End-to-End ML Pipeline for IMDB Rating Prediction w/ Advanced Feature Engineering.

The goal is to analyze historical movie data and develop a model that accurately estimates the rating given to a movie by users or critics.

This project focuses on analyzing movie ratings data using matrix factorization techniques and clustering algorithms. The goal is to identify meaningful segments of users and movies, and to evaluate the clustering results through various metrics. We apply both hierarchical and K-means clustering methods.

Deep dive into Fandango's 2015 movie ratings: uncover stars vs. true scores, vote patterns, yearly trends, and bias vs. Rotten Tomatoes/IMDB. Interactive plots reveal critic-user discrepancies and data insights.​

neural network model using TensorFlow and Keras to predict the rating user would give to a movie based on their past rating history. Utilized embeddings to encode high-cardinality categorical features.