Cleaned data by handling missing values, outliers, and duplicates using Pythonlibraries such as Pandas and NumPy.Conducted EDA to identify patterns, trends, and relationships in data using Pythonvisualization tools like Matplotlib and Seaborn.Performed feature engineering by creating new variables from existing data toenhance model performance, such as calculating patient risk scores from healthmetrics.Developed regression models (Linear regression, LASSO, Ridge, Random Forest) topredict health insurance prices based on factors such as age, health condition, andcoverage level.Evaluated model performance using metrics like Root Mean Squared Error (RMSE),Mean Absolute Error (MAE) and R2 score.Developed a machine learning model that accurately predicts health insurancepremiums with a 15% improvement in accuracy compared to the previous model,helping the client optimize their pricing strategy.Conduct regular meetings with clients to gather requirements, present projectprogress, and discuss analytical findings.

Optimized test coverage with risk-based analysis techniques, focusing on highimpactareas of the application.Mentored junior testers on best practices, enhancing overall team knowledge andcapabilities.Managed defect tracking systems, ensuring accurate documentation of issues forefficient resolution.Contributed to the successful launch of multiple software products by rigorouslyvalidating features throughout the development lifecycle.Collaborated with cross-functional teams to identify system requirements anddevelop effective test strategies.Participated in post-release reviews to analyze lessons learned from completedprojects, driving process improvements for future endeavors.Identified critical bugs and worked closely with developers to ensure timelyresolution, resulting in a more stable product.Streamlined testing processes by developing reusable test scripts and templates.

Helping protect the platform from financial losses due to fraud, ensuring a safe shopping experience for customers, and maintain the company's reputation.1. Review and analyze transaction data to detect suspicious patterns or anomalies indicative of fraudulent activity.2. Manage and document investigation cases from initial detection through to resolution.3. Collect and analyze evidence related to suspicious transactions, including customer account information, transaction history, and external data sources.4. Prepare comprehensive reports on investigation findings, including risk assessment, evidence, and take appropriate actions.5. Integrate and utilize machine learning models and algorithms to enhance fraud detection capabilities.