Machine Learning - Classification
Credit Card Fraud Detection ML Classification
An intermediate project tackling a real-world classification problem: identifying fraudulent credit card transactions. This project focuses on the critical challenge of working with highly imbalanced datasets. You will apply techniques like SMOTE to handle the class imbalance, train robust classification models, and evaluate them using appropriate metrics for skewed data, such as the ROC curve, AUC, and Precision-Recall curve.
Technologies Used
🐍Python
🔧 Scikit-learn
🔧 Pandas
🔧 imbalanced-learn
🔧 Matplotlib
🔧 Seaborn
Project Info
CategoryMachine Learning - Classification
Technologies6
Features11
Key Features
Analyze and preprocess a highly imbalanced dataset where fraudulent transactions are rare.
Apply techniques like SMOTE (Synthetic Minority Over-sampling Technique) to create a balanced training set.
Use StandardScaler to scale features for optimal model performance.
Train and compare multiple classification models
Code Implementation
Checking Class Imbalance