An interactive Machine Learning-powered web application that predicts whether a person is diabetic based on key health parameters. Built with Python, Scikit-learn, and Streamlit, this app aims to make early diabetes risk detection simple and accessible.

Predict future stock prices using a pre-trained LSTM deep learning model. Upload a CSV file with historical stock data or use a sample to visualize trends and forecast closing prices.

Handwritten Digit Classifier using a trained MNIST model. Draw or upload a digit (0-9) and get its predicted value instantly.

A machine learning model that predicts house prices based on features like size, location, and amenities. Helps buyers and sellers estimate property values accurately.

Brain Tumor MRI Classification is an end‑to‑end deep learning project that trains multiple models (ResNet50, VGG16, a custom CNN, SVM, and Random Forest) to automatically detect and classify brain tumors from MRI scans into four classes: glioma, meningioma, pituitary, and no tumor.

This Hand gesture recognition project using mediapipe is developed to recognize various hand gestures. The user can custom train any number of various hand gestures to train a model.

Real-time household energy consumption forecasting system powered by XGBoost and FastAPI. Includes MLOps automation with DVC, MLflow, Prefect, and Streamlit dashboard.

Web platform allows users to upload CSV files and train a machine learning model using the uploaded data

Heart Health Prediction using Machine Learning

A machine learning-powered web application to predict UFC fight outcomes using historical data and betting odds.

DSA Projects - Artificial Intelligence

Email Spam Detection using Machine Learning

A machine learning model designed to classify emails as spam or not spam (ham). This project uses natural language processing (NLP) techniques to process email text data and machine learning algorithms.

The Titanic classification problem involves predicting whether a passenger on the Titanic survived or not, based on various features available about each passenger. The sinking of the Titanic in 1912 is one of the most infamous maritime disasters in history, and this dataset has been widely used as a benchmark for predictive modeling.

A journey of learning and practicing machine learning fundamentals through daily problem-solving.

The main purpose of this repository is to build the pipeline for training of regression models and predict the compressive strength of concrete to reduce the risk and cost involved in discarding the concrete structures when the concrete cube test fails.

Repository for predicting house prices using the Ames Housing dataset. Implements advanced regression techniques with TensorFlow Decision Forests, including Random Forests. The project covers data exploration, feature engineering, model training, evaluation, and visualization.

A PyTorch-based Convolutional Neural Network (CNN) for image classification using the CIFAR-10 dataset, featuring advanced architecture, data augmentation, GPU support, and dynamic learning rate scheduling.

This project classifies emails into 4 categories — Incident, Request, Problem, or Change — while protecting privacy by masking PII (Personally Identifiable Information) like names, emails, and phone numbers.

A CNN-based model to classify facial expressions into 7 emotions: angry, disgust, fear, happy, neutral, sad, and surprise. Trained on grayscale 48x48 images using TensorFlow/Keras with data augmentation and class balancing.