Data Scientist
CurrentDeveloped and deployed machine learning models to identify fraudulent applications for loan pre-approvals and detect fraudulent credit card transactions using supervised learning methods.Utilized Python libraries such as Pandas, NumPy, SciPy, Matplotlib, Seaborn, and Scikit-learn for model development and data manipulation.Performed Exploratory Data Analysis (EDA), data cleaning, feature scaling, and feature engineering to optimize model performance.Evaluated models using cross-validation, log loss function, and ROC curves to ensure high accuracy and reliability.Worked with deep learning frameworks like TensorFlow and PyTorch for complex model development and natural language processing.Developed real-time anomaly detection algorithms, which reduced operational risks by detecting irregularities early