{"id":25295721,"url":"https://github.com/sayande01/unsupervised_learning_ml","last_synced_at":"2025-04-06T20:29:28.796Z","repository":{"id":252173828,"uuid":"839644574","full_name":"sayande01/Unsupervised_Learning_ML","owner":"sayande01","description":"This project merges unsupervised learning with Association Rule Learning to analyze retail market basket data. By applying K-Means, DBSCAN, Apriori, Eclat, and FP-Growth algorithms, it uncovers purchasing patterns and segments customers into clusters, aiming to optimize product placement, promotions, and product development.","archived":false,"fork":false,"pushed_at":"2024-08-08T03:48:36.000Z","size":2354,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-13T02:38:43.432Z","etag":null,"topics":["apriori-algorithm","dbscan","fp-growth-algorithm","k-means-clustering"],"latest_commit_sha":null,"homepage":"","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/sayande01.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}},"created_at":"2024-08-08T03:31:25.000Z","updated_at":"2024-08-08T03:48:40.000Z","dependencies_parsed_at":"2024-08-08T07:45:41.674Z","dependency_job_id":null,"html_url":"https://github.com/sayande01/Unsupervised_Learning_ML","commit_stats":null,"previous_names":["sayande01/unsupervised_learning_ml"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sayande01%2FUnsupervised_Learning_ML","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sayande01%2FUnsupervised_Learning_ML/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sayande01%2FUnsupervised_Learning_ML/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sayande01%2FUnsupervised_Learning_ML/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/sayande01","download_url":"https://codeload.github.com/sayande01/Unsupervised_Learning_ML/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247546517,"owners_count":20956367,"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":["apriori-algorithm","dbscan","fp-growth-algorithm","k-means-clustering"],"created_at":"2025-02-13T02:38:59.199Z","updated_at":"2025-04-06T20:29:28.777Z","avatar_url":"https://github.com/sayande01.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"### Title:\n**Comprehensive Retail Market Analysis: Clustering and Association Rule Learning**\n\n### Description:\nThis project combines unsupervised learning techniques with Association Rule Learning to analyze retail market basket data. By applying clustering algorithms (K-Means and DBSCAN) and association rule mining algorithms (Apriori, Eclat, and FP-Growth), the project aims to uncover customer purchasing patterns and segment customers into meaningful clusters. The goal is to provide actionable insights for optimizing product placement, promotional strategies, and product development.\n\n### Objective:\n1. **Data Loading and Preprocessing:**\n   - **Import Data:** Load transaction data from a CSV file (`groceries.csv`) containing customer purchase records.\n   - **Data Transformation:** Convert transaction data into a binary matrix using the `TransactionEncoder` from the `mlxtend` library. This transformation prepares the data for Association Rule Learning.\n\n2. **Frequent Itemset Mining with Association Rule Learning:**\n   - **Apriori Algorithm:** Apply the Apriori algorithm to identify frequent itemsets with a minimum support threshold of 0.05. Use Breadth-First Search to iteratively find itemsets and generate association rules.\n   - **Eclat Algorithm:** Utilize the Eclat algorithm to find frequent itemsets through Depth-First Search, offering a comparison in terms of performance with Apriori.\n   - **FP-Growth Algorithm:** Implement the FP-Growth algorithm to discover frequent itemsets using a Frequent Pattern Tree (FP-tree), avoiding candidate generation and improving efficiency.\n\n3. **Clustering Analysis:**\n   - **K-Means Clustering:** Apply K-Means clustering to segment customers based on their purchasing behavior. Determine the optimal number of clusters and analyze the clusters to understand customer segments.\n   - **DBSCAN Clustering:** Use DBSCAN (Density-Based Spatial Clustering of Applications with Noise) to identify clusters of varying shapes and densities. Evaluate how this algorithm complements K-Means by identifying noise and outliers.\n\n4. **Association Rule Generation:**\n   - **Generate Rules:** Extract association rules from frequent itemsets identified by the Apriori, Eclat, and FP-Growth algorithms. Assess the rules using metrics such as support, confidence, and lift to identify actionable patterns.\n\n5. **Data Visualization and Interpretation:**\n   - **Visualize Clusters:** Create visualizations to represent the clusters formed by K-Means and DBSCAN. Use scatter plots and cluster heatmaps to illustrate the customer segments and their purchasing patterns.\n   - **Visualize Association Rules:** Generate visualizations to display frequent itemsets and association rules. Use bar charts and heatmaps to represent the strength of item associations and support values.\n\n6. **Practical Applications and Recommendations:**\n   - **Retail Strategies:** Recommend strategies for optimizing store layouts and product placement based on cluster analysis and association rules. For example, group related items and place them together to enhance cross-selling opportunities.\n   - **Promotional Campaigns:** Suggest targeted promotional campaigns based on customer segments and frequent itemsets. Design offers or discounts that cater to specific customer clusters and their purchasing habits.\n   - **Product Innovation:** Explore opportunities for creating new product bundles or combinations based on frequent itemsets and cluster profiles.\n\n### Tools and Libraries:\n- **Pandas:** For data manipulation and preprocessing.\n- **Matplotlib and Seaborn:** For data visualization.\n- **mlxtend:** For implementing Association Rule Learning algorithms.\n- **Scikit-Learn:** For K-Means and DBSCAN clustering algorithms.\n\nThis comprehensive project description now includes both clustering and association rule learning, providing a clear overview of the techniques used and their applications in retail market analysis.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsayande01%2Funsupervised_learning_ml","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsayande01%2Funsupervised_learning_ml","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsayande01%2Funsupervised_learning_ml/lists"}