Skip to content
View hemamalini0708's full-sized avatar

Block or report hemamalini0708

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
hemamalini0708/README.md

👋 Hi, I'm Hema Malini

Data Science | Machine Learning | Generative AI

I build practical AI and ML projects using Python, TensorFlow, Flask, Streamlit, LangChain, and ChromaDB.

I work on end-to-end solutions — from data preprocessing and model training to deployment and evaluation.

I am focused on Data Science, Machine Learning, NLP, and GenAI roles where I can contribute through real project work.

📫 hemamalinig07@gmail.com · LinkedIn · GitHub

Pinned Loading

  1. Credit-Card-Risk-Prediction Credit-Card-Risk-Prediction Public

    End-to-end binary classifier on 150K+ records. Used SMOTE to resolve severe class imbalance (8K → 111K samples), benchmarked 5 models, achieved 89.1% accuracy and AUC 0.818 with Random Forest. Prod…

    Python

  2. Food_Classification_Using_CNN Food_Classification_Using_CNN Public

    Multi-class food classifier across 34 categories. Benchmarked Custom CNN vs VGG16 vs ResNet50 on 7,956 training images — VGG16 reached 73.32% validation accuracy. Flask app returns per-prediction n…

    HTML

  3. Sentiment_Analysis Sentiment_Analysis Public

    Sentiment Analysis using Bi-Directional RNN (Deep Learning). Classifies movie reviews as Positive or Negative using TensorFlow & Keras. Covers full pipeline: text preprocessing, word embeddings, mo…

    Python

  4. AI-Powered-Customer-Churn-Prediction-System AI-Powered-Customer-Churn-Prediction-System Public

    End-to-end AI-powered Customer Churn Prediction system that predicts whether a telecom customer will leave or stay based on service usage, billing details, and demographic features. Includes prepro…

    Python

  5. NLPSQL-Offline-Natural-Language-to-SQL-Engine NLPSQL-Offline-Natural-Language-to-SQL-Engine Public

    Offline NL-to-SQL engine — type a question in plain English, get PostgreSQL results instantly. Built with Ollama (local LLM), pgvector RAG, self-healing SQL, Streamlit UI and FastAPI. 100% offline,…

    Python

  6. AI-PDF-Q-A-System-using-RAG-LLM AI-PDF-Q-A-System-using-RAG-LLM Public

    A production-grade RAG system that lets users upload any PDF and ask questions in plain English. Built with LangChain, ChromaDB, HuggingFace Embeddings, Groq LLaMA 3, and Streamlit. Returns precise…

    Python