A tutorial consisting of a set of three Jupyter Notebooks that outlines the processes of 1 - building a model to predict box-office movie gross and; 2 - analyzing the results.
Envision a use case involving a marketing team for a movie studio that wants
to do targeted advertising each week before the weekend at the box-office. In order to
do so, they must identify movies that they believe will underperform in the
upcoming weekend. The team therefore needs revenue predictions each week for
all the movies at the box-office for the upcoming weekend. Before the
weekend begins, they will use these predictions in order to formulate their
targeted marketing campaigns. Here, we focus on the movie revenue predictions.
Using data from the-numbers.com, the contents of this tutorial are focused on
building a machine learning model that can predict movie revenue for the top X movies
at the box-office for a given weekend.
**Jupyter Notebooks**
- **training-testing-dataset-creator.ipynb**
Create the dataset for training and statistical validation by scraping the-numbers.com for movie
revenue data and associated features. Also, create the dataset representing the movies
at the box-office in the upcoming weekend, to be fed to the deployed web-service predictor.
- **training-testing-plot-results.ipynb**
Use the Azure ML Studio experiment to calculate feature correlations to movie gross revenue
and subsequently display those correlations in the notebook. Create a least squares regression
model in Azure ML Studio and display the validation results in the notebook. Also, deploy the
predictive experiment in Azure ML Studio as a web-service.
- **test-deployed-model-endpoint.ipynb**
Test the deployed predictive web-service. Show the effects of swapping around lead actors in
a movie on the resulting revenue. Hit the web-service for predictions of movie revenue for
the upcoming weekend at the box-office and plot the results.
**Experiments**
- [Feature Correlations Weekend Box-Office Movie Revenue][1]
- [Forecasting Weekend Box-Office Movie Revenue][2]
- [Forecasting Weekend Box-Office Movie Revenue [Predictive Exp.]][3]
**Associated Collection**
- [Collection Link][4]
[1]: https://gallery.cortanaintelligence.com/Experiment/Feature-Correlations-Weekend-Box-Office-Movie-Revenue
[2]: https://gallery.cortanaintelligence.com/Experiment/Forecasting-Weekend-Box-Office-Movie-Revenue-5
[3]: https://gallery.cortanaintelligence.com/Experiment/Forecasting-Weekend-Box-Office-Movie-Revenue-Predictive-Exp
[4]: https://gallery.cortanaintelligence.com/Collection/Forecasting-Weekend-Box-Office-Movie-Revenue-3
