Deep Neural Networks for YouTube Recommendations
- 【排序】大规模稀疏线性排序模型FTRL工程实现 Ad click prediction: a view from the trenches
- 【排序】GBDT LR融合模型 Practical Lessons from Predicting Clicks on Ads at Facebook
- 【排序】因子分解机，召回和排序的利器，速度快效果好Factorization Machines
- 【排序】深度学习模型Wide&Deep Wide & Deep Learning for Recommender Systems
- 【排序】深度兴趣网络，捕获用户历史行为与候选物料相关性Deep Interest Network for Click-Through Rate Prediction
- 【召回】基于内容的协同过滤及其变种可以说是召回中应用最广泛算法之一，这篇是最经典的ItemCF[Online Shopping for Electronics, Apparel, Computers, Books, DVDs & more recommendations: item-to-item collaborative filtering](Amazon.com recommendations: item-to-item collaborative filtering)
- 【召回】无监督embedding学习，用于向量召回Item2vec: Neural Item Embedding for Collaborative Filtering
- 【召回】双塔DNN Sampling-Bias-Corrected Neural Modeling for Large Corpus Item Recommendations
- 【召回】Youtube DNNDeep neural networks for YouTube recommendations
- 【召回】考虑用户多峰兴趣的深度召回模型Multi-Interest Network with Dynamic Routing for Recommendation at Tmall
- 【重排&机制策略】多样性重排MMR,这篇要告诉大家推荐系统中还需要很多机制策略The Use of MMR, Diversity-Based Reranking for Reordering Documents and Producing Summaries