Skip to Content
28 Practical Data ScienceRecommender Causal

Recommender Systems & Causal Inference

Collaborative filtering, content-based methods, neural CF, causal inference, DiD, and A/B testing.

Use this subtrack when you want product-facing experimentation and decision systems rather than generic supervised-learning practice. It fits especially well for marketplace, personalization, and growth-oriented problems.

How To Use This Subtrack Well

  • Separate recommendation quality questions from causal-impact questions instead of treating them as the same problem.
  • Build one recommender baseline and one experiment-analysis workflow before adding complexity.
  • Pair this work with ../../27-causal-inference/README.md if the experimentation side needs deeper conceptual support.

What Comes Next

Last updated on