Performance evaluation of ANN and Neuro-fuzzy system in business forecasting

In recent years, Artificial intelligence based algorithms are being widely used as prediction models in different domains. However, the suitability and performance of a particular technique depends on the essence of the prediction problem at hand. In this paper we perform a comparison of prediction performance of two widely used AI techniques namely Adaptive Neuro-fuzzy inference system (ANFIS) and Artificial neural network (ANN). For performance analysis two forecasting problems have been considered. First one is the sales forecasting for which the real sales dataset of cold drinks collected by authors for five months has been used. Second is the stock price prediction problem for which the daily stock market data of BSE obtained from Yahoo Finance has been used. Root mean square error and prediction accuracy have been used to evaluate the performance of the two models.