Model benchmarks for recommendation system
来源:互联网 发布:it serves you right 编辑:程序博客网 时间:2024/05/01 22:47
Model benchmarks
A lot of people have asked me what models we use for recommendations at Spotify so I wanted to share some insights. Here’s benchmarks for some models. Note that we don’t use all of them in production.
This particular benchmark looks at how well we are able to rank “related artists”. More info about models:
- vector_exp: Our own method, a latent factor method trained on all log data using Hadoop (50B+ events).
- word2vec: Google’s open sourced word2vec. We train a model on subsampled (5%) playlist data using skip-grams and 40 factors.
- rnn: Recurrent Neural Networks trained on session data (users playing tracks in a sequence). With 40 nodes in each layer, usingHierarchical Softmax for the output layer and dropout for regularization.
- koren: Collaborative Filtering for Implicit Feedback Datasets. Trained on same data as vector_exp. Running in Hadoop, 40 factors.
- lda: Latent Dirichlet Allocation using 400 topics, same dataset as above, also running in Hadoop.
- freebase: Training a latent factor model on artist entities in the Freebase dump.
- plsa: Probabilistic Latent Semantic Analysis, using 40 factors and same dataset/framework as above. More factors give significantly better results, but still nothing that can compete with the other models.
Again, not all of these models are in production, and conversely, we have other algorithms not included above that are in production. This is just a selections of things we’ve experimented with. In particular, I think it’s interesting to note that neither PLSA nor LDA perform very well. Taking sequence into account (rnn, word2vec) seems to add a lot of value, but our best model (vector_exp) is a purebag-of-words model.
- Model benchmarks for recommendation system
- open source project for recommendation system
- recommendation system
- recommendation system overview
- 130902 recommendation system
- 1129. Recommendation System 解析
- 1129. Recommendation System (25)
- 1129. Recommendation System (25)
- PAT--1129. Recommendation System
- PAT 1129Recommendation System
- 1129. Recommendation System (25)
- Recommendation System Algorithms
- Recommendation system framework
- 1129. Recommendation System (25)
- 1129. Recommendation System (25)
- 1129. Recommendation System (25)
- 1129. Recommendation System (25)
- [Benchmarks] File System Performance: F2FS vs EXT4
- 片上总线Wishbone 学习(十一)总线周期之块读操作
- hadoop中master中为什么没有namenode启动org.apache.hadoop.dfs.SafeModeException: Cannot delete /user/报错
- OpenSSL命令---prime
- J2EE中数据对象的一些概念,比如DTO,VO,BO,ORM,POJO等相关注解
- 精心挑选12款优秀的 JavaScript 日历和时间选择插件
- Model benchmarks for recommendation system
- NIO - FileChannel
- 小人快跑之WPF基础——图形与动画(二)
- 图像旋转与缩放实现
- 相关子查询和嵌套子查询 [SQL Server]
- 我的Java 我做主
- Java Map 集合类简介
- JBoss 系列五十:使用Apache httpd(mod_jk)和JBoss构架高可用集群环境
- cookie、localStorage、sessionStorage的有效期和作用域问题