The topic consists on movie predictions using multivariate regression and feature modelling. The application is built using R environment for computing and graphics.
The data comes from the Rotten Tomatoes and IMDB web sites and consists of audience and critic review scores for 651 movies (random sample of data) released from 1970 till 2016. In addition to review scores, the data contains several other variables regarding each movie such as genre, running time, MPAA rating, production studio, Oscar nominations, release year, actors participating and more. In total, there is an amount of 32 variables stored in this dataset.