DIVYA PRAKASH

Engineered and maintained a scalable Selenium automation framework using Java and TestNG, boosting test execution efficiency by 90% across web and mobile chatbot applications.

Reduced daily manual regression effort by approximately 2 hours through the development and management of over 1,000 automated test cases for Windows, macOS, Android, and iOS platforms.

Led comprehensive end-to-end functional, regression, and API testing efforts, increasing User Acceptance Testing (UAT) approval rates by 20% and ensuring robust release readiness.

Enhanced backend reliability and performance by executing REST API testing with Postman and performance testing with JMeter, ensuring stable and efficient end-to-end workflows.

Streamlined defect resolution and cross-functional delivery by fostering collaboration with engineers, designers, and product managers, meticulously managing all test artifacts in JIRA and Confluence.

Developed a wine quality classification model utilizing Random Forest classifiers, achieving 88.5% accuracy on a dataset of 1,599 samples with 12 distinct chemical features.

Conducted comparative performance analysis across six machine learning algorithms (Logistic Regression, Decision Trees, Random Forest, KNN, SVM) using Python to identify optimal solutions.

Enhanced model evaluation and interpretability through comprehensive data analysis and visualization, leveraging Pandas, NumPy, Matplotlib, and Seaborn.

Facilitated data-driven model selection by meticulously benchmarking algorithms based on accuracy metrics and performance comparisons.