Simple Stock Data Set

Context

The idea is to explore the data-set for weaknesses in the collection/generation scheme of the provider. This data-set is aimed for practice against data leakages.

Content

The dataset consists of 4 columns namely v1, v2, time, price. One can try an reverse engineer the unknown variables and provide me with an opinion about the generation process. The time and price tabs are self-explanatory. The training set consists of 50,000 cases and the test dataset consists of 10,000 cases.