Credit Card Fraud Detection using Machine Learning
Built a machine learning model to detect fraudulent credit card transactions using Scikit-Learn. Performed detailed EDA to analyze class imbalance, transaction patterns, and correlations. Preprocessed the dataset using StandardScaler, train–test split, and SMOTE to handle heavy imbalance.
Trained Logistic Regression, Random Forest, and XGBoost models and evaluated them using accuracy, precision, recall, and confusion matrix. Improved recall to reduce missed frauds.
Used Python, Pandas, NumPy, Matplotlib, and Seaborn for data cleaning, visualization, and insights.
Fraud Detection Data Analysis (EDA)
Performed exploratory data analysis on a fraud transaction dataset to identify unusual patterns, correlations, and anomalies. Cleaned data, handled imbalance, analyzed distributions, and visualized insights using Python, Pandas, Matplotlib, and Seaborn. Improved understanding of fraud behavior and data-driven decision-making.
Sales Data Analysis
Analyzed a sales dataset to identify monthly trends, top-selling products, and customer purchasing patterns. Cleaned and processed data using Python and Pandas, and created visualizations using Seaborn to generate business insights that support decision-making.