USING ARTIFICIAL NEURAL NETWORKS FOR PREDICTION OF KEY INDICATORS OF A COMPANY IN GLOBAL WORLD

Artificial neural networks can be used for regression, classification or for instance for cluster analysis as an alteration of other traditional statistical analysis. Their advantages are especially ability to work with big data, accuracy of the results or simplicity of using the gained neural network. The main disadvantage leis in the way of generating single models of artificial neural networks. The correct result is set on the basis of iteration. Therefore the best model should be supervised by an expert in the concrete field. Generally, we can use regression for prediction of future development of financial indicators of a company. They are necessary for making a financial plan of a company (especially revenues). After getting the indicators we can use causal method and in the end intuitive method for making a financial plan of a company. The objective of the paper was to validate using chosen artificial neural network to predict future development of financial key indicator of CEZ Renewable Resources, Ltd. for setting a short-term financial plan. Multi-layer perceptron neural networks and Radial Basis Function neural networks were used. 1000 neural models were generated. The best got result says that it is possible to use neural networks for prediction of the future development of financial key indicators of a company.