Information retrieval is the practice of asking questions about large documents.
- It became especially popular when doing discovery for lawsuits
- or AWS in guiding you to the relevant products
- One of the first recommenders was GroupLens for newsnet
Collaborative Filtering: Involves running Ratings and Correlations through a CF engine.
- The goal is to find a neighborhood of users
- Recommendation Interfaces: Suggestion, top n
- Prediction interfaces: Evaluate candidates and score/predictive rating
Ratings: can be implicit or explicit Preditions: Estimate of preferences around how much you like something
**Approaches to Recommendations: **
Content-Based Approaches:
https://www.w3.org/Conferences/WWW4/Papers/93/
- Non-personalized/Stereotype (overall preference based on population)
- Product Association: People who bought x also want x - also not personalized
- Content-based: Based on metadata
- Collaborative filtering: Learning preferences and using the community
Preferences and Ratings:
Preference: We want to learn what users like (can be broad) Rate / Review - Explicit Click/purchase/follow - Implicit
Explicit