This project builds a machine learning-based recommendation system for products. It leverages different machine learning models, such as Random Forest and Nearest Neighbors, to suggest products based on user interactions and product features.

Machine Learning Product Recommendation System This project builds a machine learning-based recommendation system for products. It leverages different machine learning models, such as Random Forest and Nearest Neighbors, to suggest products based on user interactions and product features.

Features: Data Loading: Loads product data from a CSV file and prepares it for machine learning by encoding categorical features and handling missing values. Data Visualization: Visualizes the distribution of ratings for products across different categories and subcategories. Recommendation System: Based on a user's input product, it suggests similar products using a K-Nearest Neighbors model. User-Based Recommendations: A different model predicts whether a user would recommend a product or not, using their historical interactions with products. ML Models: Supports training and evaluation using different models, such as Random Forest, MLP (Multi-Layer Perceptron), and others.