UCL Applied Machine Learning 1

This data comes from Kaggle.com, a machine learning competition site.

This is a prediction problem in which there are 50000 datapoints (vectors), each datapoint being itself a sparse 50000 dimensional vector.

About the data

xtrain.txt contains the training data. Each row specifies which 10 elements of the training vector contain 1, with all other entries being 0.

ytrain.txt contains the training value.

xtest.txt contains the test data.