Search Results (36)

Navigating the complexity of petroleum futures markets—marked by extreme volatility, geopolitical uncertainty, and macroeconomic shocks—demands adaptive and risk-sensitive strategies. This paper explores an Adaptive Risk-sensitive Transformer-based Deep Reinforcement Learning (ART-DRL) framework to improve portfolio optimization in commodity futures trading. While deep reinforcement learning (DRL) has been applied in equities and forex, its use in commodities remains underexplored. We evaluate DRL models, including Deep Q-Networks (DQN), Proximal Policy Optimization (PPO), Advantage Actor-Critic (A2C), and Deep Deterministic Policy Gradient (DDPG), integrating dynamic reward functions and asset-specific optimization. Empirical results show improvements in risk-adjusted performance, with an annualized return of 1.353, a Sharpe Ratio of 4.340, and a Sortino Ratio of 57.766. Although the return is below DQN (1.476), the proposed model achieves better stability and risk control. Notably, the models demonstrate resilience by learning from historical periods of extreme volatility, including the COVID-19 pandemic (2020–2021) and geopolitical shocks such as the Russia–Ukraine conflict (2022), despite testing commencing in January 2023. This research offers a practical, data-driven framework for risk-sensitive decision-making in commodities, showing how machine learning can support portfolio management under volatile market conditions. Full article

The prediction of agricultural commodity futures returns is crucial for understanding global economic trends, alleviating inflationary pressures, and optimizing investment portfolios. However, current research that uses full-sample decomposition to predict agricultural futures returns suffers from data leakage, and the resulting forecast bias leads to overly optimistic outcomes. Additionally, previous studies have lacked a comprehensive consideration of key economic variables that influence agricultural prices. To address these issues, this study proposes the “Rolling VMD-LASSO-Mixed Ensemble” forecasting framework and compares its performance with “Rolling VMD” against univariate models, “Rolling VMD-LASSO” against “Rolling VMD”, and “Rolling VMD-LASSO-Mixed Ensemble” against “Rolling VMD-LASSO”. Empirical results show that, on average, “Rolling VMD” improved MSE, MAE, Theil U, ARV, and DA by 3.05%, 1.09%, 1.52%, 2.96%, and 11.11%, respectively, compared to univariate models. “Rolling VMD-LASSO” improved these five indicators by 2.11%, 1.15%, 1.09%, 2.13%, and 1.00% over “Rolling VMD”. The decision tree-based “Rolling VMD-LASSO-Mixed Ensemble” outperformed “Rolling VMD-LASSO” by 1.98%, 0.96%, 1.28%, 2.55%, and 4.18% in the five metrics. Furthermore, the daily average return, maximum drawdown, Sharpe ratio, Sortino ratio, and Calmar ratio based on prediction results also show that “Rolling VMD” outperforms univariate forecasting, “Rolling VMD-LASSO” outperforms “Rolling VMD”, and “Rolling VMD-LASSO-Mixed Ensemble” outperforms “Rolling VMD-LASSO”. This study provides a more accurate and robust forecasting framework for the global agricultural futures market, offering significant practical value for investor risk management and policymakers in stabilizing prices. Full article

This paper explores the hypothesis that the returns of asset classes can be predicted using common, systematic risk factors represented by the level, slope, and curvature of the US interest rate term structure. These are extracted using the Nelson–Siegel model, which effectively captures the three dimensions of the yield curve. To forecast the factors, we applied autoregressive (AR) and vector autoregressive (VAR) models. Using their forecasts, we predict the returns of government and corporate bonds, equities, REITs, and commodity futures. Our predictions were compared against two benchmarks: the historical mean, and an AR(1) model based on past returns. We employed the Diebold–Mariano test and the Model Confidence Set procedure to assess the comparative forecast accuracy. We found that Nelson–Siegel factors had significant predictive power for one-month-ahead returns of bonds, equities, and REITs, but not for commodity futures. However, for 6-month and 12-month-ahead forecasts, neither the AR(1) nor VAR(1) models based on Nelson–Siegel factors outperformed the benchmarks. These results suggest that the Nelson–Siegel factors affect the aggregate stochastic discount factor for pricing all assets traded in the US economy. Full article

