AI Roadmaps
← All roadmaps
IntermediateRoadmap 16 · 12 steps · 3h 14m of video

Recommender Systems

How Netflix, YouTube, and TikTok pick what you see: collaborative filtering, matrix factorization, two-tower retrieval, ranking, and evaluation.

Before this: Machine Learning. Deep Learning helps for the later steps.

  1. 8 min
    Step 1

    The math behind recommenders

    The core idea of predicting ratings from similar users and items.

    The Math Behind Recommender Systems

    Art of the Problem

  2. 9 min
    Step 2

    Content-based vs collaborative filtering

    Two basic strategies and when each one works.

    Content-based filtering & collaborative filtering (Building recommendation systems with TensorFlow)

    TensorFlow

  3. 12 min
    Step 3

    Collaborative filtering in practice

    User-based and item-based neighbors, with their weak spots.

    Collaborative Filtering : Data Science Concepts

    ritvikmath

  4. 33 min
    Step 4

    Matrix factorization

    Learn hidden taste factors from a sparse ratings table.

    How does Netflix recommend movies? Matrix Factorization

    Luis Serrano Academy

  5. 14 min
    Step 5

    Build a recommender in Python

    Turn the ideas into working code on a movie dataset.

    Building a Recommendation System in Python

    Spencer Pao

  6. 9 min
    Step 6

    Neural collaborative filtering

    Replace the dot product with a neural network in PyTorch.

    Neural Collaborative Filtering (NCF) Explanation & Implementation in Pytorch

    Steeve Huang (steeve)

    RUCAIBox/RecBole★ 4.6k
  7. 26 min
    Step 7

    Two-tower retrieval

    How big systems narrow millions of items to a few hundred.

    Building Scalable Retrieval System with Two-Tower Models | Query-Item Retrieval Recsys Model | ML AI

    DataTrek

    tensorflow/recommenders★ 2k
  8. 19 min
    Step 8

    Fast nearest-neighbor search

    Serve embeddings at scale with approximate search indexes.

    Vector Search & Approximate Nearest Neighbors (ANN) | FAISS (HNSW & IVF)

    Mustafa Zaki

    facebookresearch/faiss★ 41.8k
  9. 23 min
    Step 9

    YouTube's deep recommender paper

    Walk through the classic two-stage candidate and ranking design.

    [Paper Review]: Deep Neural Networks for YouTube Recommendations

    Aladdin Persson

  10. 9 min
    Step 10

    Design a recommendation engine

    See retrieval, ranking, and serving fit into one system.

    Design an ML Recommendation Engine | System Design

    Interview Pen

  11. 21 min
    Step 11

    Ranking metrics: MRR, MAP, NDCG

    Measure whether the right items land near the top.

    Every Ranking Metric : MRR, MAP, NDCG

    ritvikmath

  12. 12 min
    Step 12

    Explore versus exploit with bandits

    Handle new items and users while still learning from clicks.

    Multi-Armed Bandit : Data Science Concepts

    ritvikmath

Build it

Watching isn't learning. Pick one and put it on GitHub.

Browse all roadmaps →