Skip to content

[Completed] R-Based Movielens 10M dataset with linear regression, regularization, and recosystem library

Notifications You must be signed in to change notification settings

the-ethical-ai/Movielens_Harvardx

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Netflix Movie Recommendation Challenge


Overview of the Project

Inspired by the Netflix Recommendation Challenge, where a $1,000,000 prize was offered to the first team to achieve an improve of 10% or better over Netflix's then deployed movie recommendation algorithm, this project covers the development of a matrix factorization machine learning model with an RMSE score of 0.781 (approximately 9.6% better than Netflix's model). Created independently in Summer 2022, the project utilized R, RStudio, machine learning, data visualization, and data cleaning techniques to both outperform Netflix's algorithm and make explicit the power of matrix factorization in predictive models.

Disclaimer

This project was completed in July 2022 and no further work is expected at this time.

I make no claim to the data used. The dataset is available at: https://grouplens.org/datasets/movielens/10m/.

About

[Completed] R-Based Movielens 10M dataset with linear regression, regularization, and recosystem library

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages