scholarly journals Forecasting Commodity Prices: Looking for a Benchmark

Forecasting ◽  
2021 ◽  
Vol 3 (2) ◽  
pp. 447-459
Author(s):  
Marek Kwas ◽  
Michał Rubaszek
Keyword(s):  
Random Walk ◽  
Literature Review ◽  
Commodity Prices ◽  
Local Projection ◽  
Alternative Models ◽  
Out Of Sample

The random walk, no-change forecast is a customary benchmark in the literature on forecasting commodity prices. We challenge this custom by examining whether alternative models are more suited for this purpose. Based on a literature review and the results of two out-of-sample forecasting experiments, we draw two conclusions. First, in forecasting nominal commodity prices at shorter horizons, the random walk benchmark should be supplemented by futures-based forecasts. Second, in forecasting real commodity prices, the random walk benchmark should be supplemented, if not substituted, by forecasts from the local projection models. In both cases, the alternative benchmarks deliver forecasts of comparable and, in many cases, of superior accuracy.

PALM OIL PRICE–EXCHANGE RATE NEXUS IN INDONESIA AND MALAYSIA

2021 ◽  
Vol 24 (2) ◽  
pp. 169-180
Author(s):  
Afees Salisu ◽  
Abdulsalam Abidemi Sikiru
Keyword(s):  
Exchange Rate ◽  
Exchange Rates ◽  
Palm Oil ◽  
Commodity Prices ◽  
Oil Price ◽  
Future Research ◽  
Daily Data ◽  
Out Of Sample ◽  
Exchange Rate Movements ◽  
Predictive Content

In this study, we extend the literature analyzing the predictive content of commodity prices for exchange rates by examining the role of palm oil price. Our analysis focuses on Indonesia and Malaysia, the two top producers and exporters of palm oil, and utilizes daily data covering the period from December 12, 2011 to March 29, 2021, which is partitioned into two sub-samples based on the COVID-19 pandemic. Relying on a methodology that accommodates some salient features of the variables of interest, we find that on average the in-sample predictability of palm oil price for exchange rate movements is stronger for Indonesia than for Malaysia. While Indonesia’s exchange rate appreciates due to a rise in palm oil price regardless of the choice of predictive model, Malaysia’s exchange rate only appreciates after adjusting for oil price. However, both exchange rates do not seem to be resilient to the COVID-19 pandemic as they depreciate amidst dwindling palm oil price. Similar outcomes are observed for the out-of-sample predictability analysis. We highlight avenues for future research and the implications of our results for portfolio diversification strategies.

scholarly journals The Predictability of the Exchange Rate When Combining Machine Learning and Fundamental Models

2020 ◽  
Vol 13 (3) ◽  
pp. 48 ◽  
Author(s):  
Yuchen Zhang ◽  
Shigeyuki Hamori
Keyword(s):  
Machine Learning ◽  
Exchange Rate ◽  
Random Walk ◽  
Exchange Rates ◽  
Price Index ◽  
Economic Models ◽  
Superior Performance ◽  
Support Vector ◽  
Out Of Sample ◽  
Modern Machine

In 1983, Meese and Rogoff showed that traditional economic models developed since the 1970s do not perform better than the random walk in predicting out-of-sample exchange rates when using data obtained after the beginning of the floating rate system. Subsequently, whether traditional economical models can ever outperform the random walk in forecasting out-of-sample exchange rates has received scholarly attention. Recently, a combination of fundamental models with machine learning methodologies was found to outcompete the predictability of random walk (Amat et al. 2018). This paper focuses on combining modern machine learning methodologies with traditional economic models and examines whether such combinations can outperform the prediction performance of random walk without drift. More specifically, this paper applies the random forest, support vector machine, and neural network models to four fundamental theories (uncovered interest rate parity, purchase power parity, the monetary model, and the Taylor rule models). We performed a thorough robustness check using six government bonds with different maturities and four price indexes, which demonstrated the superior performance of fundamental models combined with modern machine learning in predicting future exchange rates in comparison with the results of random walk. These results were examined using a root mean squared error (RMSE) and a Diebold–Mariano (DM) test. The main findings are as follows. First, when comparing the performance of fundamental models combined with machine learning with the performance of random walk, the RMSE results show that the fundamental models with machine learning outperform the random walk. In the DM test, the results are mixed as most of the results show significantly different predictive accuracies compared with the random walk. Second, when comparing the performance of fundamental models combined with machine learning, the models using the producer price index (PPI) consistently show good predictability. Meanwhile, the consumer price index (CPI) appears to be comparatively poor in predicting exchange rate, based on its poor results in the RMSE test and the DM test.

scholarly journals The Quanto Theory of Exchange Rates

2019 ◽  
Vol 109 (3) ◽  
pp. 810-843 ◽  
Author(s):  
Lukas Kremens ◽  
Ian Martin
Keyword(s):  
Random Walk ◽  
Exchange Rates ◽  
Purchasing Power Parity ◽  
Uncovered Interest Parity ◽  
Power Parity ◽  
Panel Regressions ◽  
Out Of Sample ◽  
Covariance Term ◽  
Interest Parity ◽  
Forecast Variable

