Pushpa Publishing House

Journal Menu

Content

Volume 4 (2009)

Volume 3 (2009)

Volume 2 (2008)

Volume 1 (2008)

Far East Journal of Experimental and Theoretical Artificial Intelligence

Far East Journal of Experimental and Theoretical Artificial Intelligence
Volume 6, Issue 1-2, Pages 43 - 60 (November 2010)

GOLD PRICE FORECASTING BY HYBRID INTELLIGENT SYSTEMS WITH GARCH EFFECTS
Hamid Abrishami, Mohsen Mehrara, Mehdi Ahrari and Vida Varahrami

Abstract:
The difficulty in gold price forecasting, due to its inherent complexity, has attracted much attention of academic researchers and business practitioners. Various methods have been tried to solve the problem of forecasting gold prices, however, none of the existing models of prediction can meet practical needs. In this paper, a novel hybrid intelligent framework is developed by applying a systematic integration of GMDH neural networks with GA and rule-based expert system (RES) with web-based text mining (WTM) employs for gold price forecasting. Our research reveals that during a financial crisis period by employing hybrid intelligent framework for gold price forecasting, we obtain better forecasting results compared to the GMDH neural networks and results will be so better when we employ hybrid intelligent system with GARCH for gold price volatility forecasting.

Keywords and phrases: gold price forecasting, web-based text mining (WTM), group method of data handling (GMDH) neural networks, genetic algorithm (GA), hybrid intelligent system, rule-based expert system (RES), GARCH (1, 1) method.

Submitted by Shun-Feng Su

Number of Downloads: 374 | Number of Views: 491