Forecasting copper prices in the short and medium terms using geostatistics (85ec8f44-0e97-49ec-a0bf-7fb69134cd4d)

"In this paper, geostatistical techniques are applied to forecast the annual copper price in the short and medium terms (from one to five years ahead). These techniques allow the incorporation of monthly and multivariate information in the analysis and provide more accurate results than traditional approaches, especially as far as the one-year forecast is concerned.A second advantage of geostatistics stems from its ability to assess the uncertainty associated with the unknown future prices, thanks to estimation variances or confidence intervals, depending on the technique used. Such an assessment has a crucial importance in decision-making, from both macroeconomic and microeconomic points of view. IntroductionThe copper price traded in the London Metal Exchange is a relevant parameter for defining macroeconomic policies of producing countries like Chile. It is also a key factor for the mining companies, since fluctuations in the sell price affect the expected financial flows. Due to the amount of money involved in decision-making, it is necessary to have accurate forecasts of the future copper prices and to quantify the uncertainty associated with such prices.This paper focuses on the annual copper price estimation in the short and medium terms, i.e., from one to five years into the future. Henceforth, the word “estimation” will be used as a synonym of “forecast,” according to the geostatistical jargon (Matheron, 1989).Two main approaches, based either on statistics or econometrics, are currently used to forecast commodity prices, but both of them are not very accurate when applied to copper. First, the main methods are briefly reviewed, then the geostatistical formalism will be presented. So far, the latter approach hardly has been used to estimate commodity prices, although it may reconcile both statistics and econometrics via (1) the use of a stochastic approach and (2) the handling of ancillary variables related to the copper market. Another advantage of geostatistical techniques is the ability not only to forecast the copper price, but also to measure the uncertainty associated with it."