I recently graduated with a Masters in Information Management from the University of Washington, Seattle. I have a bachelor's degree in Information Technology from the National Institute of Technology Raipur, India with professional experience in Software Development. I am passionate about building web applications and helping customers reach their goals by developing high-quality solutions.
I have demonstrated proficiency in technologies like Python, Java, TypeScript, JavaScript, SQL, and HTML. I have also developed services with AWS and REST APIs.
I seek to achieve excellence in everything that I work on. Qualities like a team player, being level headed, stead-fast & quick to learn new and challenging things make me stand out from the crowd.
Supervised Machine Learning | Regression | Predictive Analytics |Python
• Performed exploratory data analysis and evaluated linear, non-linear relationship between house prices and features
• Applied feature engineering and feature selection with Hypothesis Testing and Forward Stepwise Selection method
• Achieved best Adjusted R-squared value of 0.83 with Linear Regression, Random Forest and XGBoost Models
AWS | Python | Predictive Modeling | Scaling | Classification
• Developed and deployed RESTful API using AWS API Gateway to predict and classify fully qualified domain names (FQDNs) as benign(harmless) or DGA(malicious)
• Implemented and deployed XGBoost Classifier using AWS Sagemaker and AWS S3, achieving an accuracy of 81.39%
• Created custom-built dataset including 10 Million+ domains generated from 45+ Domain Generation Algorithms (DGA)
• Scaled the product to 1,000,000+ predictions per minute through AWS Lambda
Supervised Machine Learning | Text Mining | Classification | Python | Naive Bayes
• Preprocessed the text and extracted features by creating a Bag of Words of movie reviews from Rotten Tomatoes website
• Developed Naive Bayes algorithm from scratch in Python to classify the movie reviews as fresh(good) or rotten(bad)
• Performed hyperparameter tuning with cross-validation to achieve an accuracy of 71.5%
Python | Casual Modeling | Estimator
• Performed casual analysis of Progresa program on the schooling outcomes of individuals in Mexico
• Estimated casual impact through Before-After,Cross-sectional, and Differences-in-differences estimator and compared the results