Forecasting stock market volatility with various geopolitical risks categories: New evidence from machine learning models

This paper investigates how geopolitical risks influence the prediction performance on the US stock market volatility with machine learning models. Further, it compares the predictive performance of individual and combination forecast methods. With SHAP algorithm, it could identify which factor has a great impact and fully extract the information of geopolitical risks in predicting. Empirical results show that military build-ups and escalation of war have great importance on predicting realized volatility among various geopolitical risks. The research further emphasizes the superior performance of machine learning and forecast combination methods, especially SVR method and trimmed mean combination. In addition, by allocating portfolio according to the machine learning-based volatility forecasts, particularly elastic net and random forest, a mean-variance investor can achieve sizeable financial benefits. Our paper provides substantial implications for political risk management and volatility forecasting.     

国际金融市场与国际原油期货市场溢出效应实证检验——基于VAR-BEKK模型的分析

文章通过构建VAR模型和BEKK模型对道琼斯股票市场、美元/欧元汇率市场与国际原油期货市场的动态关系进行了实证检验。结果表明：道琼斯股票市场与WTI原油期货市场存在双向的价格溢出效应,以及前者向后者的单向波动溢出效应;美元/欧元汇率市场存在向WTI原油期货市场单向的价格溢出效应和波动溢出效应。所以,国际原油期货市场与国际金融市场联系紧密,国际原油的金融属性日益体现,其价格变动更多受外部国际金融市场风险影响。     

Generative Bayesian neural network model for risk-neutral pricing of American index options

Financial models with stochastic volatility or jumps play a critical role as alternative option pricing models for the classical Black–Scholes model, which have the ability to fit different market volatility structures. Recently, machine learning models have elicited considerable attention from researchers because of their improved prediction accuracy in pricing financial derivatives. We propose a generative Bayesian learning model that incorporates a prior reflecting a risk-neutral pricing structure to provide fair prices for the deep ITM and the deep OTM options that are rarely traded. We conduct a comprehensive empirical study to compare classical financial option models with machine learning models in terms of model estimation and prediction using S&P 100 American put options from 2003 to 2012. Results indicate that machine learning models demonstrate better prediction performance than the classical financial option models. Especially, we observe that the generative Bayesian neural network model demonstrates the best overall prediction performance.     

The impact of institutional analyst forecast divergence on crude oil market: Evidence from the mixed frequency models

As important information intermediaries, analysts play a non-negligible role in the crude oil market. Existing research often focuses on analysts' collection and interpretation of firm-specific information, but neglects the impact of analysts' forecasts on specific markets such as the crude oil market, which is crucial to the safe and stable development of the crude oil market. Therefore, this study uses historical data from January 2011 to December 2020 as a sample to construct analysts' forecast divergence indicators from 15 institutional analysts' forecast data on international crude oil futures prices. It then explores the impact of institutional analysts' forecast divergence on oil price return volatility, crude oil market jumps and crude oil futures trading volume, based on various mixed-frequency models. The results are as follows: First, volatility in oil price returns increases with a growing divergence in analysts' forecasts. Second, analysts' forecasts do not trigger jump in the crude oil market on the first six days after the information is released, but trigger a significant positive jump in the market on the seventh day. Third, the impact of analysts' forecast divergence on trading volume is weak; however, the reverse effect is significant, while the static and dynamic spillover results are consistent.     

Futures volatility forecasting based on big data analytics with incorporating an order imbalance effect

Future markets play vital roles in supporting economic activities in modern society. For example, crude oil and electricity futures markets have heavy effects on a nation’s energy operation management. Thus, volatility forecasting of the futures market is an emerging but increasingly influential field of financial research. In this paper, we adopt big data analytics, called Extreme Gradient Boosting (XGBoost) from computer science, in an attempt to improve the forecasting accuracy of futures volatility and to demonstrate the application of big data analytics in the financial spectrum in terms of volatility forecasting. We further unveil that order imbalance estimation might incorporate abundant information to reflect price jumps and other trading information in the futures market. Including order imbalance information helps our model capture underpinned market rules such as supply and demand, which lightens the information loss during the model formation. Our empirical results suggest that the volatility forecasting accuracy of the XGBoost method considerably beats the GARCH-jump and HAR-jump models in both crude oil futures market and electricity futures market. Our results could also produce plentiful research implications for both policy makers and energy futures market participants.     

