You will predict the opening weekend revenues of major films released in 2008 and 2009.
Features
This dataset contains a lot of features that could predict box office revenues. Some prominent candidates are: production_budget, oscar_wining_actors_present, genres, directors, christmas_release, number_of_screens.
Many other features are for you to discover and utilize in your predictions.
Solution Ideas
You have a lot of flexibility in what you might do. You could focus on feature engineering, i.e., coming up with fancy inputs for your method, or you could focus on fancy regression techniques that use the features. Here are some ideas to get you started:
Basic regression on meta-data features: A good place to start is to turn the metadata into a vectorial feature representation, and use a linear regression technique like ridge regression. You could use quantitative features such as production budget, binary holiday release variables, and number of Oscar-winning actors.
Use a neural network: If you think there isn’t enough flexibility, you could go ahead and learn about multi-layer perceptrons and how to train them with backpropagation.
Use a support vector machine: If you prefer your objectives convex, you could jump the gun and learn about regression with support vector machines.
Go totally Bayesian: Worried that you’re not accounting for uncertainty? You could take a fully Bayesian approach to linear regression and marginalize out your uncer- tainty. Intrigued by the infinite-dimensional stuff I mentioned in lecture? Check out Gaussian process regression.
Acknowledgements
We thank Professor Ryan Adams and his students @ Harvard University for putting together this public dataset.