USING NEUTRAL NETWORKS TO DETERMINE THE FINANCIAL PLAN

Planning of financial statement is annual and one of the most important activities of financial managers of all companies. The well assembled plan is the first step to the success of a company in the following period. There exist several methods how to do it: intuitive method, statistic methods, causality or combination of all of them. The aim of this paper is to utilize artificial intelligence for planning financial statements of a concrete example. Data of a company founded by ČEZ were used – ČEZ renewable resources. Complete financial statements from 2004 to 2014 are available. The following networks were used: a linear network, a probabilistic neural network, a generalised regression neural network, a radial basis function network, a three-layer perceptron network and a four-layer perceptron network. The analysis resulted in a concrete model of an artificial neural networks usable for planning financial statements. The neural networks should be able to determine with more than ninety per cent accuracy of predictable variables. The text also includes the basic statistical characteristics of the examined sample and the achieved results (sensitivity analysis, confusion matrix, etc.). The model can be utilized in practice by financial managers for planning financial statements of their companies.