A recommendation system is a type of machine learning system that filters through a large amount of information and recommends those that are most relevant to a particular user. It is a tool that helps users discover new products, services, content, or people based on their past behavior and preferences. Recommendation systems are widely used in many different industries, including e-commerce, streaming services, social media, and music.
This guide will walk you through the process of building a recommender system from scratch, using the TMDB 5000 Movie Dataset as experimental data.
The goal is to create a system that can rival the performance of Xiaohongshu's recommendation engine.
- RecommenderSystem (Chinese)
- AI-RecommenderSystem (Chinese)
- Twitter's Recommendation Algorithm
- List of Recommender Systems
- ItemCF: Item-Based Collaborative Filtering Recommendation Algorithms
- Swing: Large Scale Product Graph Construction for Recommendation in E-commerce
- UserCF: User-based Collaborative Filtering Algorithm Design and Implementation
- UserCF: UTEG
- Matrix Completion: Privileged Matrix Factorization for Collaborative Filtering
- Matrix Completion: Matrix completion by deep matrix factorization
- Approximate Nearest Neighbor Search: Faiss
- 2-Tower: Two Tower Model Architecture: Current State and Promising Extensions
- 2-Tower Pointwise:
- 2-Tower Pairwise: Embedding-based Retrieval in Facebook Search
- 2-Tower Listwise: Sampling-Bias-Corrected Neural Modeling for Large Corpus Item Recommendations
- Deep Retrieval: Deep Retrieval: Learning A Retrievable Structure for Large-Scale Recommendations
- TDM: Learning Tree-based Deep Model for Recommender Systems
- JTM: Joint Optimization of Tree-based Index and Deep Model for Recommender Systems
- OTM: Learning Optimal Tree Models under Beam Search