Volatility forecasting in commodity markets using macro uncertainty

Bakas, Dimitrios; Triantafyllou, Aggeliki

doi:10.1016/j.eneco.2019.03.016

Cited by 63 publications

(14 citation statements)

References 67 publications

(111 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides these commodity‐specific factors, commodity markets are also well known to be affected by macroeconomic factors. Bakas and Triantafyllou (2019) find that the latent macroeconomic uncertainty measure is a common volatility forecasting factor for commodity markets. However, there is still debate about the predictability of risk factors since previous studies have shown mixed results, examples include Daskalaki et al (2014), Fernandez‐Perez et al (2018), and others.…”

Section: Introductionmentioning

confidence: 99%

Predictability of commodity futures returns with machine learning models

Wang,

Zhang

2023

Journal of Futures Markets

View full text Add to dashboard Cite

We use prevailing machine learning models to investigate the predictability of futures returns in 22 commodities with commodity‐specific and macroeconomic factors as predictors. Out‐of‐sample prediction errors for the majority of futures contracts are lowered compared with those obtained by the baseline models of AR(1) and forecast combinations. Using Shapley values to explain feature importance, we identify dominant predictors for each commodity. A long–short portfolio strategy based on monthly light gradient‐boosting machine predictions outperforms the benchmark linear models in terms of annual return, Sharpe ratio, and max drawdown.

show abstract

Section: Introductionmentioning

confidence: 99%

Predictability of commodity futures returns with machine learning models

Wang,

Zhang

2023

Journal of Futures Markets

View full text Add to dashboard Cite

show abstract

“…However, these models are based on time‐series data, ignoring the significance of external influencing factors, such as extreme weather, emergencies, and sentiment in agricultural markets. Moreover, the measurement of these factors is still an open question (Adämmer & Bohl, 2018; Ahumada & Cornejo, 2016a; Bakas & Triantafyllou, 2019).…”

Section: Introductionmentioning

confidence: 99%

Text‐based soybean futures price forecasting: A two‐stage deep learning approach

Wang

Zeng

2022

Journal of Forecasting

View full text Add to dashboard Cite

This paper investigates the soybean futures price prediction problem from a new perspective and proposes an effective prediction model named Two‐Stage Hybrid Long Short‐Term Memory (TSH‐LSTM) by using text data from social media. First, the unstructured text is transformed into structured data by sentiment analysis and text classification methods. The improved sentiment score is computed by combining the degree centrality of sentiment words based on the sentiment dictionary method, and the characteristics of price fluctuations in texts are learned through the text Recurrent Convolutional Neural Networks. Second, the significant relationship between social media features and soybean futures price is assessed through stepwise regression, and the results of such an assessment are used as a basis for the identification of significant factors as input variables of the prediction model. Finally, the TSH‐LSTM prediction model is designed, and the final prediction result is acquired through the combination of prediction results of each stage using the error reciprocal method. The empirical results indicate that the incorporation of the social media text feature helps improve forecasting performances. Specifically, the proposed TSH‐LSTM is more accurate than univariate LSTM, multivariate LSTM, and eXtreme Gradient Boosting.

show abstract

“…For example, Ma et al (2018) find that the EPU index has significant predictive power for oil volatility out-of-sample. Bakas and Triantafyllou (2019) indicate that macro uncertainty generates significant predictive power for oil volatility, and Mei et al (2020) and Liu et al (2021) reveal that geopolitical risk improves oil volatility prediction. Therefore, the estimated conditional variance derived from uncertainty information will have smaller biases from the true but unobservable volatility of oil prices.…”

Section: Introductionmentioning

confidence: 99%

Uncertainty‐driven oil volatility risk premium and international stock market volatility forecasting

Tong

Miao

et al. 2022

Journal of Forecasting

View full text Add to dashboard Cite

Forecasting international stock market volatility using the oil volatility risk premium (OVRP) is important for asset allocation and financial risk management. In previous literature, the issue of biased OVRP has not been well addressed. The OVRP is defined as the difference between the ex ante risk‐neutral expectation of oil return variation and the oil realized variance. This is a biased estimator as argued by previous studies. In this paper, we propose a new measure of OVRP, namely, the uncertainty‐driven OVRP (UOVRP), in which the expected realized variation is the conditional variance of oil futures returns estimated by a typical GARCH‐MIDAS model, and the long‐term volatility component of conditional variance is directly determined by several uncertainty indices. Using heterogeneous autoregressive models (HAR), we find that UOVRPs significantly and positively predict most of the international stock market volatility in‐sample. Furthermore, it significantly outperforms the realized volatility, the “model‐free” OVRP, and recently proposed volatility predictors for most American, European, and Pacific markets out‐of‐sample. On average, UOVRPs driven by the world uncertainty index and the U.S. economic policy uncertainty perform the best among all UOVRPs. The predictive ability of UOVRPs is robust across a series of checks.

show abstract

Volatility forecasting in commodity markets using macro uncertainty

Cited by 63 publications

References 67 publications

Predictability of commodity futures returns with machine learning models

Predictability of commodity futures returns with machine learning models

Text‐based soybean futures price forecasting: A two‐stage deep learning approach

Uncertainty‐driven oil volatility risk premium and international stock market volatility forecasting

Contact Info

Product

Resources

About