A Novel Approach of Artificial Neural Networks Modeling Based on Fuzzy Regression Approach for Forecasting Purposes: The case of liquid gas price in Japan’s market

Abstract

In this paper, a new approach of modeling for Artificial Neural Networks (ANN) models based on the concepts of ANN and fuzzy regression is proposed. For this purpose, we reformulated ANN model as a fuzzy nonlinear regression model while it has advantages of both fuzzy regression and ANN models. Hence, it can be applied to uncertain, ambiguous, or complex environments due to its flexibility. In addition, the case study is brought in order to clearly show the way this approach could be utilized. The price of the liquid gas in Japan's market (the world's largest natural gas importer) is investigated based on the proposed approach. Based on the results, it is concluded that the performance of proposed model is acceptable; moreover, it can be deal with uncertain and complex environments as a clear box model.