About
B.Tech Computer Science student focused on Machine Learning and Data Science, with hands-on experience in Python, scikit-learn, NLP, and data preprocessing. Built end-to-end ML projects covering preprocessing, model training, evaluation, APIs, and deployment.
Education
-
B.Tech in Computer Science and EngineeringComputer Science and Engineering · 2024 – 2028
-
Class XIINew RSJ Public SchoolPCM · 2024
-
Class XNew RSJ Public School2022
Skills
- C <3 months
- FastAPI <3 months
- Python <3 months
- JavaScript <3 months
- Classification <3 months
- Feature Engineering <3 months
- Matplotlib <3 months
- Model Evaluation <3 months
- NumPy <3 months
- Pandas <3 months
- scikit-learn <3 months
- Seaborn <3 months
- JSON <3 months
- API Integration Understanding <3 months
- Data Structures and Algorithms <3 months
- Pydantic <3 months
- Regression <3 months
- Oop <3 months
- Naive Bayes <3 months
- Pipelines <3 months
- Tf-Idf <3 months
- Cross Validation <3 months
Tools / apps / platforms
- Git <3 months
- GitHub <3 months
- Jupyter Notebook <3 months
- MongoDB <3 months
- VS Code <3 months
Projects
-
Patient Management APIFastAPI, Pydantic, Python, JSON
REST endpoints for patient-data management with Pydantic validation, HTTP exception handling, and JSON-based persistence.
-
Movie Recommendation SystemPython, Pandas, Scikit-learn, Streamlit, TMDB API
Content-based recommendation system using movie metadata and similarity techniques, with an interactive Streamlit interface and TMDB API integration.
-
California Housing Price PredictionPython, Pandas, Scikit-learn, Linear Regression, Random Forest
Regression pipeline using feature engineering, stratified sampling, preprocessing, and feature scaling, evaluated with RMSE and cross-validation.
-
SMS Spam ClassifierPython, NLP, Scikit-learn, TF-IDF, Multinomial Naive Bayes
NLP text-classification model using TF-IDF vectorization and Multinomial Naive Bayes, with the trained model and vectorizer persisted for reuse.
-
Telco Customer Churn PredictionPython, Pandas, Scikit-learn, Logistic Regression, Random Forest
End-to-end churn prediction pipeline with missing-value imputation, categorical encoding, feature scaling, and cross-validation.
-
Student Mental Health Score PredictorPython, Pandas, NumPy, Scikit-learn, Random Forest, Streamlit, FastAPI, Joblib
End-to-end regression application predicting a student's Mental Health Score from demographic, academic, lifestyle, stress, and social-media usage features. Includes preprocessing pipelines, model comparison, and deployment through Streamlit and FastAPI.
Courses & certifications
- 3-Day Generative AI Bootcamp · WikiClub Tech, United University
- Open Machine Learning Workshop · Cognizance, IIT Roorkee