About

Data Engineering and Analytics professional with hands-on experience building end-to-end machine learning and data pipelines in Python and SQL. Delivered a fraud detection model on 280,000+ transactions with 99%+ ROC-AUC and an NLP sentiment classifier on 150,000+ tweets with 92%+ accuracy. Completed 6 applied data science projects spanning classification, regression, and NLP. Skilled in data cleaning, feature engineering, statistical analysis, and data visualization using Pandas, NumPy, Scikit-learn, Power BI, and Excel.

Experience1

1. OI

   Data Science Intern

   Jul 2026 — Present

   Oasis Infobyte

   Delivered 5 end-to-end data science projects covering classification, regression, and NLP pipelines built in Python and Scikit-learn. Performed data cleaning, exploratory data analysis, and feature engineering on real-world datasets to prepare inputs for predictive modeling.

Projects2

• Credit Card Fraud Detection System

  Engineered a machine learning pipeline on 280,000+ transaction records, achieving 99%+ ROC-AUC and 95% precision; improved model performance 15% through feature engineering and exploratory data analysis. Resolved severe class imbalance using SMOTE; benchmarked 5+ classification algorithms and produced 10+ visualizations to communicate fraud patterns to stakeholders.

  • Python
  • Pandas
  • NumPy
  • Scikit-learn
  • Matplotlib

• Tweet Sentiment Analysis

  Built an NLP pipeline to classify 150,000+ tweets into positive, negative, and neutral sentiment with 92%+ accuracy using tokenization, TF-IDF vectorization, and 4 machine learning models.

  • Python
  • NLTK
  • Matplotlib

Education1

• DU

  B.Tech

  2022 — 2026

  DIT University

  Information Technology