Credit-Card-fraud-detection-using-Machine-Learning
Detect Fraudulent Credit Card transactions using different Machine Learning models and compare performances
- 81
- Jupyter Notebook
- 6 y ago
Detect Fraudulent Credit Card transactions using different Machine Learning models and compare performances
This repository presents the code for digital modulation detection in Communication networks
This repository is for MATLAB code for balancing of multiclass data by SMOTE
Classifying whether the credit card transaction is fraudulent or not using Logistic Regression
🩺CKD Ensemble Classifier ML-based Chronic Kidney Disease prediction using 24 ensemble models across 3 feature sets (All, RFE, Boruta). Built with FastAPI + React/TypeScript, featuring MICE imputation, Borderline-SMOTE, and 8 ensemble methods (RF, XGBoost, LightGBM, GBDT, AdaBoost, Bagging, Stacking, Voting). Replicates Rahman et al., 2024 methord.
The advertisement click prediction wiith machine learning models.
PySpark for multiple linear regression on car horsepower using SMOTE for data augmentation.
This project explores the Framingham Heart disease dataset with the objective to predict its risk in 10 years. Various methods for handling missing values and outliers are explored as iterations. After analysing the dataset, important and necessary features are selected. Seven ML models are implemented, with evaluation on the basis of Test Recall.
An end-to-end Machine Learning credit card fraud detection system addressing extreme class imbalance (0.17% fraud rate) using SMOTE, XGBoost, decision threshold tuning, and a real-time Streamlit dashboard.
End-to-end supervised ML classification: Logistic Regression, SVM, Decision Trees, Gradient Boosting, MLP Neural Nets, and SMOTE imbalanced learning.
Credit card fraud detection system using machine learning. Includes multiple models and compares performance under different class imbalance techniques (SMOTE and undersampling).