This study analyses the impact of the Geopolitical Risk Index (GPR) on the volatility of commodity futures returns from 4 January 2010 to 30 June 2023, using Exponential Generalized Autoregressive Conditional Heteroskedasticity (EGARCH) models. It expands the research scope to include precious metals, agricultural products, energy, and industrial metals. The study differentiates between the impacts of geopolitical threat events and actions using GPRACT and GPRTHREAT indicators. Findings reveal that negative geopolitical shocks increase commodity returns’ volatility more than positive shocks. Specifically, gold, silver, and natural gas are negatively affected, while wheat, corn, soybeans, cotton, zinc, nickel, lead, WTI oil, and Brent oil experience positive effects. Platinum, cocoa, coffee, and copper show no significant impact. These insights highlight the importance of geopolitical risks on commodity market volatility and returns, aiding in risk management and portfolio diversification. Policymakers, financial market stakeholders, and investors can leverage these findings to better understand the GPR’s relationship with commodity markets and develop effective strategies. Full article

This paper examines the dynamic relationships between speculative activities, commodity returns, and macroeconomic conditions across five sectors compassing 29 commodities. Using weekly data spanning from January 2000 to July 2023, we construct comprehensive measures of commodity market speculation across five sectors and examine their sector-specific impact on returns through advanced econometric methods, including dynamic conditional correlation models, quantile regressions, Markov-switching models, and time-varying Granger causality tests. Our results reveal that the impact of speculative activities on commodity futures returns is conditional on the commodity sector and prevailing macroeconomic conditions. Moreover, the relationship between macroeconomic factors, speculative activities, and commodity futures returns is time varying. Among the macroeconomic variables, the financial stress indicator, as measured by the St. Louis Fed Financial Stress Index, shows a significant ability to predict commodity futures returns. The relationship between speculation and commodity returns is bi-directional across all sectors. Full article

This paper analyzes the return performance of various commodity futures-based dynamic portfolios over the period from 31 January 1986 to 31 July 2023. By constructing 30 distinct portfolios categorized by style and performance, we assess their potential for enhancing the performance of traditional portfolios consisting of equity and bonds. We find that most commodity portfolios do not offer statistically significant returns, either in terms of average or risk-adjusted returns. Only the portfolios in the basis category and portfolios in the term structure category exhibit significantly positive risk-adjusted returns, indicating their potential value for portfolio enhancement. The performance of these portfolios is not different in pre-financialization and financialization periods. Full article

The aim of this study is to enhance the understanding of volatility dynamics in commodity returns, such as gold and cocoa, as well as the financial market index S&P500. It provides a comprehensive overview of each model’s efficacy in capturing volatility clustering, asymmetry, and long-term memory effects in asset returns. By employing models like sGARCH, eGARCH, gjrGARCH, and FIGARCH, the research offers a nuanced understanding of volatility evolution and its impact on asset returns. Using the Skewed Generalized Error Distribution (SGED) in model optimization shows how important it is to understand asymmetry and fat-tailedness in return distributions, which are common in financial data. Key findings include the sGARCH model being the preferred choice for Gold Futures due to its lower AIC value and favorable parameter estimates, indicating significant volatility clustering and a slight positive skewness in return distribution. For Cocoa Futures, the FIGARCH model demonstrates superior performance in capturing long memory effects, as evidenced by its higher log-likelihood value and lower AIC value. For the S&P500 Index, the eGARCH model stands out for its ability to capture asymmetry in volatility responses, showing superior performance in both log-likelihood and AIC values. Overall, identifying superior modeling approaches like the FIGARCH model for long memory effects can enhance risk management strategies by providing more accurate estimates of Value-at-Risk (VaR) and Expected Shortfall (ES). Additionally, the out-of-sample evaluation reveals that Support Vector Regression (SVR) outperforms traditional GARCH models for short-term forecasting horizons, indicating its potential as an alternative forecasting tool in financial markets. These findings underscore the importance of selecting appropriate modeling techniques tailored to specific asset classes and forecasting horizons. Furthermore, the study highlights the potential of advanced techniques like SVR in enhancing forecasting accuracy, thus offering valuable implications for portfolio management and risk assessment in financial markets. Full article

