Pub Date : 2024-11-14DOI: 10.1016/j.jcomm.2024.100447
Qiao Wang
This paper examines whether the carbon pricing risk factor is priced in the cross-section of commodity futures. By analyzing unexpected pricing shocks in carbon emission allowances, carbon pricing risk is indeed priced in commodity futures, with a significant positive risk premium. The analysis of carbon pricing risk loadings reveals that individual commodities' sensitivities to carbon pricing risk vary. Additionally, commodity-specific characteristics, such as basis and hedging pressure, impact these risk loadings. Finally, I demonstrate that a portfolio of commodity futures constructed based on carbon pricing beta provides superior out-of-sample hedging performance for climate change risk compared to alternative hedge portfolios using equities or ETFs.
{"title":"Carbon pricing and the commodity risk premium","authors":"Qiao Wang","doi":"10.1016/j.jcomm.2024.100447","DOIUrl":"10.1016/j.jcomm.2024.100447","url":null,"abstract":"<div><div>This paper examines whether the carbon pricing risk factor is priced in the cross-section of commodity futures. By analyzing unexpected pricing shocks in carbon emission allowances, carbon pricing risk is indeed priced in commodity futures, with a significant positive risk premium. The analysis of carbon pricing risk loadings reveals that individual commodities' sensitivities to carbon pricing risk vary. Additionally, commodity-specific characteristics, such as basis and hedging pressure, impact these risk loadings. Finally, I demonstrate that a portfolio of commodity futures constructed based on carbon pricing beta provides superior out-of-sample hedging performance for climate change risk compared to alternative hedge portfolios using equities or ETFs.</div></div>","PeriodicalId":45111,"journal":{"name":"Journal of Commodity Markets","volume":"36 ","pages":"Article 100447"},"PeriodicalIF":3.7,"publicationDate":"2024-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142651526","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-13DOI: 10.1016/j.jcomm.2024.100446
Alexander Kurov , Eric Olson , Marketa Halova Wolfe
We reexamine the contemporaneous causal effects between the U.S. stock prices, crude oil prices, and monetary policy from 2005 to 2022. Our study offers two main contributions. First, we generalize a novel identification approach based on exogenous intraday shifts in the volatility in futures markets from two markets to multiple markets. Second, we examine contemporaneous causal effects between the U.S. stock prices, crude oil prices, and monetary policy. We show that the coefficients measuring contemporaneous causality have substantially changed over time. Specifically, we find that since 2008 stock returns affect crude oil returns. This time variation is also evident in the effect of monetary policy on the crude oil returns. We show that this time variation is consistent with two explanations: the zero lower bound (ZLB) and increased synchronization of crude oil prices with the business cycle.
{"title":"Have the causal effects between equities, oil prices, and monetary policy changed over time?","authors":"Alexander Kurov , Eric Olson , Marketa Halova Wolfe","doi":"10.1016/j.jcomm.2024.100446","DOIUrl":"10.1016/j.jcomm.2024.100446","url":null,"abstract":"<div><div>We reexamine the contemporaneous causal effects between the U.S. stock prices, crude oil prices, and monetary policy from 2005 to 2022. Our study offers two main contributions. First, we generalize a novel identification approach based on exogenous intraday shifts in the volatility in futures markets from two markets to multiple markets. Second, we examine contemporaneous causal effects between the U.S. stock prices, crude oil prices, and monetary policy. We show that the coefficients measuring contemporaneous causality have substantially changed over time. Specifically, we find that since 2008 stock returns affect crude oil returns. This time variation is also evident in the effect of monetary policy on the crude oil returns. We show that this time variation is consistent with two explanations: the zero lower bound (ZLB) and increased synchronization of crude oil prices with the business cycle.</div></div>","PeriodicalId":45111,"journal":{"name":"Journal of Commodity Markets","volume":"36 ","pages":"Article 100446"},"PeriodicalIF":3.7,"publicationDate":"2024-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142651525","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-08DOI: 10.1016/j.jcomm.2024.100442
Ingrid Emilie Flessum Ringstad , Kyriaki Tselika
In this paper, we investigate the time and frequency dynamics of connectedness among green assets such as green bonds, clean energy markets, and carbon prices. Using daily price data, we explore return spillovers across these green financial markets by applying the novel framework on time and frequency dynamics proposed by Baruník and Krehlík (2018). This allows us to identify the direction of spillovers among our variables, and decompose the connectedness to differentiate between short-term and long-term return spillovers. Our results indicate that green bonds and carbon prices act as net receivers of shocks, but mainly in the short-term. We also observe a low level of connectedness among our clean energy markets across both low and high frequency bands, even during times of economic or political crisis. Additionally, there are periods in which connectedness between the clean energy assets is driven by the long-term. In periods of economic and political stability, carbon prices may also provide an interesting diversifying tool for short-term investors. Our results should be of interest for investors and portfolio managers who focus on green financial markets, by strengthening the notion that green financial markets can offer diversification opportunities, for both short-term and long-term investors. Policy makers could also benefit from our insights on conectedness in their work on short-term and long-term climate policies. This paper is the first to use this framework to investigate systematic risks within green financial markets.
