MOVIE RECOMMENDATION

Recommendation systems pose a unique challenge in machine learning techniques, but have a wide range of applications on websites that involve products or ratings, such as Amazon, Netflix or any online store.

​

The data usually is very large but also very sparse, with correlations sometimes hard to notice. The goal of the algorithm is to find the best way to translate the data structure and predict missing values for future indications.

​

We study a recommendation system based on movie ratings, based on the Netflix challenge, proposed in 2006.