This is a simplified dataset used in research. Your focus will be to predict the bribes ("BribeValue") paid by the firms in the validation dataset. You'll use the training dataset for developing your...

This is a simplified dataset used in research. Your focus will be to predict the bribes ("BribeValue") paid by the firms in the validation dataset. You'll use the training dataset for developing your prediction models.using classifications and one with regression model

Files

• training_data-reg.csv- the training dataset with the target value ("BribeValue") included for training your prediction models.


• validation_data.csv- the dataset for which you'll provide predicted value of bribes.


• SampleSub-reg.csv- a sample submission file in the correct format for your reference. The predicted bribe values are 100 by default -- you'll replace that with your predicted values corresponding to the firms ("idstd") in the validation dataset.


• WorldBankSurvey.pdf- supplemental document with a version of the survey used by the World Bank