Forecasting Base Metal Prices with Commodity Currencies

Abstract

In this paper we show that the Chilean exchange rate has the ability to predict the returns of the London Metal Exchange Index and of the six primary non-ferrous metals that are part of the index: aluminum, copper, lead, nickel, tin and zinc. The economic relationship hinges on the present-value theory for exchange rates, a ‡oating exchange rate regime and the fact that copper represents about a half of Chilean exports and nearly 45% of Foreign Direct Investment. Consequently, the Chilean peso is heavily a¤ected by ‡uctuations in the copper price. As all six base metal prices show an important comovement, we test whether the relationship between copper prices and Chilean exchange rates also holds true when it comes to the six primary non-ferrous metals. We …nd interesting evidence of predictability both in-sample and out-of-sample. Our paper is part of a growing literature that in the recent years has evaluated and called into question the ability of commodity currencies to forecast commodity prices.

The Predictive Relationship Between Exchange Rate Expectations and Base Metal Prices

“…According to the present-value-model for exchange rate determination, if a given commodity price is an important driving force for a given exchange rate, then there should be Granger causality from that exchange rate to the relevant commodity price. Chen, Rossi and Rogo¤ (2010) is an in ‡uential work exploring this relationship, but many others have followed, including Chen, Rossi and Rogo¤ (2011,2014), Groen and Pesenti (2011), Gargano and Timmermann (2014), Lof and Nyberg (2017), Ciner (2017) and Pincheira and Hardy (2018). All these papers evaluate directly the predictive ability from commodity currencies to commodity prices with rather mixed results.…”

“…We focus on one particular country: Chile, which has been traditionally analyzed in the literature and o¤ers a particularly simple case given the strong connection between the Chilean economy and only one commodity: copper. As noted by Pincheira and Hardy (2018), this metal represents about a half of Chilean exports and nearly 45% of its Foreign Direct Investment (FDI). We consider the Survey of Economic Expectations (SEE) carried out on a monthly basis by the Central Bank of Chile to extract expectations about future developments of the Chilean peso.…”

Can we beat the Random Walk? The case of survey-based exchange rate forecasts in Chile

“…Our target is the h-period return defined as follows: , − In our notation, h denotes the relevant forecast horizon in months. We consider h=1, 3,6,9,11,12,18,24.…”

“…Nevertheless, starting with the influential paper of Chen, Rossi and Rogoff (2010), a growing literature has shown that the Chilean peso has the ability to Granger cause copper prices, base metal prices, and a World Commodity index. See for instance, Chen, Rogoff (2010, 2014), Pincheira and Hardy (2018a) and the references cited therein. The potential finding of good predictors of the Chilean exchange rate may also illuminate the road to find good predictors for some of these commodity prices and, therefore, may result appealing for a worldwide audience 1 .…”

Forecasting E-Commerce Products Prices by Combining an Autoregressive Integrated Moving Average (ARIMA) Model and Google Trends Data

“…As an example, authors in [4,8] describe as ARIMA can easily handle such a data format and how it is well suited for time series forecasting. One more example is represented by [21] where authors described an ARIMA model with currency as exogenous feature used to forecast commodity prices. ARIMA has also been employed within the agriculture domain where authors in [6] discussed how they have employed it for forecasting crop prices, and results indicate very low error values in terms of MSE (Mean Squared Error) and MAPE (Mean Absolute Percentage Error).…”