| Lecture 1 |
-- |
Topics: (no slides)
- Formal introduction
- Course details
- Syllabus
|
|
|
| Lecture 2 |
-- |
Topics: (slides)
- Intro recommendation tasks, retrieval vs ranking, feedback loops, goals (CTR/LTV).
|
|
|
| Lecture 3 |
-- |
Topics: (slides)
- Intro recommendation tasks, retrieval vs ranking, feedback loops, goals (CTR/LTV).
|
|
|
| Lecture 4 |
-- |
Topics: (slides)
- Data & logging implicit vs explicit feedback, sessions, exposure; dataset pitfalls
|
|
|
| Lecture 5 |
-- |
Topics: (slides)
- Data & logging implicit vs explicit feedback, sessions, exposure; dataset pitfalls
|
|
|
| Lecture 6 |
-- |
Topics: (slides)
- Baselines popularity/recency, co-occurrence, rule-based; strong baseline discipline
|
|
|
| Lecture 7 |
-- |
Topics: (slides)
- Baselines popularity/recency, co-occurrence, rule-based; strong baseline discipline
|
|
|
| Lecture 8 |
-- |
Topics: (slides)
- Evaluation Precision@K/Recall@K/NDCG/MAP; offline vs online; leakage
|
|
|
| Lecture 9 |
-- |
Topics: (slides)
- Evaluation Precision@K/Recall@K/NDCG/MAP; offline vs online; leakage
|
|
|
| Lecture 10 |
-- |
Topics: (slides)
- Content-based TF-IDF/item metadata; user profiles; cold start support
|
|
|
| Lecture 11 |
-- |
Topics: (slides)
- Content-based TF-IDF/item metadata; user profiles; cold start support
|
|
|
| Lecture 12 |
-- |
Topics: (slides)
- Memory-based CF user-user/item-item similarity; shrinkage; scalability
|
|
|
| Lecture 13 |
-- |
Topics: (slides)
- Memory-based CF user-user/item-item similarity; shrinkage; scalability
|
|
|
| Lecture 14 |
-- |
Topics: (slides)
- Matrix factorization latent factors, regularization; ALS/SGD; interpretability
|
|
|
| Lecture 15 |
-- |
Topics: (slides)
- Matrix factorization latent factors, regularization; ALS/SGD; interpretability
|
|
|
| Lecture 16 |
-- |
Topics: (slides)
- Implicit feedback learning BPR, weighted MF; negative sampling strategies
|
|
|
| Lecture 17 |
-- |
Topics: (slides)
- Implicit feedback learning BPR, weighted MF; negative sampling strategies
|
|
|
| Lecture 18 |
-- |
Topics: (slides)
- Hybrid recommenders mixing signals; feature engineering; stacking
|
|
|
| Lecture 19 |
-- |
Topics: (slides)
- Hybrid recommenders mixing signals; feature engineering; stacking
|
|
|
| Lecture 20 |
-- |
Topics: (slides)
- Learning-to-rank pointwise/pairwise/listwise; label design; metrics alignment
|
|
|
|
-- |
-- |
(Feb 25) Last Date for Proposal Submission. |
|
|
-- |
-- |
Mid Semester Exam Week |
Best of Luck.
|
| Lecture 21 |
-- |
Topics: (slides)
- Learning-to-rank pointwise/pairwise/listwise; label design; metrics alignment
|
|
|
| Lecture 22 |
-- |
Topics: (slides)
- Deep recommenders I embeddings, Neural CF; feature crosses; training pitfalls
|
|
|
| Lecture 23 |
-- |
Topics: (slides)
- Deep recommenders I embeddings, Neural CF; feature crosses; training pitfalls
|
|
|
| Lecture 24 |
-- |
Topics: (slides)
- Two-tower retrieval dual encoder, ANN search, candidate generation vs ranker
|
|
|
| Lecture 25 |
-- |
Topics: (slides)
- Two-tower retrieval dual encoder, ANN search, candidate generation vs ranker
|
|
|
| Lecture 26 |
-- |
Topics: (slides)
- Ranking models wide&deep/DeepFM intuition; context features; calibration
|
|
|
| Lecture 27 |
-- |
Topics: (slides)
- Ranking models wide&deep/DeepFM intuition; context features; calibration
|
|
|
| Lecture 28 |
-- |
Topics: (slides)
- Sequential recommenders session-based rec, Markov→RNN→Transformer ideas
|
|
|
| Lecture 29 |
-- |
Topics: (slides)
- Sequential recommenders session-based rec, Markov→RNN→Transformer ideas
|
|
|
| Lecture 30 |
-- |
Topics: (slides)
- Graph-based recommenders (intro) user-item graph, message passing; when it helps
|
|
|
| Lecture 31 |
-- |
Topics: (slides)
- Graph-based recommenders (intro) user-item graph, message passing; when it helps
|
|
|
| Lecture 32 |
-- |
Topics: (slides)
- Cold start metadata, content, onboarding, zero-shot; multi-armed bandit exploration
|
|
|
|
-- |
-- |
(Mar 30) - Last Date of Mid Presentation. |
|
| Lecture 33 |
-- |
Topics: (slides)
- Cold start metadata, content, onboarding, zero-shot; multi-armed bandit exploration
|
|
|
| Lecture 34 |
-- |
Topics: (slides)
- Bias & fairness popularity bias, exposure bias; debiasing evaluation
|
|
|
| Lecture 35 |
-- |
Topics: (slides)
- Bias & fairness popularity bias, exposure bias; debiasing evaluation
|
|
|
| Lecture 36 |
-- |
Topics: (slides)
- Exploration & bandits epsilon-greedy, UCB/TS; counterfactual evaluation basics
|
|
|
| Lecture 37 |
-- |
Topics: (slides)
- Exploration & bandits epsilon-greedy, UCB/TS; counterfactual evaluation basics
|
|
|
| Lecture 38 |
-- |
Topics: (slides)
- Serving & monitoring ANN indexes, latency budgets, drift, A/B tests guardrails
|
|
|
| Lecture 39 |
-- |
Topics: (slides)
- Serving & monitoring ANN indexes, latency budgets, drift, A/B tests guardrails
|
|
|
| Lecture 40 |
-- |
Topics: (slides)
- End-to-end pipeline + offline eval + deployment
|
|
|
| Lecture 41 |
-- |
Topics: (slides)
|
|
|
| Lecture 42 |
-- |
Topics: (slides)
|
|
|
|
-- |
-- |
(Apl 30) Last Date of Codes Submission. |
|
|
-- |
-- |
(Apl 30) Dead Line for Final Presentation Video Submission. |
|
|
-- |
-- |
(Apl 30) Dead Line for Report Submission. |
|
|
-- |
-- |
End Semester Exam Week |
Best of Luck.
|
|
Link Added on Last Date for Submission :
|
DA262
