{"id":28476310,"url":"https://github.com/aadrianleo/book-recommendation-system","last_synced_at":"2026-04-10T13:31:44.973Z","repository":{"id":296364725,"uuid":"986351640","full_name":"AadrianLeo/Book-Recommendation-System","owner":"AadrianLeo","description":"Book Recommender System using the Book-Crossing dataset. Compares content-based (TF-IDF + cosine similarity) and collaborative filtering (SVD) methods for book recommendations. Includes data cleaning, EDA, and model evaluation (Precision@5, RMSE) in Python.","archived":false,"fork":false,"pushed_at":"2025-06-03T12:18:07.000Z","size":62554,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-07-01T23:36:26.500Z","etag":null,"topics":["artificial-intelligence","collaborative-filtering","content-based-filtering","cosine-similarity","data-preprocessing","jupyter","jupyter-notebook","machine-learning","matrix-factorization","numpy","pandas","predictive-modeling","python3","recommendation-system","recommender-system","scikit-learn","sckit-surprise"],"latest_commit_sha":null,"homepage":"https://github.com/AadrianLeo/Book-Recommendation-System","language":"Jupyter Notebook","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/AadrianLeo.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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-05-19T13:32:40.000Z","updated_at":"2025-06-03T12:18:08.000Z","dependencies_parsed_at":"2025-07-01T23:43:25.273Z","dependency_job_id":null,"html_url":"https://github.com/AadrianLeo/Book-Recommendation-System","commit_stats":null,"previous_names":["aadrianleo/book-recommendation-system"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/AadrianLeo/Book-Recommendation-System","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AadrianLeo%2FBook-Recommendation-System","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AadrianLeo%2FBook-Recommendation-System/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AadrianLeo%2FBook-Recommendation-System/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AadrianLeo%2FBook-Recommendation-System/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AadrianLeo","download_url":"https://codeload.github.com/AadrianLeo/Book-Recommendation-System/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AadrianLeo%2FBook-Recommendation-System/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279014641,"owners_count":26085555,"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","status":"online","status_checked_at":"2025-10-13T02:00:06.723Z","response_time":61,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["artificial-intelligence","collaborative-filtering","content-based-filtering","cosine-similarity","data-preprocessing","jupyter","jupyter-notebook","machine-learning","matrix-factorization","numpy","pandas","predictive-modeling","python3","recommendation-system","recommender-system","scikit-learn","sckit-surprise"],"created_at":"2025-06-07T15:06:36.261Z","updated_at":"2025-10-13T10:35:10.102Z","avatar_url":"https://github.com/AadrianLeo.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Book Recommender System: Content-Based vs. Collaborative Filtering\n\nThis project implements and compares two book recommendation approaches—Content-Based Filtering and Collaborative Filtering (SVD)—using the Book-Crossing dataset.\n\n---\n\n## 📚 Project Overview\n\n- **Goal:**  \n  Design and evaluate a recommender system pipeline using real-world book data.\n- **Dataset:**  \n  [Book-Crossing Dataset (Kaggle)](https://www.kaggle.com/datasets/saurabhbagchi/books-dataset)\n- **Team Members:**  \n  Shadi Farzankia 107209  \n  Shruti Pashine 106369  \n  Dharampal Singh 106316\n\n---\n\n## 🚀 Workflow\n\n1. **Data Loading \u0026 Preprocessing:**  \n   - Load books, ratings, and users data.\n   - Clean and merge datasets, handle missing values and outliers.\n\n2. **Exploratory Data Analysis (EDA):**  \n   - Visualize distributions, check for anomalies, and understand feature relationships.\n\n3. **Recommendation Approaches:**  \n   - **Content-Based Filtering:** Uses book metadata (title, author, publisher) with TF-IDF and cosine similarity.\n   - **Collaborative Filtering (SVD):** Uses user-book ratings and matrix factorization (Surprise SVD).\n\n4. **Evaluation:**  \n   - Precision@5 (Hit Rate) for both methods.\n   - RMSE for SVD.\n\n5. **Comparison \u0026 Discussion:**  \n   - Compare strengths, weaknesses, and visualize results.\n\n---\n\n## 🗂️ Data\n\nPlace the following files in a `data/` directory:\n- `books.csv`\n- `ratings.csv`\n- `users.csv`\n\n---\n\n## 🛠️ How to Run\n\n1. Clone this repository.\n2. Install dependencies:\n    ```sh\n    pip install -r requirements.txt\n    ```\n3. Open the notebook (`Code/RecommenderSytems.ipynb`) in Jupyter or VS Code.\n4. Run all cells in order.\n\n---\n\n## 📊 Key Findings\n\n- **Content-Based Filtering:**  \n  - Interpretable, works for new/unpopular books, higher hit rate.\n- **SVD Collaborative Filtering:**  \n  - More accurate in rating prediction (lower RMSE), more personalized, but needs enough user-book interactions.\n\n---\n\n## ⚠️ Limitations \u0026 Future Work\n\n- Data sparsity and cold-start issues for collaborative filtering.\n- Evaluation for SVD is limited to a sample of users for computational reasons.\n- Future work: hybrid models, more features, deep learning approaches.\n\n---\n\n## 📎 Authors\n\n[@Shruti Pashine](https://github.com/shrutipashine), [@Shadi Farzankia](https://github.com/ShadiFarzankia), [@Dharampal Singh](https://github.com/AadrianLeo)\n\n---\n\n**Dataset:** [Book-Crossing Dataset (Kaggle)](https://www.kaggle.com/datasets/saurabhbagchi/books-dataset)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faadrianleo%2Fbook-recommendation-system","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faadrianleo%2Fbook-recommendation-system","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faadrianleo%2Fbook-recommendation-system/lists"}