Grain is a commodity related to the livelihood of the nation’s people, and the volatility of its futures price affects risk management, investment decisions, and policy making. Therefore, it is very necessary to establish an accurate and efficient futures price prediction model. Aiming at improving the accuracy and efficiency of the prediction model, so as to support reasonable decision making, this paper proposes a Bi-DSConvLSTM-Attention model for grain futures price prediction, which is based on the combination of a bidirectional long short-term memory neural network (BiLSTM), a depthwise separable convolutional long short-term memory neural network (DSConvLSTM), and an attention mechanism. Firstly, the mutual information is used to evaluate, sort, and select the features for dimension reduction. Secondly, the lightweight depthwise separable convolution (DSConv) is introduced to replace the standard convolution (SConv) in ConvLSTM without sacrificing its performance. Then, the self-attention mechanism is adopted to improve the accuracy. Finally, taking the wheat futures price prediction as an example, the model is trained and its performance is evaluated. Under the Bi-DSConvLSTM-Attention model, the experimental results of selecting the most relevant 1, 2, 3, 4, 5, 6, and 7 features as the inputs showed that the optimal number of features to be selected was 4. When the four best features were selected as the inputs, the RMSE, MAE, MAPE, and $R^2$ of the prediction result of the Bi-DSConvLSTM-Attention model were 5.61, 3.63, 0.55, and 0.9984, respectively, which is a great improvement compared with the existing price-prediction models. Other experimental results demonstrated that the model also possesses a certain degree of generalization and is capable of obtaining positive returns. Full article

The aim of this paper is to analyse Bitcoin in order to shed some light on its nature and behaviour. We select 9 cryptocurrencies that account for almost 75% of total market capitalisation and compare their evolution with that of a wide variety of traditional assets: commodities with spot and future contracts, treasury bonds, stock indices, and growth and value stocks. Fractal geometry will be applied to carry out a careful statistical analysis of the performance of Bitcoin returns. As a main conclusion, we have detected a high degree of persistence in its prices, which decreases the efficiency but increases its predictability. Moreover, we observe that the underlying technology influences price dynamics, with fully decentralised cryptocurrencies being the only ones to exhibit self-similarity features at any time scale. Full article

This study analyses a series of live cattle spot and futures prices from the Boi Gordo Index (BGI) in Brazil. The objective is to develop a model that best portrays this commodity’s behaviour to estimate futures prices more accurately. The database created contains 2010 daily entries in which trade in futures contracts occurs, as well as BGI spot sales in the market, from 1 December 2006 to 30 April 2015. One of the most important reasons why this type of risk needs to be measured is to set loss limits. To identify patterns in price behaviour in order to improve future transaction results, investors must analyse fluctuations in asset values for longer periods. Bibliographic research reveals that no other study has conducted a comprehensive analysis of this commodity using this approach. Cattle ranching is big business in Brazil given that in 2021, this sector moved BRL 913.14 billion (USD 169.29 billion). In that year, agribusiness contributed 26.6% of Brazil’s total gross domestic product. Using the proposed risk modelling technique, economic agents can make the best decision about which options within these investors’ reach produce more effective risk management. The methodology is based on Holt–Winters exponential smoothing algorithm, autoregressive integrated moving-average (ARIMA), ARIMA with exogenous inputs, generalised autoregressive conditionally heteroskedastic and generalised autoregressive moving-average (GARMA) models. More specifically, five different methods are applied that allow a comparison of 12 different models as ways to portray and predict the BGI commodity behaviours. The results show that GARMA with order c(2,1) and without intercept is the best model. Investors equipped with such precise modelling insights stand at an advantageous position in the market, promoting informed investment decisions and optimising returns. Full article

The purposes of the research have evidenced the spillover effects of oil-related factors in the oil market and the leading indexes of petrochemical commodities and the bulk shipping markets. The research gap was fitted and explored the effects associated with leading indexes for the shipping and petrochemical markets on the oil market during the US-China trade war, which is seldom bridged with significant relations in the history of oil. The scope of data for the period from 4 January 2016, through 31 August 2022, were analyzed using a generalized autoregressive conditional heteroskedastic mixed data sampling model as methodology of mix frequency to examine volatility spillover of four research hypotheses from the bulk shipping and petrochemical markets to the oil market. Main contributions revealed that spillover from the bulk shipping and petrochemical commodity markets transmitted significant volatility to West Texas Intermediate (WTI) oil returns after the US-China trade war began, a trend that has continued throughout the COVID-19 era until Ukraine–Russia war. These rare events indicate that the realized volatility derived from these market variables can be used to track the more significant contagions on WTI futures volatility in this empirical research than the weak relation in past studies. Full article

