Gold and platinum: Toward solving the price puzzle

Modeling Gold Price via Artificial Neural Network

“…Traditional mathematical models such as Autoregressive Integrated Moving Average [2], jump and dip diffusion [3], and the multi linear regression [4]- [7] models have been used for gold price forecasting. As well as, artificial intelligence models such as artificial neural networks (ANN) have been developed as a non-linear tool for gold price forecasting [2], [5], [8].…”

Short-term and long-term relationships between gold prices and precious metal (palladium, silver and platinum) and energy (crude oil and gasoline) prices

“…The price of gold, which has kept its importance for some investors and has mostly been considered as a safe haven over the years, may depend on many factors, such as crude oil price (Beckmann & Czudaj, 2013;Le & Chang, 2012;Narayan et al, 2010;Souček, 2013;Soytas et al, 2009;Wang & Chueh, 2013), inflation rates (Blose, 2010), real exchange rates (Apergis, 2014;Beckmann & Czudaj, 2013;Wang & Chueh, 2013), interest rates (Wang & Chueh, 2013), platinum prices (Kearney & Lombra, 2009;Sari et al, 2010), the consumer price index (Beckmann & Czudaj, 2013), gold reserves (Lili & Chengmei, 2013), stock indices (Anand & Madhogaria, 2012;Lili & Chengmei, 2013;Topçu & Aksoy, 2012) and future contracts (Narayan et al, 2010).…”

“…Furthermore, there was a price transmission from interest rates to gold prices. Kearney and Lombra (2009) showed that there was a positive correlation between gold and platinum prices for the period from 1985 to 2006. The correlation, which was positive in the short term in the earlier years (1996)(1997)(1998)(1999)(2000)(2001), turned out to be negative in subsequent years.…”

“…According to Kearney and Lombra (2009), precious metals such as gold and platinum are considered to be attractive assets in periods of high inflation and economic and political instability. Increases in oil prices create inflationist pressure.…”

Gold prices: Analyzing its cyclical behavior

“…Based on the latter statement, the idea of using linear or nonlinear regressions, as well as autoregressive models like ARMA, ARIMA, GARCH, among others, is discarded, because the volatility of gold prices make them all rough approximations to reality, only useful to predict in the short term. Modeling gold prices in relation to its determinants is a good proposal, like the relation between gold and platinum prices to their offer and demand in the market (Kearney & Lombra, 2009) and the macroeconomic determinants of gold prices (Batten, Ciner & Lucey, 2010). Another good model for predicting gold prices could be made by using neural networks (Parisi, Parisi & Díaz, 2008), which is fed by a lot of data, it is, daily prices of the metal constantly updated; but the predictions it can yield are of an acceptable accuracy some days ahead of today (even less than a week), and it does not work for making long-term predictions for the real dynamics of changes in prices have to be known and fed to the model in order to predict only the short-term outcomes.…”