{"id":24551429,"url":"https://github.com/samueljayasingh/e-commerce-product-recommendation-system","last_synced_at":"2025-07-30T21:33:29.602Z","repository":{"id":273264422,"uuid":"919147170","full_name":"SamuelJayasingh/E-Commerce-Product-Recommendation-System","owner":"SamuelJayasingh","description":"This repository contains a hybrid recommendation system for Amazon products in a CSV File. The system combines collaborative filtering and content-based filtering to provide personalized product recommendations","archived":false,"fork":false,"pushed_at":"2025-01-19T20:31:45.000Z","size":1989,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-16T13:41:43.923Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/SamuelJayasingh.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":"2025-01-19T20:20:04.000Z","updated_at":"2025-01-19T20:31:46.000Z","dependencies_parsed_at":"2025-01-19T21:32:31.465Z","dependency_job_id":"1f0d342b-44d7-4aad-900a-52918235c335","html_url":"https://github.com/SamuelJayasingh/E-Commerce-Product-Recommendation-System","commit_stats":null,"previous_names":["samueljayasingh/e-commerce-product-recommendation-system"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/SamuelJayasingh/E-Commerce-Product-Recommendation-System","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SamuelJayasingh%2FE-Commerce-Product-Recommendation-System","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SamuelJayasingh%2FE-Commerce-Product-Recommendation-System/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SamuelJayasingh%2FE-Commerce-Product-Recommendation-System/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SamuelJayasingh%2FE-Commerce-Product-Recommendation-System/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/SamuelJayasingh","download_url":"https://codeload.github.com/SamuelJayasingh/E-Commerce-Product-Recommendation-System/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SamuelJayasingh%2FE-Commerce-Product-Recommendation-System/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":267945168,"owners_count":24170215,"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":"2025-07-30T02:00:09.044Z","response_time":70,"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":[],"created_at":"2025-01-23T01:17:01.936Z","updated_at":"2025-07-30T21:33:29.580Z","avatar_url":"https://github.com/SamuelJayasingh.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# E-Commerce Product Recommendation System\n\nThis repository contains a hybrid recommendation system for Amazon products. The system combines collaborative filtering and content-based filtering to provide personalized product recommendations.\n\n## Table of Contents\n\n1. [Introduction](#introduction)\n2. [Data Cleaning and Transformation](#data-cleaning-and-transformation)\n3. [Collaborative Filtering](#collaborative-filtering)\n4. [Singular Value Decomposition (SVD) for Collaborative Filtering](#singular-value-decomposition-svd-for-collaborative-filtering)\n5. [Generate Collaborative Filtering Recommendations](#generate-collaborative-filtering-recommendations)\n6. [Content-Based Filtering](#content-based-filtering)\n7. [Hybrid Recommendation System](#hybrid-recommendation-system)\n8. [Real-Time Recommendations](#real-time-recommendations)\n9. [Evaluation](#evaluation)\n10. [Usage](#usage)\n11. [Dependencies](#dependencies)\n\n## Introduction\n\nThis recommendation system leverages both collaborative filtering and content-based filtering techniques to provide users with personalized product recommendations. The collaborative filtering component uses user-item interaction data, while the content-based filtering component uses product features to make recommendations.\n\n## Data Cleaning and Transformation\n\nThe dataset is first cleaned by removing duplicates and handling missing values. Text fields are standardized by converting to lowercase and removing extra spaces.\n\n## Collaborative Filtering\n\nA User-Item Interaction Matrix is created based on implicit feedback (browsing history or purchase interactions). Interactions are treated as binary values.\n\n## Singular Value Decomposition (SVD) for Collaborative Filtering\n\nSingular Value Decomposition (SVD) is applied to factorize the interaction matrix and generate user-product recommendations based on similarity.\n\n## Generate Collaborative Filtering Recommendations\n\nRecommendations are generated based on the similarity between users.\n\n## Content-Based Filtering\n\nContent-Based Filtering is implemented using TF-IDF vectorization. The `combined_features` column (which includes both category and about_product) is used to compute the similarity between products.\n\n## Hybrid Recommendation System\n\nThe hybrid recommendation system combines both collaborative and content-based recommendations.\n\n## Real-Time Recommendations\n\nFor real-time updates, you can simulate real-time browsing or interaction and immediately generate recommendations based on the recent activity.\n\n## Evaluation\n\nThe recommendation system can be evaluated using Precision, Recall, or Mean Average Precision (MAP) by comparing the generated recommendations with actual user preferences.\n\n## Usage\n\nTo use the recommendation system, follow these steps:\n\n1. Load the dataset and clean the data.\n2. Create the User-Item Interaction Matrix.\n3. Apply SVD for dimensionality reduction.\n4. Generate collaborative filtering recommendations.\n5. Implement content-based filtering using TF-IDF vectorization.\n6. Combine collaborative and content-based recommendations to form a hybrid recommendation system.\n7. Generate real-time recommendations based on recent user activity.\n8. Evaluate the recommendation system using appropriate metrics.\n\n## Dependencies\n\nThe following Python libraries are required:\n\n- pandas\n- numpy\n- scikit-learn\n\nYou can install these dependencies using pip:\n\n```sh\npip install pandas numpy scikit-learn\n```\n\nTo install the dependencies listed in the `requirements.txt` file, you can use the following command:\n\n```sh\npip install -r requirements.txt\n```\n\n## License\n\nThis project is licensed under the MIT License. See the [LICENSE](LICENSE) file for details.\n\n## Disclaimer\n\n⚠️ This project is solely for educational purposes to acquire knowledge about Collaborative Filtering and Singular Value Decomposition (SVD) for Collaborative Filtering.","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsamueljayasingh%2Fe-commerce-product-recommendation-system","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsamueljayasingh%2Fe-commerce-product-recommendation-system","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsamueljayasingh%2Fe-commerce-product-recommendation-system/lists"}