Abstract
The scientific objective of the paper is to present the findings of a study into the use of artificial neural networks in quantifying activity related risks of an innovative enterprise and to optimize its insurance cover in order to minimize the probable financial losses whenever they materialize. The Kohonen network involving the activation of 51 input variables was applied in the study. The outcomes of the stimulation for the given set of variables made it possible to determine the probability of a threat occurring in the classes. The results of the analysis were used to prepare an optimal insurance cover for the activities of the innovative company. The research findings are suitable for use in risk theory as well as in issues relating to entrepreneurship and insurance. The analytical device employed can also be put to practical use as a support tool in corporate risk management.