Recommendation Systems

Candidate generation and ranking, collaborative and content-based filtering, cold start — and feedback loops, where the model changes the data it will be trained on next.

Recommendation Systems

A recommender is a loop, not a model: events feed candidate generation, candidates are ranked, the ranking decides what users see, and what users see decides the next batch of events.

Q · What is a recommendation system made of, and why is its offline evaluation less trustworthy than a classifier's?
Collaborative Filtering
▶ lab

Learn from who interacted with what, with no item attributes at all — and inherit every bias in who was shown what, because the missing entries in the matrix are not negatives.

Q · How does a model recommend items using only interaction history, and what does it silently assume about the interactions it never saw?
Content-Based Recommendation

Recommend from what items and users are, not from who touched what. It works on day one for a new item and is limited to what the attributes can express.

Q · When should a recommender use item and user attributes instead of interactions, and what does an attribute-based model structurally miss?
Candidate Generation vs Ranking
▶ lab

Millions of items cannot be scored by a rich model inside a page-load budget. Retrieval narrows to hundreds with a cheap model; ranking orders them with an expensive one; each stage has its own metric and its own way to fail.

Q · Why is a recommender split into retrieval and ranking, how is the latency budget divided, and why do the two stages need different offline metrics?
Cold Start

A new user or item has no interaction history, so an interaction-trained model has nothing but noise for it. The answers are popularity, content, asking, and deliberately showing it — none of which is a better model.

Q · What does a recommender do for a user or item it has never seen, and why is the embedding of an unseen item not an answer?
Feedback Loops
▶ lab

The model decides what users see, what users see decides what they click, and what they click is the next training set. Retraining on that log does not correct the loop — it tightens it.

Q · How does a recommender shape its own training data, why does naive retraining make the bias worse, and what breaks the loop?
Exploration vs Exploitation

Showing the best-known item earns the most today and learns the least. Some exploration is the price of data you can trust — and in some domains that price cannot be paid.

Q · How much should a recommender show things it is unsure about, how do bandit strategies decide, and where is exploration unacceptable?