{"id":24149138,"url":"https://github.com/abdulbasit110/fraud-detection-ml-model","last_synced_at":"2026-06-08T04:32:23.447Z","repository":{"id":269618744,"uuid":"907992310","full_name":"Abdulbasit110/FRAUD-DETECTION-ML-MODEL","owner":"Abdulbasit110","description":"A robust fraud detection system using machine learning to identify suspicious transactions. Features data preprocessing, feature engineering, and advanced classifiers (e.g., Logistic Regression, Random Forest, SVM) with performance metrics like accuracy, precision, and recall for accurate anomaly detection.","archived":false,"fork":false,"pushed_at":"2025-04-10T12:15:37.000Z","size":84305,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-04-10T12:55:01.082Z","etag":null,"topics":["ai","deep-learning","fraud-detection","machine-learning","machine-learning-algorithms","prediction-model"],"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/Abdulbasit110.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":"2024-12-24T20:00:28.000Z","updated_at":"2025-04-10T12:15:40.000Z","dependencies_parsed_at":"2025-02-05T14:32:11.320Z","dependency_job_id":null,"html_url":"https://github.com/Abdulbasit110/FRAUD-DETECTION-ML-MODEL","commit_stats":null,"previous_names":["abdulbasit110/fraud-detection-ml-model"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Abdulbasit110/FRAUD-DETECTION-ML-MODEL","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Abdulbasit110%2FFRAUD-DETECTION-ML-MODEL","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Abdulbasit110%2FFRAUD-DETECTION-ML-MODEL/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Abdulbasit110%2FFRAUD-DETECTION-ML-MODEL/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Abdulbasit110%2FFRAUD-DETECTION-ML-MODEL/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Abdulbasit110","download_url":"https://codeload.github.com/Abdulbasit110/FRAUD-DETECTION-ML-MODEL/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Abdulbasit110%2FFRAUD-DETECTION-ML-MODEL/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34048681,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-08T02:00:07.615Z","response_time":111,"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":["ai","deep-learning","fraud-detection","machine-learning","machine-learning-algorithms","prediction-model"],"created_at":"2025-01-12T08:35:46.373Z","updated_at":"2026-06-08T04:32:23.442Z","avatar_url":"https://github.com/Abdulbasit110.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Fraud Detection Pipeline\n\nA machine learning pipeline for detecting suspicious financial transactions.\n\n## Overview\n\nThis pipeline processes raw transaction data through a series of steps to build a fraud detection model:\n\n1. **Data loading**: Imports raw transaction data from CSV files\n2. **Data cleaning**: Handles missing values and converts data types\n3. **Feature engineering**: Creates transaction pattern metrics and risk indicators\n4. **Model training**: Trains various classifiers (Random Forest, SVM, etc.)\n5. **Evaluation**: Measures model performance with standard metrics\n\n## Features\n\n- **Transaction Analysis**: Detects unusual transaction patterns and spiking\n- **Email Matching**: Identifies discrepancies between sender names and email domains\n- **Multiple Classifiers**: Random Forest, Logistic Regression, SVM, KNN, and more\n- **Class Imbalance Handling**: Uses SMOTE to address the rarity of fraudulent transactions\n- **Performance Visualization**: Generates confusion matrices and performance graphs\n\n## Installation\n\n```bash\n# Clone the repository\ngit clone https://github.com/Abdulbasit110/FRAUD-DETECTION-ML-MODEL.git\ncd fraud-detection-pipeline\n\n# Create and activate virtual environment (optional but recommended)\npython -m venv venv\nsource venv/bin/activate  # On Windows: venv\\Scripts\\activate\n\n# Install dependencies\npip install -r requirements.txt\n```\n\n## Usage\n\n### Basic Usage\n\n```python\nfrom fraud_detection_pipeline import FraudDetectionPipeline\n\n# Initialize the pipeline\npipeline = FraudDetectionPipeline(\n    raw_data_path=\"path/to/your/data.csv\",\n    model_save_path=\"random_forest_model.pkl\"\n)\n\n# Run the complete pipeline\nresults = pipeline.run_pipeline(model_type='random_forest')\n\n# Save the trained model\npipeline.save_model()\n\n# Make predictions on new data\nnew_transactions = pd.read_csv(\"new_transactions.csv\")\npredictions, probabilities = pipeline.predict_transaction(new_transactions)\n```\n\n### Advanced Usage\n\nYou can run each step of the pipeline individually:\n\n```python\npipeline = FraudDetectionPipeline()\n\n# Load and prepare data\npipeline.load_data(\"path/to/your/data.csv\")\npipeline.clean_data()\npipeline.engineer_features()\npipeline.prepare_data_for_training(test_size=0.25, random_state=42)\n\n# Train different models and compare\nmodels = ['random_forest', 'logistic_regression', 'svm', 'voting']\nresults = {}\n\nfor model_type in models:\n    pipeline.train_model(model_type)\n    results[model_type] = pipeline.evaluate_model()\n    \n# Save the best model\nbest_model = max(results, key=lambda k: results[k]['f1'])\npipeline.train_model(best_model)\npipeline.save_model(f\"{best_model}_model.pkl\")\n```\n\n## Model Performance\n\nThe pipeline includes evaluation metrics for model performance:\n- Accuracy\n- Precision\n- Recall\n- F1 Score\n- Confusion Matrix\n\nA confusion matrix visualization is saved as `confusion_matrix.png` after evaluation.\n\n## Customization\n\nYou can customize the pipeline by:\n- Adding new features in the `engineer_features()` method\n- Implementing different models in the `train_model()` method\n- Modifying the evaluation metrics in `evaluate_model()`\n\n## Requirements\n\n- Python 3.8+\n- pandas\n- numpy\n- scikit-learn\n- imbalanced-learn\n- matplotlib\n- seaborn\n- Flask (for API integration)\n- joblib\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fabdulbasit110%2Ffraud-detection-ml-model","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fabdulbasit110%2Ffraud-detection-ml-model","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fabdulbasit110%2Ffraud-detection-ml-model/lists"}