Multi-target regression datasets

Mulan , a sourceforge net multi-target dataset available in www.openml.org. Despite the numerous interesting applications of MTR, there are only few publicly available datasets of this kind - perhaps because most applications are industrial - and most experimental evaluations of MTR methods are based on a limited amount of datasets. For this study, much effort was made for the composition of a large and diverse collection of benchmark MTR datasets. In addition to 5 datasets that have been used in previous studies and are publicly available (edm, sf1, sf2, jura, wq), we also used 5 publicly available datasets (enb, slump, andro, osales, scpf) that have not been used for MTR benchmarking in the past. The raw MTR data from a variety of interesting application domains and composed 8 new benchmark datasets (atp1d, atp7d, oes97, oes10, rf1, rf2, scm1d, scm20d). In total there are 18 datasets which are made publicly available. This is the largest collection of benchmark MTR datasets to date.