Skip to content
View manasviantil's full-sized avatar
🎯
Focusing
🎯
Focusing

Block or report manasviantil

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
manasviantil/README.md

Hi, I'm Manasvi Antil πŸ‘‹

AI/ML Developer | Data Science Enthusiast | 3rd Year CSE Student

I'm a Computer Science student at Maharaja Agrasen University (CGPA: 8.60) passionate about building end-to-end AI\ML applications β€” from data preprocessing to model deployment.


πŸš€ About Me

  • πŸŽ“ B.Tech in Computer Science & Engineering (2024–2028)
  • πŸ€– Focused on AI, Machine Learning, Deep Learning, and Natural Language Processing
  • πŸ› οΈ I build AI/ML apps and deploy using Streamlit
  • πŸ“Š Experienced in AI Tools, EDA, predictive modeling, and data preprocessing
  • πŸ“« Reach me at: manasviantil17@gmail.com
  • πŸ”— Connect on LinkedIn

🧠 Tech Stack

Languages

Python C++ SQL

ML & Deep Learning

TensorFlow Keras Scikit-learn

Data & Visualization

Pandas NumPy Matplotlib Seaborn

NLP & Deployment

NLTK Streamlit Jupyter Git


πŸ“‚ Featured Projects

LSTM-based deep learning model for context-aware next-word prediction

  • Built with TensorFlow/Keras, applied tokenization, sequence padding & feature engineering
  • Achieved 75% prediction accuracy on test sequences
  • Deployed as an interactive Streamlit web app for real-time text prediction

ML-based system to predict stroke risk from patient health data

  • Performed full EDA, feature engineering & hyperparameter tuning
  • Compared multiple algorithms, achieved 87% accuracy
  • Deployed with Streamlit for real-time clinical predictions

Text classification model to detect positive, negative, and neutral sentiment

  • NLP preprocessing pipeline: tokenization, stop-word removal, stemming
  • Implemented Naive Bayes & Logistic Regression, achieved 86% accuracy
  • Live prediction UI built with Streamlit

Personalized movie recommendations using ML

  • Implemented content-based filtering and collaborative filtering
  • Focused on data preprocessing, model optimization & user preference matching

πŸ“Š GitHub Stats

Manasvi's GitHub Stats

Top Languages


πŸ… Certifications

  • πŸ† Microsoft Elevation Program β€” AI, ML & Microsoft Copilot (Feb 2026)
  • πŸ† SmartEd Training & Internship Program β€” AI/ML with Python (Sep–Dec 2025)

πŸ“¬ Let's Connect

LinkedIn GitHub Email


⭐ If you find my projects useful, consider giving them a star!

Pinned Loading

  1. Heart-stroke-prediction-system-using-Machine-Learning Heart-stroke-prediction-system-using-Machine-Learning Public

    Developed a predicitive model to access the risk of stroke/heart disease using patient health data.

    Jupyter Notebook 1

  2. Movie-recommendation-system Movie-recommendation-system Public

    It is a machine learning project that suggests movies to users based on their preferences. It works by analyzing movie features like genre, cast, and ratings, and finding similarities between movie…

    Jupyter Notebook 1

  3. Next-Word-predictor Next-Word-predictor Public

    LSTM- based deep learning model for real time next word prediction | TensorFlow, Keras, NLP, Streamlit | 75% accuracy

    Jupyter Notebook 1

  4. RAG-Chatbot RAG-Chatbot Public

    A Retrieval-Augmented Generation (RAG) chatbot built with LangChain, ChromaDB, Mistral AI, and Streamlit. Upload PDF books, perform semantic search, and get accurate, context-aware answers powered…

    Python 1