Recommender Systems
Matrix factorisation, two-tower retrieval, ranking objectives, feedback loops and cold start.
12concepts
152flashcards
92minutes of reading
- 01 Cold Start and Content-Based Hybrids Why a new user or item is invisible to collaborative filtering, how hybrid models build representations from metadata instead of interaction history, and the exploration cost that no content feature removes.
- 02 Matrix Factorisation and Implicit Feedback Learning low-rank user and item vectors from a sparse interaction matrix, and why the shift from ratings to clicks changes the loss, the negatives and the meaning of the output.
- 03 Semantic IDs for Recommendation Why recommenders hash item identifiers into meaningless buckets, how quantising a content embedding into a short tuple of discrete codes replaces that hash with an address that carries similarity, and what the second training stage costs you.
- 04 Collapsing the Retrieval and Ranking Cascade What a single end-to-end generative recommender buys in efficiency when it replaces the retrieve-prerank-rank pipeline, and what you give up by deleting the stage boundaries that business logic, calibration and debugging all live on.
- 05 Deep CTR Ranking Models: Wide & Deep, DCN and DLRM How ranking models for click-through prediction combine huge sparse embedding tables with explicit feature-interaction layers, what Wide & Deep, Deep & Cross and DLRM each assume about crosses, and why careful benchmarking shrank the differences between them.
- 06 Feedback Loops and Filter Bubbles A recommender trained on data it generated is optimising against its own past choices, which narrows what users see and makes offline evaluation systematically agree with the incumbent.
- 07 Generative Retrieval for Recommendation What changes when a model decodes an item identifier token by token instead of scoring a catalogue, why the index moves into the weights, and the cold-start collapse that the headline benchmark numbers hide.
- 08 Item Tokeniser Drift and Catalogue Updates Why moving the retrieval index into model weights turns every new item and every content-encoder upgrade into a continual-learning problem, and how much retrieval quality forgetting actually destroys.
- 09 Offline Evaluation and Sampled Metrics in Recommenders Why ranking against 100 sampled negatives can reverse which recommender looks best, how random splits leak the future into training, and what a decade of reproducibility studies says about reported progress.
- 10 Sequential Recommendation: SASRec and BERT4Rec Treating a user's history as an ordered sequence and predicting the next item with a transformer, and why the famous SASRec versus BERT4Rec comparison turned out to be about loss functions and training budgets rather than attention direction.
- 11 Sequential Transduction for Recommendation Why deep CTR models stopped improving when given more compute, how reformulating ranking as next-action prediction over one unified event stream restored a scaling curve, and where that curve flattens.
- 12 Two-Tower Retrieval and Candidate Generation Splitting the model so that item representations can be precomputed and searched with approximate nearest neighbours, which is what makes recommending from a hundred-million-item catalogue possible at all.