{"title":"Connectedness between green bonds, clean energy markets and carbon quota prices: Time and frequency dynamics","authors":"Ingrid Emilie Flessum Ringstad , Kyriaki Tselika","doi":"10.1016/j.jcomm.2024.100442","DOIUrl":"10.1016/j.jcomm.2024.100442","url":null,"abstract":"<div><div>In this paper, we investigate the time and frequency dynamics of connectedness among green assets such as green bonds, clean energy markets, and carbon prices. Using daily price data, we explore return spillovers across these green financial markets by applying the novel framework on time and frequency dynamics proposed by Baruník and Krehlík (2018). This allows us to identify the direction of spillovers among our variables, and decompose the connectedness to differentiate between short-term and long-term return spillovers. Our results indicate that green bonds and carbon prices act as net receivers of shocks, but mainly in the short-term. We also observe a low level of connectedness among our clean energy markets across both low and high frequency bands, even during times of economic or political crisis. Additionally, there are periods in which connectedness between the clean energy assets is driven by the long-term. In periods of economic and political stability, carbon prices may also provide an interesting diversifying tool for short-term investors. Our results should be of interest for investors and portfolio managers who focus on green financial markets, by strengthening the notion that green financial markets can offer diversification opportunities, for both short-term and long-term investors. Policy makers could also benefit from our insights on conectedness in their work on short-term and long-term climate policies. This paper is the first to use this framework to investigate systematic risks within green financial markets.</div></div>","PeriodicalId":45111,"journal":{"name":"Journal of Commodity Markets","volume":"36 ","pages":"Article 100442"},"PeriodicalIF":3.7,"publicationDate":"2024-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142651764","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We investigate systemic risk and spillovers in the commodity network during left-tail events using state-of-the-art methodologies: the Component Exponent Shortfall (CES), Quantile-Vector Autoregression (QVAR) and Causality-in-Risk. Our analysis focuses on five commodity groups: Energy (Crude Oil, Heating Oil, Natural Gas, Coal), Base Metals (Aluminum, Copper, Nickel, Zinc), Ferrous Metals (Iron, Steel), Precious Metals (Gold, Palladium, Platinum, Silver), and Others (Rubber). Across the models utilized, we consistently find that energy commodities and precious metals, along with copper as a standalone commodity, represent the most systemically risky group. Thus, portfolios incorporating these commodities are advised to implement more careful diversification to mitigate risks stemming from systemic factors. This may require additional attention to precious metals, as they are often considered safe-haven assets. Expediting the implementation of regulations that promote the replacement of fossil energy sources with green alternatives could be instrumental in managing systemic risk in the commodity market while also facilitating global sustainability. Finally, the results show that the impact of the Israeli-Palestinian conflict on both systemic risk and spillovers has been limited compared to the effects of COVID-19 and the Russia-Ukraine war.
