For this exercise, you are going to work again with a movie review dataset. In this dataset, conventional and social media movies, the ratings, budgets, and other information of popular movies released in 2014 and 2015 were collected from social media websites, such as YouTube, Twitter, and IMDB, etc.; the aggregated dataset can be downloaded from OA 8.6. Use this dataset to complete the following objectives:

a. What can you tell us about the rating of a movie from its budget and aggregated number of followers in social media channels?

b. If you incorporate the type of interaction the movie has received (number of likes, dislikes, and comments) in social media channels, does it improve your prediction?

c. Among all the factors you considered in the last two models, which one is the best predictor of movie rating? With the best predictor feature, use the gradient descent algorithm to find the optimal intercept and gradient for the dataset. Often the hardest part of solving a machine learning problem can be finding the right estimator for the job. Different estimators are better suited for different types of data and different problems