School of Mining Engineering (ETDs)
Permanent URI for this community
Browse
Browsing School of Mining Engineering (ETDs) by Keyword "Multiple regression"
Now showing 1 - 1 of 1
Results Per Page
Sort Options
Item Application of derivative techniques to improve the forecasting of price volatility of copper, gold and platinum metals(2024) Veriyadi, VeriyadiThis research investigates the forecasted price volatility of copper, gold and platinum metals based on the selected companies; Palabora Copper Mining Ltd, AngloGold Ashanti Ltd, Gold Fields Ltd, Sibanye-Stillwater, Anglo Platinum Ltd and Impala Platinum Ltd. In responding to the latter sentence, single price volatilities are dual volatilities, where dual volatilities comprise of financial and technical variables. The selected firms either have global operations or they are subsidiaries of global companies. Dual volatility is computed using a Sample Correlation Coefficient and in order to explore the dual volatility, this research introduces three hypotheses. The first hypothesis uses a Decision Tree Analysis to test dual volatility based on financial and technical variables (e.g., mineral commodity price, metal grade, operating cost and production rate) in improving the forecasting of price volatility of copper, gold and platinum metals. For validation, the first hypothesis uses the Markov-Regime Switching Model. The results of this hypothesis illustrate that dual volatilities are more accurate and robust than price only volatilities. Then, the second hypothesis examines dual volatility using a GBM model. This hypothesis tests dual volatility; which is computed based on financial and technical variables (e.g., oil price, copper price, oil production and consumption, copper production and consumption; and the exchange rate from U.S.$ to ZAR and gold and platinum price data). The chosen variables that affect the dual volatility are examined using a Multiple Regression Model and that model confirms that those variables are independent in principle. Finally, the third hypothesis estimates future profits based on a binomial tree, which has risk-neutral probabilities based on dual volatility using mineral commodity price, metal grade, operating cost and production rate. The results of risk-neutral probabilities using dual volatility are less optimal than a mineral commodity price volatility due to not accounting for the mean of logarithmic returns. The robustness test uses the VAR model, which indicates that the profits react differently to different shock stages from revenues, risk-free interest rates and profits. In conclusion, dual volatility can improve future price forecasting performance because duality is underpinned by different variables, which include independent variables from the global commodity markets. The forecasting performance improvement from dual volatility in predicting the future price can be shown by the lower value of the Root Mean Square Error and Mean Absolute Percentage Error results than a mineral commodity price volatility. The findings of this research apply to copper, gold and platinum metals for mining around the globe.