Tanuj Saxena

Email: tanuj.saxena.rks@gmail.com | Phone: +91 8126560686 | LinkedIn: linkedin.com/in/tanujsaxena437

About Me

Tanuj Saxena

Aspiring Machine Learning and Data Science student pursuing a degree in Computer Science and Engineering with a focus on Data Science. Currently working on cutting-edge projects, including Gait Recognition Systems and Sentiment Analysis, leveraging advanced machine learning algorithms and data-driven techniques.
Proficient in Python, SQL, and Object-Oriented Programming, with expertise in data analysis, feature engineering, and model optimization. Skilled in creating impactful data visualizations using tools like Tableau, Power BI, and Matplotlib to extract actionable insights.
Passionate about applying machine learning and AI to solve real-world problems, I thrive in collaborative environments that drive innovation and growth. Eager to contribute to projects that utilize data and technology for impactful solutions.

Skills

Education

B.Tech in Computer Science

Sharda University | 2022-2026

Secondary Education

ST. Peter's Sr. Sec. School | 2020-2022

Experience

Machine Learning Intern

CodSoft, India | Sep 2023 - Oct 2023

  • Boosted classification accuracy from 70% to 80% by optimizing preprocessing and model selection using Scikit-learn.
  • Developed an SMS Spam Detection model with SVM, achieving 99% accuracy through advanced feature extraction and hyperparameter tuning.
  • Improved customer churn prediction by optimizing Random Forest, increasing accuracy from 81% to 86%.
  • Implemented cross-validation and grid search to ensure robust model performance and actionable insights.

Projects

Adaptive AI Questioning System

  • Developed a Python-based adaptive questioning system using Scikit-learn to dynamically adjust question difficulty based on student performance, enhancing system efficiency.
  • Implemented Item Response Theory (IRT) and Cognitive Diagnostic Models (CDM), achieving a 10% improvement in model accuracy.
  • Utilized Object-Oriented Programming (OOP) for scalability and analyzed real-time student interactions to improve engagement and educational outcomes.

Sentiment Analysis Web Application

  • Built a sentiment analysis app using Streamlit, integrating Logistic Regression with TF-IDF vectorization and BERT, achieving a 10% accuracy increase.
  • Enabled real-time sentiment predictions with robust text preprocessing and features to input text or upload CSV/Excel files, providing downloadable results.
  • Optimized model performance, improving F1-score by 12% and overall accuracy to 92%, ensuring reliable sentiment analysis for actionable insights.

Certifications

Download My Resume