*** Final Report with entirity of project is all compiled in the file: TMDbMovieBoxOfficePredictionModel.ipynb
This project was completed in full by Nick Mitchell and Cole Leppert. This is the first full scale machine learning project that either of us had ever worked on and proved to be an incredibly useful learning experience. We learned a lot as we went and truly gave it our best efforts, however, mistakes are a natural part of the learning process and we likely made some. All feedback and constructive criticism is not only welcomed, but encouraged.
The film industry is quite popular in today's society and only growing more popular each year. So many major blockbuster hits release every year, making hundreds of millions of dollars (sometimes even over 1 billion), that are exceedingly successful. But for all of the successful movies, there are plenty more that absolutely flop in the box office and are dissappointing by every metric. The goal of this project is to analyze what makes particular movies successful, and others not so much, by a measure of worldwide box office revenue. Futhermore, after analyzing the data on these movies, we aim to sccuessfully predict the revenue for movies as well, as it proves to be extremely useful in industry to know what the significant factors of success may be. This challenge was presented on Kaggle roughly a year ago, so we are a bit late to the party, however we decided it was a fun challenge to do and came up with the idea independently before finding the dataset and challenge. Since it was already avaiable to us and seemed like a great initial project for us to take on, we decided to dive into it. This notebook is the result, including full exploratory data analysis, feature engineering and selection, and modeling. Thank you for taking the time to look at our work and we hope you enjoy!
Check out the original challenge here: https://www.kaggle.com/c/tmdb-box-office-prediction