{"id":13472312,"url":"https://github.com/mJackie/RecSys","last_synced_at":"2025-03-26T15:32:01.987Z","repository":{"id":41378256,"uuid":"174549829","full_name":"mJackie/RecSys","owner":"mJackie","description":"计算广告/推荐系统/机器学习(Machine Learning)/点击率(CTR)/转化率(CVR)预估/点击率预估","archived":false,"fork":false,"pushed_at":"2019-12-17T10:44:07.000Z","size":44172,"stargazers_count":1988,"open_issues_count":1,"forks_count":438,"subscribers_count":70,"default_branch":"master","last_synced_at":"2025-03-23T10:44:26.860Z","etag":null,"topics":["ctr","ctr-prediction","machine-learning","recommendation-system","recommender-system"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/mJackie.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2019-03-08T14:16:10.000Z","updated_at":"2025-03-21T12:41:02.000Z","dependencies_parsed_at":"2022-07-15T15:17:15.882Z","dependency_job_id":null,"html_url":"https://github.com/mJackie/RecSys","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mJackie%2FRecSys","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mJackie%2FRecSys/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mJackie%2FRecSys/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mJackie%2FRecSys/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mJackie","download_url":"https://codeload.github.com/mJackie/RecSys/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245681432,"owners_count":20655194,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ctr","ctr-prediction","machine-learning","recommendation-system","recommender-system"],"created_at":"2024-07-31T16:00:53.720Z","updated_at":"2025-03-26T15:32:01.980Z","avatar_url":"https://github.com/mJackie.png","language":null,"readme":"推荐系统/计算广告/机器学习/CTR预估资料汇总\n===\n[![License](https://img.shields.io/badge/license-MIT-blue.svg)](./LICENSE.md) ![Update](https://img.shields.io/badge/update-weekly-green.svg) ![Progress](https://img.shields.io/badge/progress-1003%20%2F%201003-ff69b4.svg) [![SayThanks](https://img.shields.io/badge/say-thanks-ff69f4.svg)](https://saythanks.io/to/kamyu104) ![Travis](https://travis-ci.org/kamyu104/LeetCode-Solutions.svg?branch=master)\n\n**说明**：本仓库主要汇集推荐系统/计算广告/机器学习/CTR预估相关学习资料，欢迎一起补充更新👼\n\n**更多前沿技术文章，欢迎移步 -\u003e [精选文章](https://github.com/mJackie/RecNews)**\n\n# RoadMap\n- [推荐系统](#推荐系统)\n- [计算广告](#计算广告)\n- [统计学习模型](#统计学习模型)\n\t- [技术文章](#技术文章)\n\t- [实践工具](#实践工具)\n- [深度学习模型](#深度学习模型)\n\t- [技术文章](#技术文章)\n\t- [实践代码](#实践代码)\n- [相关比赛](#相关比赛)\n\t- [Criteo Display Advertising Challenge](#CriteoDisplayAdvertisingChallenge)\n\t- [Avazu Click Through Rate Prediction](#AvazuClickThroughRatePrediction)\n\t- [2018 IJCAI 阿里妈妈搜索广告转化预测](#2018-IJCAI-阿里妈妈搜索广告转化预测)\n\t- [2018腾讯广告算法大赛](#2018腾讯广告算法大赛)\n- [技术博客](#技术博客)\n- [经典论文清单](#经典论文清单)\n\n---\n### 推荐系统\n- [推荐系统简明教程-概述](https://zhuanlan.zhihu.com/p/87411668)\n- [推荐系统简明教程-召回](https://zhuanlan.zhihu.com/p/87578318)\n- [推荐系统简明教程-排序](https://zhuanlan.zhihu.com/p/87796986)\n- [推荐系统实践-项亮](./resource/推荐系统实践-项亮.pdf)\n\n---\n\n### 计算广告\n- [互联网广告系统综述系列博文](https://blog.csdn.net/mytestmy/article/list)\n- [计算广告学系列视屏-刘鹏](https://study.163.com/course/introduction.htm?courseId=321007#/courseDetail?tab=1)\n- [计算广告学讲义-刘鹏](https://dirtysalt.github.io/html/computational-advertising.html)\n\n---\n\n### 统计学习模型\n#### 技术文章\n- [前深度学习时代CTR预估模型的演化之路](https://zhuanlan.zhihu.com/p/61154299)\n- [逻辑回归LR模型简介](https://tech.meituan.com/2015/05/08/intro-to-logistic-regression.html)\n- [FFM讲解PPT](./resource/ffm.pdf)\n- [深入FFM原理与实践](https://tech.meituan.com/2016/03/03/deep-understanding-of-ffm-principles-and-practices.html)\n- [GBDT算法原理与系统设计简介](./resource/GBDT-wepon.pdf)\n\n#### 