We aim to replicate the paper "Why do tree-based models still outperform deep learning on tabular data?" as a competition. As the paper gather 59 datasets, it is in fact a 59 in 1 competition.  It is set as a benchmark to compare 'State of the art' tree models and DL models. 

Your goal is to provide a solution to outperform a boosted tree ensemble baseline. Despite the title it can be anything. 

The more general goal of the competition is to provide a benchmark so that newcomers can learn about best practices and more experienced people can evaluate advances in ML for tabular data.