成为一名推荐系统工程师永远都不晚
https://www.jianshu.com/p/6f1c2643d31b
CTR预估基本知识
https://blog.csdn.net/supinyu/article/details/52248934
推荐系统学习笔记之三 LFM (Latent Factor Model) 隐因子模型 + SVD (singular value decomposition) 奇异值分解
https://blog.csdn.net/asd136912/article/details/78290679
Boosting学习笔记(Adboost、GBDT、Xgboost)
https://www.cnblogs.com/willnote/p/6801496.html
从ctr预估问题看看f(x)设计—DNN篇
https://zhuanlan.zhihu.com/p/28202287
推荐系统中使用ctr排序的f(x)的设计-dnn篇
https://github.com/ajoeajoe/dnn_ctr
CTR预估算法之FM, FFM, DeepFM及实践(有代码)
https://blog.csdn.net/john_xyz/article/details/78933253
https://github.com/Johnson0722/CTR_Prediction
用Keras实现一个DeepFM
https://blog.csdn.net/songbinxu/article/details/80151814
ctr预估之DeepFM
https://zhuanlan.zhihu.com/p/32563337
https://github.com/charleshm/deep-ctr
深度学习在CTR预估中的应用 | CTR深度模型大盘点
https://blog.csdn.net/wallace_emily/article/details/79908508
深入FFM原理与实践
https://tech.meituan.com/deep-understanding-of-ffm-principles-and-practices.html
深度学习大行其道,个性化推荐如何与时俱进?(推荐系统演进图)
https://blog.csdn.net/np4rHI455vg29y2/article/details/79071609
推荐系统遇上深度学习(三)--DeepFM模型理论和实践
https://www.jianshu.com/p/6f1c2643d31b
网友评论