Dynamic volatility spillovers across oil and natural gas futures markets based on a time-varying spillover method

This paper analyzes dynamic volatility spillovers between four major energy commodities (i.e., crude oil, gasoline, heating oil and natural gas) in the oil-natural gas future markets. We construct a time-varying spillover method by combining the TVP-VAR-SV model and the spillover method of Diebold and Yilmaz (2009, 2012, 2014). We use the spillover method to obtain time-varying total, directional and pairwise volatility spillover indices. Our results summarize as follows: (1) The volatility spillover indices present peaks and troughs during some periods, such as shale gas revolution, financial crisis, and oil price crash; (2) After the U.S. shale gas revolution, the size of volatility spillover from natural gas future market has reduced sharply, but volatility doesn't decouple from the other three oil future markets; (3) The directional spillover is asymmetric. The crude oil and heating oil futures market are main net transmitter of volatility risk information, while the gasoline and natural gas futures markets are the net receiver; (4) For natural gas future market, the pairwise volatility spillover from crude oil future market has the most significant influence.     

The role of gold futures in mitigating the impact of economic uncertainty on spot prices: Evidence from China

This paper studies the co-integration relationship and volatility spillover effect between China's gold futures and spot prices through the VECM-BEKK-GARCH model. Then, MSGARCH and DCCE-GARCH are applied to study the relationship among China's gold futures market, spot market price volatility and the stabilization effect in uncertain economic environments. This paper enriches the current research, providing gold market participants with hints to address economic uncertainty. The empirical results show that China's gold futures market has a weak stabilization effect on spot price volatility. In scenarios with uncertain economic information and uncertain macroeconomic changes, the correlation between gold futures and spot price volatility is reduced in China, and the role of gold futures in stabilizing the spot price weakens. Furthermore, with economic uncertainty, the fluctuation range of the gold futures price is greater than that of the spot price, with a tendency of more frequent fluctuations. This also means that the effectiveness of the futures market in regulating the spot price will be reduced, and gold market regulators need to stabilize the market through alternative methods to futures.     

Information connectedness of international crude oil futures: Evidence from SC,WTI, and Brent

The first Yuan (RMB) denominated crude oil futures contract, SC, was launched in the Shanghai International Energy Exchange (INE) on 26 March 2018, which is extremely meaningful for China and other Asian countries by offering a new option of oil price risk management. To identify the information connectedness among this emerging contract and those mature WTI and Brent oil futures, we provide return and volatility directional connectedness evidence among them in both the time and frequency domains. The empirical results show that, firstly the three oil futures of SC, WTI, and Brent present high degree of total connectedness in the return and volatility series, implying tight information transfer among them. Secondly, the net directional connectedness results suggest that the SC can provide competitive information on oil returns and is a net and powerful contributor to volatility shocks. In addition, from a frequency-specific perspective, we find that the SC appears to be not only a net transmitter of return shocks on the medium- and long-term frequencies but also a net transmitter of volatility shocks consistently across the whole frequency ranges. The overall evidence suggests that China's new oil futures is an active participant in the international oil futures market, and may become an important product in information transmission across international crude oil futures markets by providing effective hedging instrument for crude oil producers, refiners, consumers, and investors, especially those in Asia.     

Returns and volatilities of energy futures markets: Roles of speculative and hedging sentiments

This study examines how speculative and hedging sentiments influence the returns and volatilities of energy futures markets. We construct speculative and hedging sentiment indices based on the weekly data of fund and commercial positions of four energy futures: crude oil, heating oil, gasoline, and natural gas, traded on the New York Mercantile Exchange (NYMEX) from 15 January 2013 to 5 February 2019. Our study demonstrates that speculative sentiment generates greater market fluctuations in the energy futures markets than hedging sentiment; and, further, speculative sentiment stimulates a reversal effect on the returns of crude oil futures. Moreover, speculative sentiment exerts positive systemic risk compensation on the four futures' returns, whereas hedging sentiment alleviates volatilities in the energy futures markets. Most notably, distinguishing it from the leverage effect in stock markets, the speculative sentiment in the energy futures markets is influenced more by good than by bad news; while hedging sentiment exhibits emotional neutrality, as opposed to its impact on stock markets as reported in the literature. Additionally, the positive hedging sentiment in crude oil futures demonstrates significant systemic risk compensation, whereas the three other futures do not have an influence, confirming the prevalence of speculation in hedging transactions in crude oil futures. Our further analysis shows cross-market volatility spillover effects, among which speculative sentiment inherent in crude oil futures causes volatility spillovers to the three other futures, while hedging sentiment has no such effect. Our study has implications for overseeing international energy futures markets, providing regulators with evidence that will facilitate the development of effective strategies to strengthen market supervision.     

Volatility forecasting in the Chinese commodity futures market with intraday data

Given the unique institutional regulations in the Chinese commodity futures market as well as the characteristics of the data it generates, we utilize contracts with three months to delivery, the most liquid contract series, to systematically explore volatility forecasting for aluminum, copper, fuel oil, and sugar at the daily and three intraday sampling frequencies. We adopt popular volatility models in the literature and assess the forecasts obtained via these models against alternative proxies for the true volatility. Our results suggest that the long memory property is an essential feature in the commodity futures volatility dynamics and that the ARFIMA model consistently produces the best forecasts or forecasts not inferior to the best in statistical terms.     

Evaluating the performance of futures hedging using factors-driven realized volatility

The complexity and uncertainty of the financial market mainly stem from the rich market internal transaction information and a wide range effect of external factors. To this end, this paper proposes the combination factors-driven forecasting method to predict realized volatilities of the CSI 300 index and index futures. Based on the volatilities predicted by the proposed method, we further evaluate the ex-ante hedging performance in comparison to the conventional HAR model as well as GARCH-type models. The empirical results indicate that the factors-driven realized volatility model significantly dominates the other commonly used models in terms of hedging effectiveness. Furthermore, the superiority of the proposed method is robust in different market conditions, including significant rising or falling and abnormal market fluctuations in the COVID-19 pandemic, and in different index markets. Therefore, this paper improves the prediction accuracy of volatility by integrating market internal transaction information and external factor information, and the proposed method in this paper can be used by investors to obtain an excellent hedging effect.     

Initial margin policy and stochastic volatility in the crude oil futures market

This article examines the relationship between the volatilityof the crude oil futures market and changes in initial marginrequirements. To closely match changes in futures market volatilitywith the corresponding changes in margin requirements, we inferthe volatility of the futures market from the prices of crudeoil futures options contracts. Using a mean-reverting diffusionprocess for volatility, we show that changes in margin policydo not affect subsequent market volatility.     

A Likelihood Ratio Test of Price Volatilities: Comparing Stock Index Spot and Futures

This paper uses three methods to estimate the price volatility of two stock market indexes and their corresponding futures contracts. The classic variance measure of volatility is supplemented with two newer measures, derived from the Garman-Klass and Ball-Torous estimators. A likelihood ratio test is used to compare the classic variance measure of price volatilities of two stock market indexes and their corresponding futures contracts during the bull market of the 1980s. The stock market volatilities of the Standard & Poor's 500 (S&P 500) and New York Stock Exchange (NYSE) indexes were found to be significantly lower than their respective futures price volatilities. Since information may flow faster in the futures markets than in the corresponding stock market, our results support Ross's information-volatility hypothesis. It was also noted that the NYSE spot volatility was lower than the S&P 500 spot volatility. If the rate of information flow and firm size are positively related, then the lower NYSE spot volatility is explained by the size effect. The futures price volatilities for the two indexes were insignificantly different from each other. With stock index spot-futures price correlations approaching unity, one implication of our results for index futures activity is that smaller positions in futures contracts may suffice to achieve hedging or arbitrage goals.     

Volatility forecasting of crude oil futures market: Which structural change-based HAR models have better performance?

The paper focuses on the smooth and sharp structural changes in crude oil futures volatility and singles out the flexible Fourier form (FFF) and the modified ICSS algorithm to detect them, respectively, so as to explore whether different structural change-based HAR models exhibit significantly better performance for crude oil return volatility forecasting than traditional HAR-type models. The empirical results indicate that, on the one hand, crude oil market displays a strong evidence of breaks, and the incorporation of trigonometric terms can account for the structural changes in crude oil return volatility. On the other hand, the flexible Fourier form (FFF) based HAR-type models and the Structural Breakpoints (SB) based HAR-type models yield superior forecasting performance than traditional HAR-type models. Meanwhile, the forecasting results and economic performance of the former usually outperform the latter, particularly for the short- and medium-term forecasts.     

The hedging effect of green bonds on carbon market risk

This paper explores effective hedging instruments for carbon market risk. Examining the relationship between the carbon futures returns and the returns of four major market indices, i.e., the VIX index, the commodity index, the energy index and the green bond index, we find that the connectedness between the carbon futures returns and the green bond index returns is the highest and this connectedness is extremely pronounced during the market's volatile period. Further, we develop and evaluate hedging strategies based on three dynamic hedge ratio models (DCC-APGARCH, DCC-T-GARCH, and DCC-GJR-GARCH models) and the constant hedge ratio model (OLS model). Empirical results show that among the four market indices the green bond index is the best hedge for carbon futures and performs well even in the crisis period. The paper also provides evidence that the dynamic hedge ratio models are superior to the OLS model in the volatile period as more sophisticated models can capture the dynamic correlation and volatility spillover between the carbon futures and market index returns.     

A regime-switching real-time copula GARCH model for optimal futures hedging

A regime-switching real-time copula GARCH (RSRTCG) model is suggested for optimal futures hedging. The specification of RSRTCG is to model the margins of asset returns with state-dependent real-time GARCH and the dependence structure of asset returns with regime switching copula functions. RSRTCG is faster in adjusting to the new level of volatility under different market regimes which is a regime-switching multivariate generalization of the state-independent univariate real-time GARCH. RSRTCG is applied to cross hedge the price risk of S&P 500 sector indices with crude oil futures. The empirical results show that RSRTCG possesses superior hedging performance compared to its nested non-real-time or state-independent copula GARCH models based on the criterion of percentage variance reduction, utility gain, model confidence set, model combination strategy, risk-adjusted return and reward-to-semivariance ratio.     

Calibrating a market model with stochastic volatility to commodity and interest rate risk

Based on the multi-currency LIBOR Market Model, this paper constructs a hybrid commodity interest rate market model with a stochastic local volatility function allowing the model to simultaneously fit the implied volatility surfaces of commodity and interest rate options. Since liquid market prices are only available for options on commodity futures, rather than forwards, a convexity correction formula for the model is derived to account for the difference between forward and futures prices. A procedure for efficiently calibrating the model to interest rate and commodity volatility smiles is constructed. Finally, the model is fitted to an exogenously given correlation structure between forward interest rates and commodity prices (cross-correlation). When calibrating to options on forwards (rather than futures), the fitting of cross-correlation preserves the (separate) calibration in the two markets (interest rate and commodity options), while in the case of futures a (rapidly converging) iterative fitting procedure is presented. The fitting of cross-correlation is reduced to finding an optimal rotation of volatility vectors, which is shown to be an appropriately modified version of the ‘orthonormal Procrustes’ problem in linear algebra. The calibration approach is demonstrated in an application to market data for oil futures.     

Currency futures market in India: an empirical analysis of market efficiency and volatility

As the Indian currency futures market has been in existence for over 7 years, this paper analyses the effectiveness of the 1-month USD/INR currency futures rates in predicting the expected spot rate. The volatility of the USD/INR spot returns was also analysed. Modelling volatility of the USD/INR spot rate using a generalized autoregressive conditional heteroskedasticity (GARCH) and exponential generalized autoregressive conditional heteroskedasticity (EGARCH) model indicated the presence of volatility clustering. Using multivariate GARCH models such as the constant conditional correlation and dynamic conditional correlation, signs of a volatility spillover between the USD/INR spot and currency futures market were also observed.     

股指期货是股灾的“幕后推手”吗——基于2015年股灾期间沪深300股指期货高频数据实证分析

选取2015年6月15日至8月26日股灾期间沪深300股指期货与沪深300指数5分钟高频数据,通过E-G两步协整检验、格兰杰因果检验、脉冲响应模型等,对股灾期间股指期货市场价格发现功能及波动溢出效应进行实证研究.结果表明:股灾期间沪深300股指期货仍具备价格发现功能,但存在对现货市场的单向波动溢出,具有一定的"助跌"效应.     

Investor Attention and Time‐varying Comovements

This paper analyses the effect of an increase in market‐wide uncertainty on information flow and asset price comovements. We use the daily realised volatility of the 30‐year treasury bond futures to assess macroeconomic shocks that affect market‐wide uncertainty. We use the ratio of a stock's idiosyncratic realised volatility with respect to the S&P500 futures relative to its total realised volatility to capture the asset price comovement with the market. We find that market volatility and the comovement of individual stocks with the market increase contemporaneously with the arrival of market‐wide macroeconomic shocks, but decrease significantly in the following five trading days. This pattern supports the hypothesis that investors shift their (limited) attention to processing market‐level information following an increase in market‐wide uncertainty and then subsequently divert their attention back to asset‐specific information.