{"title":"Commodity market downturn: Systemic risk and spillovers during left tail events","authors":"Samet Gunay , Destan Kirimhan , Emrah Ismail Cevik","doi":"10.1016/j.jcomm.2024.100445","DOIUrl":"10.1016/j.jcomm.2024.100445","url":null,"abstract":"<div><div>We investigate systemic risk and spillovers in the commodity network during left-tail events using state-of-the-art methodologies: the Component Exponent Shortfall (CES), Quantile-Vector Autoregression (QVAR) and Causality-in-Risk. Our analysis focuses on five commodity groups: Energy (Crude Oil, Heating Oil, Natural Gas, Coal), Base Metals (Aluminum, Copper, Nickel, Zinc), Ferrous Metals (Iron, Steel), Precious Metals (Gold, Palladium, Platinum, Silver), and Others (Rubber). Across the models utilized, we consistently find that energy commodities and precious metals, along with copper as a standalone commodity, represent the most systemically risky group. Thus, portfolios incorporating these commodities are advised to implement more careful diversification to mitigate risks stemming from systemic factors. This may require additional attention to precious metals, as they are often considered safe-haven assets. Expediting the implementation of regulations that promote the replacement of fossil energy sources with green alternatives could be instrumental in managing systemic risk in the commodity market while also facilitating global sustainability. Finally, the results show that the impact of the Israeli-Palestinian conflict on both systemic risk and spillovers has been limited compared to the effects of COVID-19 and the Russia-Ukraine war.</div></div>","PeriodicalId":45111,"journal":{"name":"Journal of Commodity Markets","volume":"36 ","pages":"Article 100445"},"PeriodicalIF":3.7,"publicationDate":"2024-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142651524","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-29DOI: 10.1016/j.jcomm.2024.100444
Kaixin Li , Zhikai Zhang , Yudong Wang , Yaojie Zhang
We construct North American oil-related industry ESG indices based on Elastic Net and PCA/SPCA/PLS dimensionality reduction techniques. We discover that the ESG indices show significant forecasting power for crude oil returns both in- and out-of-sample, and their ability to significantly predict oil returns remains when the delayed ESG release is considered. Additionally, our analysis suggests that the predictive abilities of ESG indices remain robust and unaffected by stock returns in the oil-related industry. The ESG indices can provide information that is heterogeneous and complementary to macroeconomic variables and technical indicators. Based on the analysis over the business cycle, ESG indices show predictability in forecasting crude oil returns during economic expansions rather than recessions. Moreover, ESG indices' predictive ability is also of economic significance, as shown by the substantial economic value it generates for mean-variance investors. Finally, we explore the potential economic channels, and the result reveals that the predictive power of ESG indices arises from speculative behavior in the oil market and oil demand.
{"title":"Forecasting crude oil returns with oil-related industry ESG indices","authors":"Kaixin Li , Zhikai Zhang , Yudong Wang , Yaojie Zhang","doi":"10.1016/j.jcomm.2024.100444","DOIUrl":"10.1016/j.jcomm.2024.100444","url":null,"abstract":"<div><div>We construct North American oil-related industry ESG indices based on Elastic Net and PCA/SPCA/PLS dimensionality reduction techniques. We discover that the ESG indices show significant forecasting power for crude oil returns both in- and out-of-sample, and their ability to significantly predict oil returns remains when the delayed ESG release is considered. Additionally, our analysis suggests that the predictive abilities of ESG indices remain robust and unaffected by stock returns in the oil-related industry. The ESG indices can provide information that is heterogeneous and complementary to macroeconomic variables and technical indicators. Based on the analysis over the business cycle, ESG indices show predictability in forecasting crude oil returns during economic expansions rather than recessions. Moreover, ESG indices' predictive ability is also of economic significance, as shown by the substantial economic value it generates for mean-variance investors. Finally, we explore the potential economic channels, and the result reveals that the predictive power of ESG indices arises from speculative behavior in the oil market and oil demand.</div></div>","PeriodicalId":45111,"journal":{"name":"Journal of Commodity Markets","volume":"36 ","pages":"Article 100444"},"PeriodicalIF":3.7,"publicationDate":"2024-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142577461","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-26DOI: 10.1016/j.jcomm.2024.100443
Yanli Zhu , Xian Yang , Chuanhai Zhang , Sihan Liu , Jiayi Li
This paper investigates the role of infectious disease uncertainty on multi-scale risk spillovers and portfolio implications across 12 international commodity futures markets from January 2006 to August 2022. We use wavelet packet decomposition and a novel risk spillover network topology approach based on a smooth transition vector autoregression model. The main findings are summarized as follows. First, there is an obvious asymmetry in spillover effects, i.e., the intensity of risk spillovers increases significantly during periods of high infectious disease uncertainty, and clear evidence of time-varying total spillovers across various regimes and frequencies. Second, cross-category risk spillovers are more pronounced in high-uncertainty regimes, while risk networks tend to cluster within the same category during low-uncertainty regimes. Third, the role of commodity futures in the risk spillover networks varies across different time scales and regimes, with gold consistently acting as a stable net risk transmitter. We also develop optimal portfolio strategies across commodity futures markets at different time scales and regimes based on the risk spillover analysis.
{"title":"Asymmetric multi-scale systemic risk spillovers across international commodity futures markets: The role of infectious disease uncertainty","authors":"Yanli Zhu , Xian Yang , Chuanhai Zhang , Sihan Liu , Jiayi Li","doi":"10.1016/j.jcomm.2024.100443","DOIUrl":"10.1016/j.jcomm.2024.100443","url":null,"abstract":"<div><div>This paper investigates the role of infectious disease uncertainty on multi-scale risk spillovers and portfolio implications across 12 international commodity futures markets from January 2006 to August 2022. We use wavelet packet decomposition and a novel risk spillover network topology approach based on a smooth transition vector autoregression model. The main findings are summarized as follows. First, there is an obvious asymmetry in spillover effects, i.e., the intensity of risk spillovers increases significantly during periods of high infectious disease uncertainty, and clear evidence of time-varying total spillovers across various regimes and frequencies. Second, cross-category risk spillovers are more pronounced in high-uncertainty regimes, while risk networks tend to cluster within the same category during low-uncertainty regimes. Third, the role of commodity futures in the risk spillover networks varies across different time scales and regimes, with gold consistently acting as a stable net risk transmitter. We also develop optimal portfolio strategies across commodity futures markets at different time scales and regimes based on the risk spillover analysis.</div></div>","PeriodicalId":45111,"journal":{"name":"Journal of Commodity Markets","volume":"36 ","pages":"Article 100443"},"PeriodicalIF":3.7,"publicationDate":"2024-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142572506","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-20DOI: 10.1016/j.jcomm.2024.100441
Linjie Wang , Xiaoli Etienne , Jian Li
This paper investigates the dynamic relationship between crude oil, ethanol, and corn markets across various quantiles of return distributions, as well as at higher statistical moments. Using a quantile vector autoregression model and data from 2007 to 2022, we find that the cross-market linkages are quantile dependent, with the strongest connections observed in the tails of the distribution. A shock to the oil market significantly impacts ethanol and corn returns under extreme bearish and bullish conditions. Positive shocks to the corn market reduce ethanol returns when the ethanol market is highly bullish, but this effect becomes positive in the left tail of the distribution. We also identify significant co-movement in higher statistical moments between these markets. Extreme excess kurtosis in the food-fuel nexus is more likely to occur with high financial market uncertainty, a bullish stock market, contracting industrial production, and a strong US dollar. In addition to these variables, credit spreads, futures market liquidity, futures term structure, and hedging pressure also influence kurtosis in individual markets within the nexus.
{"title":"Food-fuel nexus beyond mean-variance: New evidence from a quantile approach","authors":"Linjie Wang , Xiaoli Etienne , Jian Li","doi":"10.1016/j.jcomm.2024.100441","DOIUrl":"10.1016/j.jcomm.2024.100441","url":null,"abstract":"<div><div>This paper investigates the dynamic relationship between crude oil, ethanol, and corn markets across various quantiles of return distributions, as well as at higher statistical moments. Using a quantile vector autoregression model and data from 2007 to 2022, we find that the cross-market linkages are quantile dependent, with the strongest connections observed in the tails of the distribution. A shock to the oil market significantly impacts ethanol and corn returns under extreme bearish and bullish conditions. Positive shocks to the corn market reduce ethanol returns when the ethanol market is highly bullish, but this effect becomes positive in the left tail of the distribution. We also identify significant co-movement in higher statistical moments between these markets. Extreme excess kurtosis in the food-fuel nexus is more likely to occur with high financial market uncertainty, a bullish stock market, contracting industrial production, and a strong US dollar. In addition to these variables, credit spreads, futures market liquidity, futures term structure, and hedging pressure also influence kurtosis in individual markets within the nexus.</div></div>","PeriodicalId":45111,"journal":{"name":"Journal of Commodity Markets","volume":"36 ","pages":"Article 100441"},"PeriodicalIF":3.7,"publicationDate":"2024-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142536028","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-16DOI: 10.1016/j.jcomm.2024.100440
Renata Karkowska, Szczepan Urjasz
This paper aims to explore the complex linkages and evolving structure of price volatility in the global oil, biofuels, and grain commodity markets during periods of global turbulence. With the growing urgency for energy stability amid climate change, biofuels are gaining traction as a viable alternative energy source. However, their production can significantly impact essential commodities like grains and vegetable oils, increasing food prices and heightened market volatility. We introduced a TVP-VAR frequency connectedness method to address this, analyzing data from January 1, 2013, to September 29, 2023. Our approach offers a fresh perspective on market dynamics and geopolitical risks.
The study underscores the growing influence of agricultural shocks on energy markets, particularly within the ethanol sector. It confirms that the Russia-Ukraine war, a significant geopolitical event, has had a profound and enduring impact on the interconnectedness of these markets across various timeframes and frequencies. We offer concrete, actionable policy recommendations to mitigate the transmission of market shocks within the energy and food sectors, thereby bolstering investor and policymaker confidence and facilitating informed decision-making.
{"title":"Importance of geopolitical risk in volatility structure: New evidence from biofuels, crude oil, and grains commodity markets","authors":"Renata Karkowska, Szczepan Urjasz","doi":"10.1016/j.jcomm.2024.100440","DOIUrl":"10.1016/j.jcomm.2024.100440","url":null,"abstract":"<div><div>This paper aims to explore the complex linkages and evolving structure of price volatility in the global oil, biofuels, and grain commodity markets during periods of global turbulence. With the growing urgency for energy stability amid climate change, biofuels are gaining traction as a viable alternative energy source. However, their production can significantly impact essential commodities like grains and vegetable oils, increasing food prices and heightened market volatility. We introduced a TVP-VAR frequency connectedness method to address this, analyzing data from January 1, 2013, to September 29, 2023. Our approach offers a fresh perspective on market dynamics and geopolitical risks.</div><div>The study underscores the growing influence of agricultural shocks on energy markets, particularly within the ethanol sector. It confirms that the Russia-Ukraine war, a significant geopolitical event, has had a profound and enduring impact on the interconnectedness of these markets across various timeframes and frequencies. We offer concrete, actionable policy recommendations to mitigate the transmission of market shocks within the energy and food sectors, thereby bolstering investor and policymaker confidence and facilitating informed decision-making.</div></div>","PeriodicalId":45111,"journal":{"name":"Journal of Commodity Markets","volume":"36 ","pages":"Article 100440"},"PeriodicalIF":3.7,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142445380","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-09DOI: 10.1016/j.jcomm.2024.100439
Gonzalo Cortazar , Hector Ortega , Joaquin Santa Maria , Eduardo S. Schwartz
This paper proposes a new way of estimating ETFs' expected returns. Instead of using traditional CAPM-like expected return models on ETFs' market prices, it consists of implementing ETFs' investment strategy on the underlying assets and using these assets' pricing models to estimate the expected returns on the ETFs. The hypothesis is that whenever valuable knowledge is available on the underlying asset returns, this information can be helpful when estimating expected ETF returns.
We illustrate our approach by choosing the United States Oil Fund (USO), the largest oil futures-based ETF. We propose estimating ETF returns using their investment strategy in oil futures and an oil pricing model. We use a three-factor stochastic process for oil futures and forecasts calibrated using a Kalman Filter and maximum likelihood estimation procedure.
Using historical futures prices, we successfully replicate historical NAV values following their investment strategy. We then estimate ETFs' expected returns using NAVs as a proxy for ETFs' market values and implement their investment strategy priced using the oil price model. We then compare our results with the more traditional CAPM expected return estimation, obtaining a similar average but a time-varying expected ETF return that reacts to market conditions and allows us to analyze their macroeconomic determinants.
{"title":"Expected returns on commodity ETFs and their underlying assets","authors":"Gonzalo Cortazar , Hector Ortega , Joaquin Santa Maria , Eduardo S. Schwartz","doi":"10.1016/j.jcomm.2024.100439","DOIUrl":"10.1016/j.jcomm.2024.100439","url":null,"abstract":"<div><div>This paper proposes a new way of estimating ETFs' expected returns. Instead of using traditional CAPM-like expected return models on ETFs' market prices, it consists of implementing ETFs' investment strategy on the underlying assets and using these assets' pricing models to estimate the expected returns on the ETFs. The hypothesis is that whenever valuable knowledge is available on the underlying asset returns, this information can be helpful when estimating expected ETF returns.</div><div>We illustrate our approach by choosing the United States Oil Fund (USO), the largest oil futures-based ETF. We propose estimating ETF returns using their investment strategy in oil futures and an oil pricing model. We use a three-factor stochastic process for oil futures and forecasts calibrated using a Kalman Filter and maximum likelihood estimation procedure.</div><div>Using historical futures prices, we successfully replicate historical NAV values following their investment strategy. We then estimate ETFs' expected returns using NAVs as a proxy for ETFs' market values and implement their investment strategy priced using the oil price model. We then compare our results with the more traditional CAPM expected return estimation, obtaining a similar average but a time-varying expected ETF return that reacts to market conditions and allows us to analyze their macroeconomic determinants.</div></div>","PeriodicalId":45111,"journal":{"name":"Journal of Commodity Markets","volume":"36 ","pages":"Article 100439"},"PeriodicalIF":3.7,"publicationDate":"2024-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142432445","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-05DOI: 10.1016/j.jcomm.2024.100438
Christian Oliver Ewald , Yaoyu Li
This paper employs deep learning models and sentiment analysis to predict salmon spot prices. Our data includes historical price data and sentiment scores from 2018 to 2022. We extract sentiment scores from salmon-related news headlines by using FinBERT and TextBlob. We begin with price prediction using only historical price data and then introduce sentiment scores to improve the prediction accuracy of deep learning models. We find that the prediction performance of deep learning models outperforms traditional prediction methods in the salmon market. Our primary hybrid CNN-LSTM model outperforms other deep learning models and traditional models. Additionally, deep learning models incorporating sentiment scores exhibit reduced prediction errors. Our findings confirm the value of sentiment information in improving forecasting performance. These findings highlight the effectiveness and robustness of our CNN-LSTM model combined with sentiment analysis for price prediction in the salmon market.
{"title":"The role of news sentiment in salmon price prediction using deep learning","authors":"Christian Oliver Ewald , Yaoyu Li","doi":"10.1016/j.jcomm.2024.100438","DOIUrl":"10.1016/j.jcomm.2024.100438","url":null,"abstract":"<div><div>This paper employs deep learning models and sentiment analysis to predict salmon spot prices. Our data includes historical price data and sentiment scores from 2018 to 2022. We extract sentiment scores from salmon-related news headlines by using FinBERT and TextBlob. We begin with price prediction using only historical price data and then introduce sentiment scores to improve the prediction accuracy of deep learning models. We find that the prediction performance of deep learning models outperforms traditional prediction methods in the salmon market. Our primary hybrid CNN-LSTM model outperforms other deep learning models and traditional models. Additionally, deep learning models incorporating sentiment scores exhibit reduced prediction errors. Our findings confirm the value of sentiment information in improving forecasting performance. These findings highlight the effectiveness and robustness of our CNN-LSTM model combined with sentiment analysis for price prediction in the salmon market.</div></div>","PeriodicalId":45111,"journal":{"name":"Journal of Commodity Markets","volume":"36 ","pages":"Article 100438"},"PeriodicalIF":3.7,"publicationDate":"2024-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142420267","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号