In the turbulent landscape of financial markets, Bitcoin has emerged as a significant focus for investors due to its highly volatile returns. However, the risks and uncertainties associated with it necessitate effective hedging strategies. This paper explores the potential of various financial assets, including interest rates, stock markets, commodities, and exchange rates, as dynamic hedges against Bitcoin’s risk. Utilizing a DCC-GARCH model, we construct a dynamic hedging model to analyze the viability of these financial assets as hedges. The data is categorized into pre-pandemic and pandemic periods to assess any change in hedging performance due to the outbreak of COVID-19. Our empirical findings suggest that the dynamic DCC-GARCH model outperforms the static OLS model in this context. During the pandemic period, a diverse set of financial assets demonstrated enhanced efficiency in hedging Bitcoin risk compared to the pre-pandemic phase. Among the hedging commodities, stock market indices, the US dollar index, and commodity futures displayed superior performance. Full article

This paper investigates the heterogeneous dependence between global crude oil futures and China’s biofuel feedstock commodities under different market conditions. Quantile-on-quantile regression and the causality-in-quantiles test are employed to capture comprehensive and informative relationships. The empirical results are as follows: First, there is a positive relationship between the returns on China’s biofuel feedstock commodities and crude oil. The effects are heterogeneous, conditional on the market regimes, where the impacts of the bearish/bullish crude oil market on biofuel feedstock commodity returns are significant when the commodity market in China is in a bearish/bullish state. Second, crude oil returns have reliable predictive power for the returns on China’s biofuel feedstock commodities under the average market condition and move in connection with the volatility of China’s biofuel-related commodity market in normal and bullish market conditions. Third, the risk reduction effectiveness of soybean and corn is significant, while for wheat, this reduction in portfolio risk is less apparent and enhanced, and the risk reduction effectiveness increases significantly during financial and oil crises. Overall, our findings will be helpful in understanding the heterogeneous interplay between global oil and China’s biofuel-related commodities and in evaluating portfolio diversification opportunities under different market conditions. Full article

Atlantic bluefin tuna (Thunnus thynnus) is the most important tuna species in Mediterranean tuna fishery and a valuable commodity on the global fish market. Croatia is a pioneer in tuna farming in the Mediterranean and the only country that has the exclusive right to farm wild-caught juvenile tuna (8 to 30 kg). This paper identifies key challenges to the sustainability of current farming and fattening practices, primarily economic and environmental, and possible solutions to overcome these challenges. This paper analyses data on tuna catch and aquaculture production (FAO FishStatJ and EU-Eurostat database) and updates the latest literature on farming practices, production challenges related to biotechnical, economic and environmental issues, the market and current legislation in Croatia, as well as fattening in other Mediterranean countries. Tuna capture-based aquaculture is attractive to investors because it promises high returns, but the sustainability of intensive tuna farming and fattening is questionable and raises many ethical issues. Tuna farming and fattening relies on wild fish for stocking and feeding, and further expansion of tuna farming and fattening is limited by the size of wild tuna and small fish populations. To meet the growing global demand for tuna and to conserve wild tuna stocks, further investments are needed. The knowledge gained in Croatian tuna farming is valuable for future sustainable close-cycled tuna farming in the Mediterranean. Due to its good environmental status, the availability of small pelagic fish, the availability of a highly qualified and well-organised labour force, the good cooperation between producers and researchers, and the application of modern farming technologies, ABFT farmed in Croatia have high quality and a good reputation on the market. The main weakness of Croatian tuna farming is that the entire industry is dependent on the Japanese market, but this can be overcome by the possibility of product diversification for new markets, including the tourism industry. Full article

This study investigated how stock market volatility responded dynamically to unexpected changes during the COVID-19 pandemic and the resulting uncertainty in Thailand. Using a multivariate GARCH-BEKK model, the conditional volatility dynamics, the interlinkages, and the conditional correlations between stock market volatility and the increasing rate of COVID-19 infection cases are examined. The increased rate of COVID-19 infections impacts stock returns detrimentally; in Thailand, stock market volatility responses are asymmetric in the increase and decline situations. This disparity is due to the unfavourable impact of the pandemic’s volatility. Finally, we acknowledge that directional volatility spillover effects exist between the increase in COVID-19 cases and stock returns, suggesting that time-varying conditional correlations occur and are generally positive. Using this study’s results, governments and financial institutions can devise strategies for subsequent recessions or financial crises. Furthermore, investment managers can manage portfolio risk and forecast patterns in stock market volatility. Academics can apply our methodology in future investment trend studies to analyse additional variables in the economic system, such as the value of the US dollar, the price of commodities, or GDP. Full article