This data is based on the competition previously held on Kaggle. It contains the location and circumstances of every field goal attempted by Kobe Bryant during his 20-year career. Your task is to predict whether the basket went in (shot made flag).

There are three files. The first one is called "kobe-train.csv". This set is the training data set, and the name of the output attribute is "shotmadeflag". "1" means that the shot went in, and "0" otherwise.

The attribute names are self explanatory. You have to build a prediction model and make predictions for each observation on the test given in "kobe-test". In this set, the output attribute is removed on purpose. When you make a submission of your predictions as given in the file "kobe-sample-submission.csv", where the second column contains the probability that the observation belongs to class "1".

For each observation in the test data set, you should predict a probability that Kobe made the field goal. The file should have a header and the following format:

shotid,shotmade_flag 6 0.714 7 0.842 15 0.677 56 0.243

etc.

The performance of your model will be assessed on the basis of the measure "Area Under the Curve", and reported to you. You can make one submissions each day.

You are provided a sample submission file. Your file to be submitted should look like this where the second column indicates the probability the shot went in.