Developed a machine learning-based classification and prediction system for DDoS attacks using various algorithms such as Random Forest, K-Nearest Neighbors (KNN), and Decision Tree. Streamlined customer onboarding, reducing time by 30% and improving efficiency by 40%.Responsibilities:· Developed efficient and scalable data models, leveraging AI/ML frameworks, resulting in a 20% improvement in application performance.· Applied machine learning algorithms for the classification and prediction of DDoS attacks, enhancing detection accuracy and system robustness.· Resolved critical bugs and issues through meticulous debugging and testing, ensuring a bug fix success rate of 95% and minimizing production incidents by 30%.· Integrated data analysis applications with databases (e.g., Oracle, MySQL, PostgreSQL), optimizing database schemas and executing SQL queries for seamless data retrieval and storage.· Conducted code reviews, resolving 90% of bugs and enhancing application performance by 15%.

Worked on multiple Kaggle datasets including Titanic, Bank Churn, and Smoke Signals, achieving an accuracy of 80% using various machine learning algorithms.Responsibilities:· Developed machine learning models to analyze and predict outcomes for Titanic, Bank Churn, and Smoke Signals datasets.· Utilized algorithms such as Random Forest, K-Nearest Neighbors (KNN), and Decision Tree to achieve high accuracy.· Conducted data preprocessing, feature engineering, and model tuning to optimize performance.· Evaluated model performance using cross-validation and other statistical techniques.· Collaborated with team members to refine models and improve prediction accuracy.