible candidates on their own.
To continue reading this article, click here.