Film Industry is one of the most important industries in the world, making a big impact in our society. But film making requires many resources. Producers are interested in finding the future commercial performance of a film project. In this project, a set of neural networks predict if a film will be nominated to an Oscar Award. This neural networks try to find patterns within the films that have the most award success.
This research compares several self-programmed multi-layer perceptrons, making combinations of number of neurons per layer and other hyper-parameters, tested on the data set formed by the processing some characteristics of a film.
If you want to replicate the results of this project you must download the data folder
In the file there are several algorithms tested on easy datasets to cluster, and a hard movies dataset. The data used for this research is from the combination of two Kaggle data sets. The resulting data set contains the following features.
- Title of the movie.
- Rating, a categorical variable indicating the Motion Picture Association film rating.
- Genres, a categorical variable indicating the main genre of the movie.
- Duration of the movie in minutes.
- Number of years since the film premiere.
- Votes in IMDb.
- Score in IMDb.
- Country, 1 if the country is The United States, 0 if not.
- Budget of the film
As said above, the data folder must be downloaded and simply run the notebook. The notebook already includes a requirements.txt generator. Anyway there is a requirements.txt file in this repository.
The description, analysis and conclusion of the results are in the paper Trabajo_Redes_Neuronales_Juliana_Henao.pdf.