实践工具\n- [LightGBM](https://github.com/Microsoft/LightGBM)\n- [XGBoost](https://github.com/dmlc/xgboost)\n- [LIBFFM](https://github.com/guestwalk/libffm)\n- [xLearn](https://github.com/aksnzhy/xlearn)\n- [DeepCTR](https://github.com/shenweichen/DeepCTR)\n\n---\n\n### 深度学习模型\n#### 技术文章\n- [深度学习如何应用在广告、推荐及搜索业务？](https://mp.weixin.qq.com/s/nboZ6p_l30L__FJNyz6Ohw)\n- [深度学习在CTR预估中的应用](https://zhuanlan.zhihu.com/p/35484389)\n- [深度学习在 CTR 中应用](http://www.mamicode.com/info-detail-1990002.html)\n- [深度学习在美团点评推荐业务中实践](https://gitbook.cn/books/5aa0dd15cfbe2c144b71906d/index.html)\n#### 实践代码\n- [CTR预估算法之FM, FFM, DeepFM及实践](https://github.com/Johnson0722/CTR_Prediction)\n- [推荐系统中使用ctr排序的dnn模型](https://github.com/nzc/dnn_ctr)\n\n---\n\n### 相关比赛\n#### [CriteoDisplayAdvertisingChallenge](https://www.kaggle.com/c/criteo-display-ad-challenge)\n- Rank1: [借鉴了Facebook的方案: GBDT 特征编码 + FFM](https://www.kaggle.com/c/criteo-display-ad-challenge/discussion/10555)\n- Rank3: [Quadratic Feature Generation + FTRL 传统特征工程和 FTRL 线性模型的结合](https://www.kaggle.com/c/criteo-display-ad-challenge/discussion/10534)\n\n#### [AvazuClickThroughRatePrediction](https://www.kaggle.com/c/avazu-ctr-prediction)\n- Rank1: [Feature Engineering + FFM + Ensemble, 只基于 FFM 进行集成](https://www.kaggle.com/c/avazu-ctr-prediction/discussion/12608)\n- Rank2: [Feature Engineering + GBDT 特征编码 + FFM + Blending](https://github.com/owenzhang/kaggle-avazu)\n\n#### [2018 IJCAI 阿里妈妈搜索广告转化预测](https://tianchi.aliyun.com/competition/entrance/231647/introduction?spm=5176.12281957.1004.10.38b04c2aaROEf9)\n- Rank1: [GBDT，用了嫁接技术处理样本分布不一致](https://github.com/plantsgo/ijcai-2018)\n- Rank2: [GBDT单模型+大量特征工程](https://github.com/YouChouNoBB/ijcai-18-top2-single-mole-solution)\n\n#### [2018腾讯广告算法大赛](https://algo.qq.com/)\n- Rank3: https://github.com/DiligentPanda/Tencent_Ads_Algo_2018\n- Rank6: https://github.com/nzc/tencent-contest\n\n---\n\n### 技术博客\n- [深度推荐系统](https://zhuanlan.zhihu.com/deep-recsys)\n- [美团技术点评](https://tech.meituan.com/)\n- [深度学习沿言笔记](https://zhuanlan.zhihu.com/c_188941548)\n- [王喆的机器学习笔记](https://zhuanlan.zhihu.com/wangzhenotes)\n- [推荐系统理论及实战](https://www.jianshu.com/nb/21403842)\n- [刘十三的机器学习笔记](https://zhuanlan.zhihu.com/c_1169669630389440512)\n\n---\n\n### 经典论文清单\n筛选文章的标准：**前沿或者经典的，工程导向的，google、阿里、facebook等一线互联网公司出品的**：\n\n[**Wide \u0026 Deep Learning for Recommender Systems**](./paper/wide\u0026deep.pdf)\n\n\u003e google 的 wide\u0026deep，必看论文，经典到难以附加\n\n[**DeepFM: An End-to-End Wide \u0026 Deep Learning\nFramework for CTR Prediction**](./paper/deepfm.pdf)\n\n\u003e 华为对wide\u0026deep的改进，加了wide层的交叉项。如今工业界的主流模型\n\n[**Practical lessons from predicting clicks on ads at facebook**](./paper/2014GBDT+LR-Facebook.pdf)\n\n\u003e facebook GBDT+LR的经典方案。虽然如今已不是主流方案，但论文中的思想很值得学习。\n\n[**Deep Neural Networks for YouTube Recommendations**](./paper/youtube-recsys.pdf)\n\n\u003e 介绍了Youtube推荐系统工业界架构与方案，经典必看\n\n\n[**Real-time Personalization using Embeddings for Search Ranking at Airbnb**](./paper/airbnb2018KDD.pdf)\n\n\u003e KDD2018 best paper，Embedding 必看论文，非常经典\n\n[**Entire Space Multi-Task Model: An Effective Approach for Estimating Post-Click Conversion Rate**](./paper/ESSM2018.pdf)\n\n\u003e 阿里的多目标学习经典方案，同时优化CTR \u0026 CVR\n\n\n[**Real-time Personalization using Embeddings for Search Ranking at Airbnb**](./paper/aribnbSearch.pdf)\n\u003e 介绍了 airbnb 搜索排序模型的演进，工业性质很强，值得参考\n\n\n[**搜索引擎点击模型综述**](./paper/搜索引擎点击模型综述.pdf)\n\u003e 清华马少平团队的文章点击模型入门必看，搜索引擎点击模型综述\n\n\n\n\n\n\n\n\n\n\n","funding_links":[],"categories":["Others","Recommendation, Advertisement \u0026 Ranking"],"sub_categories":["Others"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FmJackie%2FRecSys","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FmJackie%2FRecSys","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FmJackie%2FRecSys/lists"}