ML-powered web app that predicts telecom customer churn using Random Forest — built with Flask, Scikit-Learn & Pandas

Enterprise-grade CSV data quality analyzer powered by Machine Learning. Automatic anomaly detection, statistical profiling, PII scanning, and actionable insights. Secure user authentication, custom data pipelines, and interactive dashboards. Production-ready SaaS application.

A personalized Movie Recommender project. Utilizes scikit-learn for content-based recommendations, the TMDB API for movie data, and Streamlit for a user-friendly web interface. Deployed on Streamlit Cloud.

This project leverages advanced machine learning techniques to predict musical genres based on various sonic signatures within tracks. By analyzing attributes such as tempo, speechiness, and acousticness, we aim to provide an accurate classification that underscores the intrinsic nature of each song.

This is the final project for the First Term of the Machine Learning Nanodegree by Udacity. Here, we are trying to implement unsupervised learning to create customer segments for a given retail dataset.