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
- Continue to ../README.md for the broader practical data science roadmap.
- Continue to ../../27-causal-inference/README.md for deeper effect-estimation concepts.
- Continue to ../../16-model-evaluation/README.md if you want stronger experimental reporting and comparison habits.
Last updated on