{"id":27162890,"url":"https://github.com/philiptitus/collaborative-book-recommender","last_synced_at":"2026-04-27T20:32:26.024Z","repository":{"id":285728404,"uuid":"959135191","full_name":"philiptitus/Collaborative-Book-Recommender","owner":"philiptitus","description":"Made use of the content-based filtering algorithm to make a book recommender model","archived":false,"fork":false,"pushed_at":"2025-04-02T10:24:09.000Z","size":11,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-02T11:28:35.516Z","etag":null,"topics":["content-based-filtering","content-based-recommendation","recommender-system","tensorflow"],"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/philiptitus.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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2025-04-02T10:20:31.000Z","updated_at":"2025-04-02T10:24:12.000Z","dependencies_parsed_at":"2025-04-02T11:39:08.593Z","dependency_job_id":null,"html_url":"https://github.com/philiptitus/Collaborative-Book-Recommender","commit_stats":null,"previous_names":["philiptitus/collaborative-book-recommender"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/philiptitus%2FCollaborative-Book-Recommender","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/philiptitus%2FCollaborative-Book-Recommender/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/philiptitus%2FCollaborative-Book-Recommender/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/philiptitus%2FCollaborative-Book-Recommender/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/philiptitus","download_url":"https://codeload.github.com/philiptitus/Collaborative-Book-Recommender/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247957879,"owners_count":21024774,"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":["content-based-filtering","content-based-recommendation","recommender-system","tensorflow"],"created_at":"2025-04-09T01:34:19.444Z","updated_at":"2026-04-27T20:32:25.975Z","avatar_url":"https://github.com/philiptitus.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Book Recommendation System\n\nA deep learning-based collaborative filtering recommendation system for books using the Book-Crossing dataset. This system predicts user ratings for books based on both user and book features.\n\n## Overview\n\nThis project implements a neural network-based recommendation system that:\n- Uses collaborative filtering to predict book ratings\n- Incorporates both user and book features\n- Provides personalized book recommendations\n- Achieves good prediction accuracy on the test set\n\n## Features\n\n- User embedding layer for learning user preferences\n- Item embedding layer for learning book characteristics\n- Dot product layer for rating prediction\n- Regularization to prevent overfitting\n- Data preprocessing and feature engineering\n- Model evaluation and recommendation generation\n\n## Dataset\n\nThe model uses the Book-Crossing dataset from Kaggle, which contains:\n- Book information (ISBN, title, author, year of publication, publisher)\n- User information (user ID, location, age)\n- Rating information (user ratings for books)\n\n## Setup\n\n1. Clone the repository:\n```bash\ngit clone \u003crepo-url\u003e\ncd book-recommendation-system\n```\n\n2. Create a virtual environment (recommended):\n```bash\npython -m venv venv\nsource venv/bin/activate  # On Windows: venv\\Scripts\\activate\n```\n\n3. Install dependencies:\n```bash\npip install -r requirements.txt\n```\n\n4. Place the dataset files in the `data` directory:\n- BX_Books.csv\n- BX-Users.csv\n- BX-Book-Ratings.csv\n\n## Usage\n\n1. Run the Jupyter notebook:\n```bash\njupyter notebook model.ipynb\n```\n\n2. Execute all cells in sequence to:\n- Load and preprocess the data\n- Train the model\n- Generate recommendations\n\n## Model Architecture\n\nThe recommendation system uses a neural network with:\n- User embedding layer (256 → 128 → 32 neurons)\n- Item embedding layer (256 → 128 → 32 neurons)\n- Dot product layer for rating prediction\n- L2 normalization for embeddings\n\n## Performance\n\nThe model achieves:\n- Training loss: ~0.56\n- Test loss: ~0.57\n- Efficient training on 66,003 samples\n- Good generalization on test set\n\n## Author\n\nPhilip Titus\n\n## Connect with Me\n\n- 🌐 [Personal Website](https://mrphilip.pythonanywhere.com/)\n- 🛍️ [Shop](https://pmart-pi.vercel.app/)\n- 👥 [LinkedIn](https://linkedin.com/in/philiptitus)\n\n## License\n\nCopyright © 2025 Philip Titus. All rights reserved. ","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fphiliptitus%2Fcollaborative-book-recommender","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fphiliptitus%2Fcollaborative-book-recommender","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fphiliptitus%2Fcollaborative-book-recommender/lists"}