Learning Outcome

By completing this project, you will learn how to:

• Load and work with real-world datasets using pandas for analysis and preprocessing

• Perform exploratory data analysis to understand ratings behavior and genre distribution

• Apply content-based filtering by converting movie genres into numerical vectors using TF-IDF

• Use K-Nearest Neighbors with cosine similarity to find similar movies efficiently

• Combine genre similarity and average ratings using a hybrid scoring approach

• Build a complete movie recommendation pipeline from raw data to ranked output

• Deploy a machine learning model using Gradio to create an interactive web interface

This project demonstrates practical skills in data processing, machine learning modeling, and lightweight deployment.