{"title":"Trading the FX volatility risk premium with machine learning and alternative data","authors":"Thomas Dierckx , Jesse Davis , Wim Schoutens","doi":"10.1016/j.jfds.2022.07.001","DOIUrl":"https://doi.org/10.1016/j.jfds.2022.07.001","url":null,"abstract":"<div><p>In this study, we show how both machine learning and alternative data can be successfully leveraged to improve and develop trading strategies. Starting from a trading strategy that harvests the EUR/USD volatility risk premium by selling one-week straddles every weekday, we present a machine learning approach to more skillfully time new trades and thus prevent unfavorable ones. To this end, we build probability-calibrated Random Forests on various predictors, extracted from both traditional market data and financial news, to predict the closing Sharpe ratio of short one-week delta-hedged straddles. We then demonstrate how the output of these calibrated machine learning models can be used to engineer intuitive new trading strategies. Ultimately, we show that our proposed strategies outperform the original strategy on risk-based performance measures. Moreover, the features that we derived from financial news articles significantly improve the performance of the approach.</p></div>","PeriodicalId":36340,"journal":{"name":"Journal of Finance and Data Science","volume":"8 ","pages":"Pages 162-179"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2405918822000083/pdfft?md5=b58dced6034ed9a3c7acc83ec4f3a4fd&pid=1-s2.0-S2405918822000083-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"92057697","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A causal approach to test empirical capital structure regularities","authors":"Simone Cenci , Stephen Kealhofer","doi":"10.1016/j.jfds.2022.09.002","DOIUrl":"https://doi.org/10.1016/j.jfds.2022.09.002","url":null,"abstract":"<div><p>Capital structure theories are often formulated as causal narratives to explain which factors drive financing choices. These narratives are usually examined by estimating cross–sectional relations between leverage and its determinants. However, the limitations of causal inference from observational data are often overlooked. To address this issue, we use structural causal modeling to identify how classic determinants of leverage are causally linked to capital structure and how this causal structure influences the effect-estimation process. The results provide support for the causal role of variables that measure the potential for information asymmetry concerning firms’ market values. Overall, our work provide a crucial step to connect capital structure theories with their empirical tests beyond simple correlations.</p></div>","PeriodicalId":36340,"journal":{"name":"Journal of Finance and Data Science","volume":"8 ","pages":"Pages 214-232"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2405918822000125/pdfft?md5=6e2a9c2d5c0693015b4e5612c8b4914d&pid=1-s2.0-S2405918822000125-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"92138689","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Term structure of interest rates with short-run and long-run risks","authors":"Olesya V. Grishchenko , Zhaogang Song , Hao Zhou","doi":"10.1016/j.jfds.2022.09.001","DOIUrl":"https://doi.org/10.1016/j.jfds.2022.09.001","url":null,"abstract":"<div><p>We find that interest rate variance risk premium (IRVRP) — the difference between implied and realized variances of interest rates — is a strong predictor of U.S. Treasury bond returns of maturities ranging between one and ten years for return horizons up to six months. IRVRP is not subsumed by other predictors such as forward rate spread or equity variance risk premium. These results are robust in a number of dimensions. We rationalize our findings within a consumption-based model with long-run risk, economic uncertainty, and inflation non-neutrality. In the model IRVRP is related to short-run risk only, while standard forward-rate-based factors are associated with both short-run and long-run risks in the economy. Our model qualitatively replicates the predictability pattern of IRVRP for bond returns.</p></div>","PeriodicalId":36340,"journal":{"name":"Journal of Finance and Data Science","volume":"8 ","pages":"Pages 255-295"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2405918822000113/pdfft?md5=4c7fa4b913e0800959a06b47e66ade65&pid=1-s2.0-S2405918822000113-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"92105790","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Machine learning for cryptocurrency market prediction and trading","authors":"Patrick Jaquart, Sven Köpke, Christof Weinhardt","doi":"10.1016/j.jfds.2022.12.001","DOIUrl":"https://doi.org/10.1016/j.jfds.2022.12.001","url":null,"abstract":"<div><p>We employ and analyze various machine learning models for daily cryptocurrency market prediction and trading. We train the models to predict binary relative daily market movements of the 100 largest cryptocurrencies. Our results show that all employed models make statistically viable predictions, whereby the average accuracy values calculated on all cryptocurrencies range from 52.9% to 54.1%. These accuracy values increase to a range from 57.5% to 59.5% when calculated on the subset of predictions with the 10% highest model confidences per class and day. We find that a long-short portfolio strategy based on the predictions of the employed LSTM and GRU ensemble models yields an annualized out-of-sample Sharpe ratio after transaction costs of 3.23 and 3.12, respectively. In comparison, the buy-and-hold benchmark market portfolio strategy only yields a Sharpe ratio of 1.33. These results indicate a challenge to weak form cryptocurrency market efficiency, albeit the influence of certain limits to arbitrage cannot be entirely ruled out.</p></div>","PeriodicalId":36340,"journal":{"name":"Journal of Finance and Data Science","volume":"8 ","pages":"Pages 331-352"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2405918822000174/pdfft?md5=cf49eff9de16cb4b7a287b73a7b86b12&pid=1-s2.0-S2405918822000174-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"92078387","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A new measure of corporate bond liquidity using survival analysis","authors":"Kaihua Cai , Peter Yesley","doi":"10.1016/j.jfds.2022.05.001","DOIUrl":"https://doi.org/10.1016/j.jfds.2022.05.001","url":null,"abstract":"<div><p>We define liquidity for corporate bonds as the expected waiting time to reduce a risk position. Our methodology addresses the fact that many bonds are liquidated quickly despite having few trades in the recent past. Building on research from the housing market, we apply survival analysis to bond holding times. We generalize across bond properties and market conditions to arrive at a liquidity measure for all corporate bonds, independent of how often they trade and whatever transaction costs they incur.</p></div>","PeriodicalId":36340,"journal":{"name":"Journal of Finance and Data Science","volume":"8 ","pages":"Pages 105-119"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2405918822000058/pdfft?md5=e130b3985440bfd3c741593b81f86abf&pid=1-s2.0-S2405918822000058-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"92138688","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Betting against noisy beta","authors":"Thorsten Lehnert","doi":"10.1016/j.jfds.2022.04.001","DOIUrl":"https://doi.org/10.1016/j.jfds.2022.04.001","url":null,"abstract":"<div><p>Strategies that overweight low beta stocks and underweight high beta stocks earn positive alphas. Price noise is known to affect high beta stocks, hence, noise trading can be expected to significantly affect the performance of these strategies. I study the impact of flows between bond and equity funds (net exchanges) on the Frazzini and Pedersen’s (2014) Betting Against Beta (BAB) factor in the US for a period 1984 until 2015. I find mispricing and reversal effects. In particular, when retail investors are caught up in the market euphoria, they are too optimistic, and shift their holdings from bond to equity mutual funds. My results suggest that higher-than-rational beta stocks are particularly exposed to this non-fundamental price pressure. Subsequently, the short-term reversal relation is stronger for high beta stocks and, therefore, returns are significantly lower. As a results, while the market performs poorly, the BAB factor returns are significantly positive. A dynamic trading strategy that is based on signals from past net exchanges and the BAB factor significantly outperforms the market factor by 0.71% monthly on average, during months following positive net exchanges by 1.62% and during market stress episodes by 2.14%. Accounting for transaction costs, other equity risk factors and non-standard procedures used in the BAB construction reduces the profitability of the strategy, but does not change the conclusions. My findings suggest that a major part of the success of the BAB factor is due to its exposure to flow-induced price noise.</p></div>","PeriodicalId":36340,"journal":{"name":"Journal of Finance and Data Science","volume":"8 ","pages":"Pages 55-68"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2405918822000010/pdfft?md5=bf5f7e9ac7ab3c49a972681fa499145a&pid=1-s2.0-S2405918822000010-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"92057695","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"The use of predictive analytics in finance","authors":"Daniel Broby","doi":"10.1016/j.jfds.2022.05.003","DOIUrl":"https://doi.org/10.1016/j.jfds.2022.05.003","url":null,"abstract":"<div><p>Statistical and computational methods are being increasingly integrated into Decision Support Systems to aid management and help with strategic decisions. Researchers need to fully understand the use of such techniques in order to make predictions when using financial data. This paper therefore presents a method based literature review focused on the predictive analytics domain. The study comprehensively covers classification, regression, clustering, association and time series models. It expands existing explanatory statistical modelling into the realm of computational modelling. The methods explored enable the prediction of the future through the analysis of financial time series and cross-sectional data that is collected, stored and processed in Information Systems. The output of such models allow financial managers and risk oversight professionals to achieve better outcomes. This review brings the various predictive analytic methods in finance together under one domain.