Data Science Recommender System Global Baseline

This project focuses on building a simple recommender system using global baseline predictors on a simulated dataset of book ratingsby users.The baseline recommender estimates unknown ratings by considering three components:• The overall average rating (global mean),• A user bias — the tendency of a user to rate higher or lower than average,• An item bias — how a book tends to be rated across all users.Mathematically:Baseline Estimate = 𝜇 + 𝑏𝑢 + 𝑏𝑖Where: - 𝜇 = global average rating, - 𝑏𝑢 = bias of user u, - 𝑏𝑖 = bias of item i.Baseline recommenders are often the first step in building scalable systems. They are interpretable, efficient, and lay the groundworkfor more complex techniques like matrix factorization or deep learning.This project aims to:• Simulate sparse user-item rating data,• Predict unknown ratings using baseline predictors,• Evaluate accuracy using Root Mean Square Error (RMSE). This publication presents brief overview of Project. It includes key methods, datasets, or findings, with the goal of Global baseline predictors. The work contributes to Data Science Recommender Systems by providing baseline predictors. If you find this work useful, please cite it using the DOI: 10.5281/zenodo.16579428