{"id":19389878,"url":"https://github.com/dsxiangli/ctr","last_synced_at":"2025-04-06T04:12:30.830Z","repository":{"id":41377742,"uuid":"245584878","full_name":"DSXiangLi/CTR","owner":"DSXiangLi","description":"CTR模型代码和学习笔记总结","archived":false,"fork":false,"pushed_at":"2021-08-28T02:04:22.000Z","size":31303,"stargazers_count":384,"open_issues_count":2,"forks_count":96,"subscribers_count":8,"default_branch":"master","last_synced_at":"2025-03-30T03:06:09.490Z","etag":null,"topics":["afm","ctr-prediction","dcn","deep-cross","deepfm","deepinterestnetwork","ffm","fibinet","fm","fnn","frappe","nfm","pnn","recommendation-algorithms","tensorflow","wide-and-deep","xdeepfm"],"latest_commit_sha":null,"homepage":"","language":"Python","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/DSXiangLi.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":"2020-03-07T07:03:45.000Z","updated_at":"2025-03-27T01:20:30.000Z","dependencies_parsed_at":"2022-09-05T13:10:35.303Z","dependency_job_id":null,"html_url":"https://github.com/DSXiangLi/CTR","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/DSXiangLi%2FCTR","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DSXiangLi%2FCTR/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DSXiangLi%2FCTR/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DSXiangLi%2FCTR/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/DSXiangLi","download_url":"https://codeload.github.com/DSXiangLi/CTR/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247430873,"owners_count":20937874,"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":["afm","ctr-prediction","dcn","deep-cross","deepfm","deepinterestnetwork","ffm","fibinet","fm","fnn","frappe","nfm","pnn","recommendation-algorithms","tensorflow","wide-and-deep","xdeepfm"],"created_at":"2024-11-10T10:17:46.085Z","updated_at":"2025-04-06T04:12:30.752Z","avatar_url":"https://github.com/DSXiangLi.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# CTR学习笔记\n\nThe code is not rigorously tested, if you find a bug, welcome PR ^_^ ~\n\n- Run: python main.py --model DeepFM --step train --dataset census --clear_model 1\n- Requirement: tensorflow 1.15\n\n1. 已完成模型列表[支持数据集]\n\n- FM [census]\n- FFM [census]\n- Embedding+MLP [census]\n- wide \u0026 Deep [census]\n- FNN [census]\n- PNN [census]\n- DeepFM [census \u0026 frappe]\n- AFM [census \u0026 frappe]\n- NFM [census \u0026 frappe]\n- Deep Crossing [census]\n- Deep \u0026 Cross [census \u0026 frappe]\n- xDeepFM [census \u0026 frappe]\n- FiBiNET [census \u0026 frappe]\n- DIN [amazon]\n\n2. 数据集\n当前支持census, frappe数据集，详情见data目录，training parameter和preprocess与数据集绑定\n\n3. 参考论文列表\n- [GBDT+LR] Practical Lessons from Predicting Clicks on Ads at Facebook\n- [FM] S. Rendle, Factorization machines\n- [FM Model] Fast Context-aware Recommendations with Factorization Machines\n- [FFM] Yuchin Juan，Yong Zhuang，Wei-Sheng Chin，Field-aware Factorization Machines for CTR Prediction\n- [NCF] Neural Collaborative Filtering\n- [Wide\u0026Deep] Cheng H T, Koc L, Harmsen J, et al. Wide \u0026 deep learning for recommender systems\n- [FNN] Weinan Zhang, Tianming Du, and Jun Wang. Deep learning over multi-field categorical data - - A case study on user response\n- [PNN] Qu Y, Cai H, Ren K, et al. Product-based neural networks for user response prediction\n- [DeepFM] Huifeng Guo et all. DeepFM: A Factorization-Machine based Neural Network for CTR Prediction\n- [AFM] Attentional Factorization Machines - Learning the Weight of Feature Interactions via Attention Networks\n- [NFM] Neural Factorization Machines for Sparse Predictive Analytics\n- [DCN] Deep \u0026 Cross Network for Ad Click Predictions\n- [Deep Crossing] Deep Crossing - Web-Scale Modeling without Manually Crafted Combinatorial Features\n- [xDeepFM] xDeepFM- Combining Explicit and Implicit Feature Interactions for Recommender Systems\n- [FiBiNET]- Combining Feature Importance and Bilinear feature Interaction for Click-Through Rate Prediction\n- [AutoInt]- Automatic Feature Interaction Learning via Self-Attentive Neural Networks\n- [DIN] Deep Interest Network for Click-Through Rate Prediction.\n- [DIEN] Deep Interest Evolution Network for Click-Through Rate Prediction\n\n4. 总结博客\n- [CTR学习笔记\u0026代码实现1-深度学习的前奏 LR-\u003eFFM](https://www.cnblogs.com/gogoSandy/p/12501846.html)\n- [CTR学习笔记\u0026代码实现2-深度ctr模型 MLP-\u003eWide\u0026Deep](https://www.cnblogs.com/gogoSandy/p/12658051.html)\n- [CTR学习笔记\u0026代码实现3-深度ctr模型 FNN-\u003ePNN-\u003eDeepFM](https://www.cnblogs.com/gogoSandy/p/12742417.html)\n- [CTR学习笔记\u0026代码实现4-深度ctr模型 NFM/AFM](https://www.cnblogs.com/gogoSandy/p/12814804.html)\n- [CTR学习笔记\u0026代码实现5-深度ctr模型 DeepCrossing -\u003e DCN](https://www.cnblogs.com/gogoSandy/p/12892973.html)\n- [CTR学习笔记\u0026代码实现6-深度ctr模型 后浪 xDeepFM/FiBiNET](https://www.cnblogs.com/gogoSandy/p/13023265.html)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdsxiangli%2Fctr","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdsxiangli%2Fctr","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdsxiangli%2Fctr/lists"}