{"id":18494145,"url":"https://github.com/amitkaps/recommendation","last_synced_at":"2025-04-05T01:05:19.614Z","repository":{"id":37612073,"uuid":"73704950","full_name":"amitkaps/recommendation","owner":"amitkaps","description":"Recommendation System using ML and DL","archived":false,"fork":false,"pushed_at":"2022-12-08T06:10:37.000Z","size":63150,"stargazers_count":486,"open_issues_count":22,"forks_count":159,"subscribers_count":17,"default_branch":"master","last_synced_at":"2025-03-29T00:05:11.206Z","etag":null,"topics":["colloborative-filtering","deep-learning","hybrid-recommender","primer","recsys","workshop"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/amitkaps.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2016-11-14T13:00:55.000Z","updated_at":"2025-03-27T02:33:25.000Z","dependencies_parsed_at":"2023-01-24T15:15:43.835Z","dependency_job_id":null,"html_url":"https://github.com/amitkaps/recommendation","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/amitkaps%2Frecommendation","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/amitkaps%2Frecommendation/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/amitkaps%2Frecommendation/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/amitkaps%2Frecommendation/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/amitkaps","download_url":"https://codeload.github.com/amitkaps/recommendation/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247271519,"owners_count":20911587,"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":["colloborative-filtering","deep-learning","hybrid-recommender","primer","recsys","workshop"],"created_at":"2024-11-06T13:18:07.629Z","updated_at":"2025-04-05T01:05:14.597Z","avatar_url":"https://github.com/amitkaps.png","language":"Jupyter Notebook","readme":"# Recommendation Systems\n\nThis is a workshop on using Machine Learning and Deep Learning Techniques to build Recommendation Systesm\n\n- **Theory**: ML \u0026 DL Formulation, Prediction vs. Ranking, Similiarity, Biased vs. Unbiased\n- **Paradigms**: Content-based, Collaborative filtering, Knowledge-based, Hybrid and Ensembles\n- **Data**: Tabular, Images, Text (Sequences)\n- **Models**: (Deep) Matrix Factorisation, Auto-Encoders, Wide \u0026 Deep, Rank-Learning, Sequence Modelling\n- **Methods**: Explicit vs. implicit feedback, User-Item matrix, Embeddings, Convolution, Recurrent, Domain Signals: location, time, context, social,\n- **Process**: Setup, Encode \u0026 Embed, Design, Train \u0026 Select, Serve \u0026 Scale, Measure, Test \u0026 Improve\n- **Tools**: python-data-stack: numpy, pandas, scikit-learn, keras, spacy, implicit, lightfm\n\n## Notes \u0026 Slides\n\n- Basics: [Deep Learning](Notes/Deep-Learning-Basics.pdf)\n- AI Conference 2019: [WhiteBoard Notes](Notes/AIConf-CA-2019-Notes.pdf) | [In-Class Notebooks](https://notes.pipal.in/2019/AIConf-CA/) \n\n\n## Notebooks\n\n- [Movies - Movielens](MovieLens)\n    - [01-Acquire](MovieLens/01-Acquire.ipynb)\n    - [02-Augment](MovieLens/02-Augment.ipynb)\n    - [03-Refine](MovieLens/03-Refine.ipynb)\n    - [04-Transform](MovieLens/04-Evaluation.ipynb)\n    - [05-Evaluation](MovieLens/05-Evaluation.ipynb)\n    - [06-Model-Baseline](Movielens/06-Model-Baseline.ipynb)\n    - [07-Feature-extractor](Movielens/07-Feature-Extractor.ipynb)\n    - [08-Model-Matrix-Factorization](Movielens/08-Model-MF-Linear.ipynb)\n    - [09-Model-Matrix-Factorization-with-Bias](Movielens/09-MF-Linear-Bias.ipynb)\n    - [10-Model-MF-NNMF](Movielens/10-Model-MF-NNMF.ipynb)\n    - [11-Model-Deep-Matrix-Factorization](Movielens/11-Model-Deep-Factorisation.ipynb)\n    - [12-Model-Neural-Collaborative-Filtering](Movielens/12-Neural-CF.ipynb)\n    - [13-Model-Implicit-Matrix-Factorization](Movielens/13-Implicit-CF.ipynb)\n    - [14-Features-Image](Movielens/14-Image-Features.ipynb)\n    - [15-Features-NLP](Movielens/15-Doc-Embedding.ipynb)\n\n- [Ecommerce - YooChoose](YooChoose)\n    - [01-Data-Preparation](YooChoose/01-Data-Preparation.ipynb)     \n    - [02-Models](YooChoose/02-Models.ipynb)\n    \n- [News - Hackernews](HackerNews)\n- [Product - Groceries](Groceries)\n    \n\n## Python Libraries\n\nDeep Recommender Libraries\n- [Tensorrec](https://github.com/jfkirk/tensorrec) - Built on Tensorflow\n- [Spotlight](https://github.com/maciejkula/spotlight) - Built on PyTorch\n- [TFranking](https://github.com/tensorflow/ranking) - Built on TensorFlow (Learning to Rank)\n\nMatrix Factorisation Based Libraries\n- [Implicit](https://github.com/benfred/implicit) - Implicit Matrix Factorisation\n- [QMF](https://github.com/quora/qmf) - Implicit Matrix Factorisation\n- [Lightfm](https://github.com/lyst/lightfm) - For Hybrid Recommedations\n- [Surprise](http://surpriselib.com/) - Scikit-learn type api for traditional alogrithms\n\nSimilarity Search Libraries\n- [Annoy](https://github.com/spotify/annoy) - Approximate Nearest Neighbour\n- [NMSLib](https://github.com/nmslib/nmslib) - kNN methods\n- [FAISS](https://github.com/facebookresearch/faiss) - Similarity search and clustering\n\nContent-based Libraries\n- [Cornac](https://github.com/PreferredAI/cornac) - Leverage Auxiliary Data (Images, Text, Social Networks)\n\n## Learning Resources\n\n### Reference Slides\n- [Deep Learning in RecSys by Balázs Hidasi](http://pro.unibz.it/projects/schoolrecsys17/DeepLearning.pdf)\n- [Lessons from Industry RecSys by Xavier Amatriain](http://pro.unibz.it/projects/schoolrecsys17/RecsysSummerSchool-XavierAmatriain.pdf)\n- [Architecting Recommendation Systems by James Kirk](https://www.slideshare.net/JamesKirk58/boston-ml-architecting-recommender-systems)\n- [Recommendation Systems Overview by Raimon and Basilico](http://nn4ir.com/ecir2018/slides/08_RecommenderSystems.pdf)\n\n### Benchmarks\n- [MovieLens Benchmarks for Traditional Setup](https://github.com/microsoft/recommenders/blob/master/benchmarks/movielens.ipynb)\n- [Microsoft Tutorial on Recommendation System at KDD 2019](https://github.com/microsoft/recommenders)\n\n\n### Algorithms \u0026 Approaches\n- [Collaborative Filtering for Implicit Feedback Datasets](http://yifanhu.net/PUB/cf.pdf)\n- [Bayesian Personalised Ranking for Implicit Data](https://arxiv.org/pdf/1205.2618)\n- [Logistic Matrix Factorisation](https://web.stanford.edu/~rezab/nips2014workshop/submits/logmat.pdf)\n- [Neural Network Matrix Factorisation](https://arxiv.org/abs/1511.06443)\n- [Neural Collaborative Filtering](https://arxiv.org/abs/1708.05031)\n- [Variational Autoencoders for Collaborative Filtering](https://arxiv.org/abs/1802.05814)\n\n### Evaluations\n- [Evaluating Recommendation Systems](https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/EvaluationMetrics.TR_.pdf)\n\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Famitkaps%2Frecommendation","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Famitkaps%2Frecommendation","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Famitkaps%2Frecommendation/lists"}