🙌 Recommendation Systems
A one-stop shop for all things RecSys!.
📌 Table of Contents
Introduction
overview; retrieval; ranking
RecSys Toolkit
embedding space; alternating least squares; matrix factorization; mean normalization
Candidate Generation
notation; content-based filtering; code deep-dive; collaborative filtering; code deep-dive; retrieval
Ranking / Scoring
overview; scoring with the candidate generator?; objective function for scoring; positional bias
Re-ranking
overview; freshness; diversity; fairness
Building a Music Recommendation System using PySpark
code deep-dive; data preprocessing; data aggregation; data split; spin up your model!
Evaluation, Metrics, Testing, and Loss function for Recommender Systems
evaluating candidate generation; evaluating scoring; evaluating ranking; A/B testing
Content Moderation for Recommender Systems
videos, text, and image moderation; early and late moderation
Summary of relevant papers
popular recommendation systems in production demystified
Position Bias
reasons for position bias; measuring positional bias; mitigation strategies
Cold Start Problem
types of cold start; mitigation strategies
Multi-armed bandit
exploration; exploitation; contextual bandit
📖 References
- Google's course on Recommendation Systems
- Coursera: Music Recommender System Project
- Coursera: DeepLearning.AI's specialization
- Recommender system from learned embeddings
- Google's Recommendation Systems Developer Crash Course
- ALS introduction by Sophie Wats
- Matrix Factorization
- Recommendation System for E-commerce using Alternating Least Squares (ALS) on Apache Spark
- Personalized Re-ranking for Recommendation
- Dot Product Wiki
📝 Citation
If you found our work useful, please cite it as:
{
author = {Jain, Vinija},
title = {Notes for Recommender Systems},
howpublished = {\url{https://www.vinija.ai}},
year = {2022},
note = {Accessed: 2022-07-01},
url = {www.vinija.ai}
}
V. Jain, Notes for Recommendation Systems https://www.vinija.ai, 2022, Accessed: July 1 2022.