Abstract
The project will be built on a recommendation system, particularly for material pertaining to digital media such as movies or web series. A method known as collaborative filtering is going to be the approach that forms the basis of our research. In order to carry out the implementation of this model, we will make use of the ml-25m dataset, as well as spark (MLib), the ideas of matrix factorization, and the ALS algorithm. The distributed computing architecture that Spark offers will not only make it possible to analyse massive datasets quickly and effectively, but with the use of Deep Learning,it will also increase the scalability and performance of the system.
)