fraud-detection-analysis

With the rapid increase in mobile transactions, financial fraud has emerged as a significant concern for businesses, organizations, and individuals. This project aims to address this issue by performing an exploratory analysis to detect and prevent fraudulent activities based mobile transaction data. We use the power of PySpark toprocess large volumes of data and engineer relevant features. Spark ML algorithms such as Logistic Regression and Principal Component Analysis to predict fraudulent transactions. The performance of these models is evaluated using metrics like recall and precision. This project highlights the importance of data analysis, feature engineering and model selection in achieving high accuracy in identifying fraudulent transactions.