I'm a Machine Learning Engineer and Full Stack Developer who builds end-to-end ML systems β from raw data to deployed applications. I work across the full pipeline: data cleaning, feature engineering, model training, evaluation, and deployment.
- π€ ML Engineering β feature scaling, encoding, log transformation, model comparison & evaluation pipelines
- π Deployed ML apps using Streamlit β live diabetes risk prediction in production
- π Full Stack β building web applications with JavaScript, Node.js & Python
- πΈοΈ Data collection β building web scrapers with BeautifulSoup for real-world datasets
- 𧩠DSA β solving problems on LeetCode @codewithgate28
- π« rahulkumarsaxena9988@gmail.com Β |Β LinkedIn
| # | Project | Description | Stack |
|---|---|---|---|
| π©Ί | diabetes-risk-prediction | End-to-end ML system β EDA, full model comparison (LR, KNN, DT, RF), evaluation pipeline & live Streamlit deployment | Python, scikit-learn, Streamlit |
| π’ | ambitionbox-scraper | Production scraper extracting company data from AmbitionBox β ratings, reviews, type & location | Python, BeautifulSoup |
| π | log-transformation-titanic | Feature engineering deep-dive β log transformation on Titanic with distribution analysis (Histogram + Q-Q) and before/after model accuracy comparison | Python, scikit-learn |
| πΌ | Job-Portal | Full-stack job portal web application | JavaScript, Node.js |
| π‘ | sklearn-onehot-encoding | One-hot encoding, k-1 trick, high-cardinality handling & ColumnTransformer pipelines |
Python, scikit-learn |
| π | min-max-feature-scaling | Min-Max normalization on UCI Wine dataset with before/after distribution visualizations | Python, scikit-learn |
| π | Feature-Scaling-using-Standardization-method | Standardization-based feature scaling β theory to implementation | Python, scikit-learn |
| Level | Skills |
|---|---|
| π΄ Advanced | Dynamic Programming Β· Backtracking Β· Divide and Conquer |
| π‘ Intermediate | Math Β· Depth-First Search Β· Hash Table |
| π’ Fundamental | Arrays Β· Strings Β· Two Pointers |