For information about this contest, please see the official Kaggle.com contest website or the official contest announcement on Dataists.com.
To start working on this contest, simply download/clone this repository and run the example_model.R script in an R interpreter to see the model how our baseline model works. After that, you can start trying to build a model that makes better predictions on the data/training_data.csv data set than our example model.
For the moment, the data/installations.csv file, a part of the normalized data set for advanced users, is not yet available to the public. It will become available before the contest goes live on Kaggle. You can still use the data/training_data.csv to test your models.