Feature Engineering

Build ranking features by examining the searcher, query, document, and context, then the relationships between them. The examples combine intent, engagement history, text matching, location, and embedding similarity.

Start by identifying which entity or interaction each feature describes. This makes the feature set easier to explain and helps distinguish a document’s general properties from its relevance to one query or searcher.

Note: The terms “features” and “signals” are generally used interchangeably as we will also do so.

The four such actors for search are:

1. Searcher

2. Query

3. Document

4. Context

In the above figure, the context for a search query is browser history. However, it is a lot more than just search history. It can also include the searcher’s age, gender, location, and previous queries and the time of day.

---