This paper deals with methods for finding the suitable weights in an Artificial Neural Network (ANN) using Genetic Algorithms (GA). We study the weakness and strengthness of the proposed approach in case of a statistical data forecasting. We describe a different approach when using the input data during optimization phase. Besides GA, we applied stationary wavelet transform (SWT) as a signal preprocessing, and time-delay neural networks(TDNN) approach for the system’s inputs. Our results show that this optimization is suitable only for certain purposes in case of a statistical data prediction.