Journal of Futures Markets最新文献

This paper investigates the ability of a ChatGPT-based indicator to forecast excess returns of the commodity futures index. Using ChatGPT to extract information from over 2.5 million articles from nine international newspapers, we demonstrate that our constructed commodity news ratio index significantly predicts future commodity returns, both in-sample and out-of-sample. Furthermore, it outperforms traditional textual analysis methods, including Bidirectional Encoder Representations from Transformers (BERT) and Bag-of-Words (BoW), while indicating economic significance within an asset allocation framework. The results highlight the critical role of ChatGPT in forecasting commodity market dynamics and provide valuable insights for both financial market participants and researchers.

This paper proposes that the tail risk associated with commodity futures returns performs well at predicting the S&P 500 index futures returns in- and out-of-sample, even after controlling business cycles, economic factors, investor sentiment factors, other forms of tail risk factors, and macroeconomic conditions. Following Kelly and Jiang (2014), we directly estimate the commodity tail risk factor from the cross-section of commodity futures returns, which can efficiently capture the prevailing level of tail risk in the cross-sectional distribution. Our empirical analysis involves forecasting regressions, which aim to predict index futures returns using lagged up-tail risk, down-tail risk, and overall tail risk. We uncover asymmetric forecasting power between up-tail risk and down-tail risk, highlighting their distinct influences. Notably, our return decomposition analysis shows that the commodity tail risk factors primarily drive index futures returns through the discount rate channel.

This study investigates the performance of USD interest rate swaption straddle strategies during the unconventional monetary policy and pandemic eras. We construct long–short portfolio swaption straddles using longer tenors and maturities than those in the previous literature. Moreover, we propose an equally weighted strategy that takes risk exposures to both volatility and jump risks. This strategy generates a higher Sharpe ratio than the delta–gamma neutral strategy during the unconventional monetary policy period. This result is weakly associated with spot swap forward rate jumps and robust, including transaction costs. We also observe that adopting longer maturity swaptions in the long position leads to higher values of risk and returns.

A latent-factor model based on the instrumented principal component analysis (IPCA) methodology of Kelly et al. outperforms existing factor models in explaining cross-sectional variations in commodity futures returns. The model allows for observed commodity futures characteristics to work as instruments for unobservable dynamic factor loadings. We find that the relationship between characteristics and commodity futures returns is driven by compensation for exposure to latent risk factors (beta) rather than compensation for exposure to mispricing (alpha). Three latent factors deliver more powerful explanations than any number of observable factors. Among a collection of 20 characteristics, only three are significantly related to latent factor betas. These three characteristics are momentum, expected shortfall, and idiosyncratic volatility.

We present a model to explain the diversification benefits of incorporating commodities into a portfolio of traditional assets from the perspective of domestic investors. Utilizing a sample of 38 countries from 2000 to 2020, we show that investors in high-commodity dependence countries generally do not benefit from adding commodities to their portfolios while investors located in low-commodity dependence countries usually do. Our results thus show that local contexts matter and that commodities may augment a diversified portfolio if investors are not excessively exposed to commodity risk through their country's economic structure.

This paper investigates the interdependence between economic policy uncertainty (EPU) and implied market volatility using a Bayesian copula network. The results indicate that market-implied volatilities serve as more reliable forward-looking indicators of uncertainty compared to newspaper-based EPU. Through a complex partial wavelet coherence approach, the study further explores the dynamic interdependence between these variables, revealing the specific time-domain patterns of their effects on economic uncertainty and the conditions under which they can be distinguished as measures of risk aversion and ambiguity aversion. Notably, the findings suggest that, in the short time scales, the media tends to generate ambiguity, contributing to belief divergence among market participants. However, over longer time scales, EPU increasingly reflects economic uncertainty. These insights are valuable for gaining a deeper understanding of the media's role in conveying information and the behavioral traits influencing economic decision-making.

We apply the regression-based affine term structure model to estimate the term structure of commodity futures. This model is advantageous in that it has a simple and fast algorithm, can accommodate a variety of observable and unspanned factors, and can be applied to daily and even real-time observations. The results show that the model appropriately captures time-series variations across different maturities and exhibits satisfactory performance in capturing cross-sectional variations for specific months. Furthermore, we investigate the relationship between the existing commodity risk factor returns and the risk premiums inferred by the model. Our analysis reveals that different risk factor returns explain the spot and term premiums differently. Therefore, using the advantages of the model, we can better understand the term structure and risk premiums in commodity futures.