Skip to content
View poorvaja-1603's full-sized avatar
6 followers · 7 following
  • 08:28 (UTC +05:30)

Achievements

Achievement: Pair ExtraordinaireAchievement: Pull Shark

Achievements

Achievement: Pair ExtraordinaireAchievement: Pull Shark

Highlights

  • Pro

Block or report poorvaja-1603

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.

Content in all repositories owned by your account will be closed.
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
poorvaja-1603/README.md

LinkedIn GitHub

👩‍💻 About Me

Hey! I'm Poorvaja, a Computer Engineering student at VESIT, Mumbai (Sem IV), building at the intersection of full-stack development and AI/ML.

  • 🧠 Currently deepening my knowledge in Deep Learning
  • 🏆 Best Paper Presentation winner at VESIT Department Day (BuzzPro '26)
  • 📍 Mumbai, India

🔥 Featured Project

🎵 VibeSync — Emotion-Driven Music Recommender

Real-time facial emotion detection that recommends music matching your mood.

  • 🧬 CNN trained from scratch on FER2013 (6 emotion classes, PyTorch + CUDA)
  • 📸 Live webcam feed via OpenCV + Haar Cascade
  • 🎶 Music served via Deezer API (30s previews)
  • ⚡ FastAPI backend · Next.js frontend · Deployed on Vercel + Render

PyTorch FastAPI Next.js OpenCV CNN FER2013

🤖 ML Projects

Project What it does Stack
🎵 Song Popularity Predictor Predicts Spotify track popularity (0–100) — EDA, frequency encoding, 3 models compared, hyperparameter tuning Python, RandomForest, scikit-learn, Pandas, Streamlit
📧 Spam-Ham Classifier NLP-based email classifier — TF-IDF, CountVectorizer, 96% accuracy, deployed as web app Python, NLTK, scikit-learn, Streamlit
🏠 Melbourne House Price Predictor Random Forest regressor on Melbourne housing data — feature importance viz, map plotting, R² 0.767 Python, RandomForest, scikit-learn, Streamlit

All projects include EDA, feature engineering, model evaluation metrics, and are deployed as Streamlit web apps.

🛠️ Tech Stack

Languages

Python JavaScript Java C++

AI / ML

PyTorch scikit-learn Pandas NumPy Matplotlib NLP

Web & Full-Stack

React Next.js Node.js Express MongoDB FastAPI Streamlit

Tools

Git GitHub Vercel

Pinned Loading

  1. melbourne-house-price-predictor melbourne-house-price-predictor Public

    End-to-end machine learning project to predict Melbourne house prices using Random Forest. Built with Streamlit for deployment.

    Jupyter Notebook

  2. Song_Popularity_Predictor Song_Popularity_Predictor Public

    This model predicts popularity of a song with the help of song's audio attributes and gives a score out of 100, where 100 being the best

    Jupyter Notebook

  3. Spam_VS_Ham_Classifier Spam_VS_Ham_Classifier Public

    A machine Learning Learning model that predicts if the entered mail contents is spam or ham

    Jupyter Notebook

  4. vibe-sync vibe-sync Public

    AI Mini-Project

    JavaScript