This project uses a K-Means clustering method to find unique groupings of film reviews. Which review scores are best at predicting Box Office revenue?
In this dataset, we find audience reviews (Rotten Tomatoes Score) and critics reviews (Metascore) of Disney films ( only films with Box Office revenue excludes Disney+ releases) by identifying patterns and trends beyond simply sorting. I use Python for its ease-of-use, plotting capabilities, and a wide array of K-Means methods.
K-Means clustering is considered a reasonably straightforward partitioning technique: tell the model how many groups you want and assign all the data points to the appropriate group.
View the process in its entirety in datalore below:
