The aim of this article is to utilize artificial neural networks to predict potential financial problems in transport companies in the Czech Republic. It is logical that uncertain economic environment it is necessary for companies to be able to plan better, to report more precisely and to be able to better evaluate their future financial development. The text uses financial statement data, non-accounting data and six types of neural network. The autors predict how companies are able to overcome potential financial problems, within how many years a company might go bankrupt, or whether a company might go bankrupt within one calendar year.