We present a new identity that relates expected exchange rate appreciation to a risk-neutral covariance term, and use it to motivate a currency forecasting variable based on the prices of quanto index contracts. We show via panel regressions that the quanto forecast variable is an economically and statistically significant predictor of currency appreciation and of excess returns on currency trades. Out of sample, the quanto variable outperforms predictions based on uncovered interest parity, on purchasing power parity, and on a random walk as a forecaster of differential (dollar-neutral) currency appreciation. (JEL C53, E43, F31, F37, G12, G15)

scholarly journals A Simple Out-of-Sample Test of Predictability against the Random Walk Benchmark

Mathematics ◽  
2022 ◽  
Vol 10 (2) ◽  
pp. 228
Author(s):  
Pablo Pincheira ◽  
Nicolas Hardy ◽  
Andrea Bentancor
Keyword(s):  
Monte Carlo ◽  
Random Walk ◽  
Monte Carlo Simulations ◽  
Strong Assumption ◽  
Empirical Application ◽  
Random Walk Hypothesis ◽  
Out Of Sample ◽  
Sample Test ◽  
Commodity Currencies

We show that a straightforward modification of a trading-based test for predictability displays interesting advantages over the Excess Profitability (EP) test proposed by Anatolyev and Gerco when testing the Driftless Random Walk Hypothesis. Our statistic is called the Straightforward Excess Profitability (SEP) test, and it avoids the calculation of a term that under the null of no predictability should be zero but in practice may be sizable. In addition, our test does not require the strong assumption of independence used to derive the EP test. We claim that dependence is the rule and not the exception. We show via Monte Carlo simulations that the SEP test outperforms the EP test in terms of size and power. Finally, we illustrate the use of our test in an empirical application within the context of the commodity-currencies literature.

scholarly journals Re-estimation of Keynesian Model by Considering Critical Events and Multiple Cointegrating Vectors

2015 ◽  
Vol 54 (2) ◽  
pp. 123-145
Author(s):  
Hafsa Hina ◽  
Abdul Qayyum
Keyword(s):  
Exchange Rate ◽  
Random Walk ◽  
Error Correction ◽  
Unit Root ◽  
Dynamic Error ◽  
Correction Model ◽  
Keynesian Model ◽  
Long Run ◽  
Out Of Sample ◽  
Short Run

This study employs the Mundell (1963) and Fleming (1962) traditional flow model of exchange rate to examine the long run behaviour of rupee/US $ exchange rate for Pakistan economy over the period 1982:Q1 to 2010:Q2. This study investigates the effect of output levels, interest rates and prices and different shocks on exchange rate. Hylleberg, Engle, Granger, and Yoo (HEGY) (1990) unit root test confirms the presence of non-seasonal unit root and finds no evidence of biannual and annual frequency unit root in the level of series. Johansen and Juselious (1988, 1992) likelihood ratio test indicates three long-run cointegrating vectors. Cointegrating vectors are uniquely identified by imposing structural economic restrictions on purchasing power parity (PPP), uncovered interest parity (UIP) and current account balance. Finally, the short-run dynamic error correction model is estimated on the basis of identified cointegrated vectors. The speed of adjustment coefficient indicates that 17 percent of divergence from long-run equilibrium exchange rate path is being corrected in each quarter. US war with Afghanistan has significant impact on rupee in short run because of high inflows of US aid to Pakistan after 9/11. Finally, the parsimonious short run dynamic error correction model is able to beat the naïve random walk model at out of sample forecasting horizons. JEL Classification: F31, F37, F47 Keywords: Exchange Rate Determination, Keynesian Model, Cointegration, Out of Sample Forecasting, Random Walk Model

scholarly journals Um Modelo de Fatores Latentes com Variáveis Macroeconômicas para a Curva de Cupom Cambial

2007 ◽  
Vol 5 (1) ◽  
pp. 79 ◽  
Author(s):  
Felipe Pinheiro ◽  
Caio Ibsen Rodrigues de Almeida ◽  
José Valentim Vicente
Keyword(s):  
Random Walk ◽  
Term Structure ◽  
Legendre Polynomials ◽  
Yield Curve ◽  
Factor Model ◽  
Impulse Response Function ◽  
Factor Models ◽  
Latent Factors ◽  
Macroeconomic Variables ◽  
Out Of Sample

Recently, a myriad of factor models including macroeconomic variables have been proposed to analyze the yield curve. We present an alternative factor model where term structure movements are captured by Legendre polynomials mimicking the statistical factor movements identified by Litterman e Scheinkmam (1991). We estimate the model with Brazilian Foreign Exchange Coupon data, adopting a Kalman filter, under two versions: the first uses only latent factors and the second includes macroeconomic variables. We study its ability to predict out-of-sample term structure movements, when compared to a random walk. We also discuss results on the impulse response function of macroeconomic variables.

Sign in / Sign up

Export Citation Format

Share Document