https://pwaabdullah.github.io/categories/recsys-series/ Recent content in RecSys Series on Abdullah Al Mamun https://pwaabdullah.github.io/og-default.png https://pwaabdullah.github.io/og-default.png Hugo en newabdullah 2025 Wed, 12 Mar 2025 00:00:00 +0000 https://pwaabdullah.github.io/posts/the-evaluation-of-recsys-part-3/ Wed, 12 Mar 2025 00:00:00 +0000 https://pwaabdullah.github.io/posts/the-evaluation-of-recsys-part-3/ Part 3 of the RecSys series. Traces the deep-learning revolution in RecSys from 2016 to 2023 — Neural Collaborative Filtering, Wide & Deep, DeepFM, Deep Interest Network, DLRM, and AdaTT. Architectures, intuition, where each one wins. https://pwaabdullah.github.io/posts/the-evaluation-of-recsys-part-2/ Tue, 11 Mar 2025 00:00:00 +0000 https://pwaabdullah.github.io/posts/the-evaluation-of-recsys-part-2/ Part 2 of the RecSys series. Factorization Machines generalize matrix factorization to arbitrary feature spaces, and XGBoost brings non-linear ranking via gradient-boosted trees. We cover the math, loss functions, strengths, and the limitations that drove the field toward deep learning. https://pwaabdullah.github.io/posts/the-evaluation-of-recsys-part-1/ Sat, 01 Mar 2025 00:00:00 +0000 https://pwaabdullah.github.io/posts/the-evaluation-of-recsys-part-1/ Part 1 of a deep-dive series on the evolution of recommendation systems. Covers content-based filtering, collaborative filtering (user/item), and matrix factorization — with loss functions, intuition, and where each technique breaks down.