Investigating sales and production volumes of gold, PGM, iron ore and manganese using a Bayesian change point detection approach

Abstract

This paper identified change points in the production volumes and sales of various Industrial Metals in South Africa from the period 2003 – 2016. The socio-economic environment in which the mining sector operates is complicated, with countless factors influencing the performance of industrial metals. This complexity makes it difficult for mining stakeholders to accurately forecast the production and sales for specific metals. A descriptive model that links the identified change points to causative events or factors was constructed. This model provides mining stakeholders with information on the events or factors that have the greatest impact on the performance of the various metals. This information allows mining stakeholders to focus forecasting efforts on the identified factors. Combining the focused forecasts with the impact that similar events had in the past helps the mining stakeholders to alter production levels or schedule investments before forecasted events take place, minimising the potential negative impact of said event. In this study, the monthly production volumes and sales of Gold, Platinum Group Metals (PGMs), Iron Ore and Manganese were analysed. The data spanned from 2003 – 2016 and was supplied by StatsSA. The data was analysed using the Bayesian Change Point Analysis (BH) (Barry and Hartigan, 1993). The results reveal that production drops were caused predominantly by mining strikes and increases in production costs, while sales were influenced by changes in the exchange rates and rand value of the commodity. Future papers will use sales volumes instead of Actual Rand values in order to identify changes that can be attributed to shifts in the demand of each metal. Future papers will also focus on performing a multivariate analysis on similar data to determine whether certain factors influence numerous metals.