</p></div>","PeriodicalId":36340,"journal":{"name":"Journal of Finance and Data Science","volume":"8 ","pages":"Pages 145-161"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2405918822000071/pdfft?md5=9b4df085f510c9fc0fa1fbac52010d37&pid=1-s2.0-S2405918822000071-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"92057698","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Feiqi Huang , Won Gyun No , Miklos A. Vasarhelyi , Zhaokai Yan
{"title":"Audit data analytics, machine learning, and full population testing","authors":"Feiqi Huang , Won Gyun No , Miklos A. Vasarhelyi , Zhaokai Yan","doi":"10.1016/j.jfds.2022.05.002","DOIUrl":"https://doi.org/10.1016/j.jfds.2022.05.002","url":null,"abstract":"<div><p>Emerging technologies like data analytics and machine learning are impacting the accounting profession. In particular, significant changes are anticipated in audit and assurance procedures because of those impacts. One such potential change is audit sampling. As audit sampling only provides a small snapshot of the entire population, it starts to lose some of its meaning in this big data era. One feasible solution is the usage of audit data analytics and machine learning to enable an analysis of the entire population rather than a sample of the transactions. This paper presents an approach for applying audit data analytics and machine learning to full population testing and discusses related challenges.</p></div>","PeriodicalId":36340,"journal":{"name":"Journal of Finance and Data Science","volume":"8 ","pages":"Pages 138-144"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S240591882200006X/pdfft?md5=4b953cb6a7425c87262a7317dc1fef45&pid=1-s2.0-S240591882200006X-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"92105792","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Machine learning portfolio allocation","authors":"Michael Pinelis , David Ruppert","doi":"10.1016/j.jfds.2021.12.001","DOIUrl":"https://doi.org/10.1016/j.jfds.2021.12.001","url":null,"abstract":"<div><p>We find economically and statistically significant gains when using machine learning for portfolio allocation between the market index and risk-free asset. Optimal portfolio rules for time-varying expected returns and volatility are implemented with two Random Forest models. One model is employed in forecasting monthly excess returns with macroeconomic factors including payout yields. The second is used to estimate the prevailing volatility. Reward-risk timing with machine learning provides substantial improvements over the buy-and-hold in utility, risk-adjusted returns, and maximum drawdowns. This paper presents a unifying framework for machine learning applied to both return- and volatility-timing.</p></div>","PeriodicalId":36340,"journal":{"name":"Journal of Finance and Data Science","volume":"8 ","pages":"Pages 35-54"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2405918821000155/pdfft?md5=68c09e5e42a490b0df888e1badb3c66a&pid=1-s2.0-S2405918821000155-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"92057696","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Musaib Ashraf, John (Xuefeng) Jiang, Isabel Yanyan Wang
{"title":"Are there trade-offs with mandating timely disclosure of cybersecurity incidents? Evidence from state-level data breach disclosure laws","authors":"Musaib Ashraf, John (Xuefeng) Jiang, Isabel Yanyan Wang","doi":"10.1016/j.jfds.2022.08.001","DOIUrl":"https://doi.org/10.1016/j.jfds.2022.08.001","url":null,"abstract":"<div><p>On March 23, 2022, the SEC proposed that firms publicly disclose their cybersecurity incidents within four days of discovery. In the U.S., state-level data breach disclosure laws require firms to disclose the occurrence of a data breach, with some mandating disclosure within a deadline while others do not. Exploiting this state-level variation in disclosure deadlines, we find that, when facing a deadline, firms disclose a data breach 90 percent faster but are 58 percent less likely to disclose breach details. Investors respond negatively to delayed breach disclosures but are forgiving of a delay when it is used to gather more breach details. Our study highlights the trade-offs of mandating a disclosure deadline for cybersecurity incidents.</p></div>","PeriodicalId":36340,"journal":{"name":"Journal of Finance and Data Science","volume":"8 ","pages":"Pages 202-213"},"PeriodicalIF":0.0,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2405918822000101/pdfft?md5=12292f55581a3ddd898da95c706a8ab9&pid=1-s2.0-S2405918822000101-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"92105793","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
