Comparison Between the Hybrid Model of Genetic Fuzzy and Self - Organizing Systems and Linear Model to Predict the Price of Gold Coin Futures Contracts

Abstract

This paper investigates the forecasting gold coin futures contract price in Iran Mercantile Exchange. this research has presented a hybrid model based on genetic fuzzy systems (GFS) and artificial neural network (ANN) to forecast the gold futures contract, At first, we use stepwise regression analysis (SRA) to determine factors which have most influence on stock prices. At the next stage we divide our raw data into k clusters by means of self-organizing map (SOM) neural networks. Finally, all clusters will be fed into independent GFS models. Finally, the results from the proposed hybrid model was compared with the results from forecasting ARIMA model using mean absolute percentage error (MAPE). Results show that the proposed approach outperforms of ARIMA model, so it can be considered as a suitable tool for forecasting price Gold coin futures contracts problems.

Keywords

• self – organizing map (som)
• genetic fuzzy system (gfs)
• arima model
• gold coin futures contracts