[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125758-en":3,"doc-seo-125758-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},125758,3848291630094,"Emma Wilson","https://eur-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45",8,"Research & Report","A Comparison of Machine Learning Methods for Predicting the Direction of the US Stock Market - Using Volatility Indices","This paper investigates the information content of volatility indices for predicting the future direction of the US stock market. Different machine learning methods are applied to a dataset of S&P 500 index returns and volatility indices from January 2011 to July 2022. Predictive performance is assessed using accuracy, ROC area, and F-measure. Results show that machine learning models outperform classical least squares linear regression, with random forests and bagging achieving the best overall performance across all metrics.","A comparison of machine learning methods for predicting the direction of the US stock market on the basis of volatility indices  \nGiovanni Campisi a ,∗, Silvia Muzzioli a , Bernard De Baetsba Marco Biagi Department of Economics, University of Modena and Reggio Emilia, Modena, Italy b Department of Data Analysis and Mathematical Modelling, Ghent University, Belgium  \n| a r t i c l e i n f o |  | a b s t r a c t |\n| --- | --- | --- |\n| Keywords:\u003Cbr>Machine learning\u003Cbr>Volatility indices Forecasting Market risk\u003Cbr>US market |  | This paper investigates the information content of volatility indices for the purpose of predicting the future direction of the stock market. To this end, different machine learning methods are applied. The dataset used consists of stock index returns and volatility indices of the US stock market from January 2011 until July 2022. The predictive performance of the resulting models is evaluated on the basis of three evaluation metrics: accuracy, the area under the ROC curve, and the F-measure. The results indicate that machine learning models outperform the classical least squares linear regression model in predicting the direction of S&P 500 returns. Among the models examined, random forests and bagging attain the highest predictive performance based on all the evaluation metrics adopted.\u003Cbr>© 2023 The Author(s). Published by Elsevier B.V. on behalf of International Institute of Forecasters. This is an open access article under the CC BY-NC-ND license ([http://creativecommons.org/licenses/by-nc-nd/4.0/](http://creativecommons.org/licenses/by-nc-nd/4.0/)). |\n\n1. Introduction  \nStock market prediction has always been an important issue in the financial literature (Elyasiani et al., 2017 ; Giot, 2005 ; Gonzalez-Perez, 2015 ; Lubnau & Todorova, 2015 ; Rubbaniy et al., 2014). In recent decades, the quantity and quality of the information available to researchers have increased dramatically. In particular, implied volatility indices are essential for asset pricing and risk management. They contain information embedded in option prices that reflect investor opinion about future underlying asset trends. Moreover, new and efficient decisionmaking algorithms, including machine learning methods, have become increasingly common in the literature and the markets.  \n∗ Corresponding author.  \nE-mail addresses: [giovanni.campisi@unimore.it](giovanni.campisi@unimore.it) (G. Campisi), [silvia.muzzioli@unimore.it](silvia.muzzioli@unimore.it) (S. Muzzioli), bernard.deBaets@ugent.be (B. De Baets).  \nThis paper contributes to the literature on the prediction of stock returns by using multiple forward-looking volatility indicators, which may carry conflicting information on future returns. For this purpose, we rely on several machine learning methods that are able to analyze largescale models and select the relevant variables. It has been shown that the flexible nature of these data-driven methods allows them to deal with various aspects of prediction problems (Gu et al., 2020). Moreover, machine learning methods focus on making predictions as accurately as possible (Athey & Imbens, 2019).  \nThere is strong evidence that volatility indices provide useful information about current and future stock returns. In this context, Giot (2005) argues that high implied volatility levels indicate oversold markets and could be viewed as short- to medium-term buy signals. Zhu (2013) investigates the US stock and bond returns using a distribution-based framework, finding evidence that the VIX helps to forecast the distribution of US stock returns. Gonzalez-Perez (2015) provides a comprehensive literature review on forecasting volatility models. Other  \n[https://doi.org/10.1016/j.ijforecast.2023.07.002](https://doi.org/10.1016/j.ijforecast.2023.07.002)  \n0169-2070/© 2023 The Author(s). Published by Elsevier B.V. on behalf of International Institute of Forecasters. This is an open access article under the CC BY-NC-ND license ([http://creativeco","cbCaieZUgY9Fcgqa","https://ap.wps.com/l/cbCaieZUgY9Fcgqa","pdf",644540,1,12,"English","en",105,"# Introduction\n## Volatility indices and market information\n## Machine learning approaches for forecasting\n## Related work and motivation","[{\"question\":\"What is the main goal of the study?\",\"answer\":\"To evaluate whether volatility indices contain information useful for predicting the future direction of the US stock market.\"},{\"question\":\"Which data are used to build and test the models?\",\"answer\":\"The dataset combines US market stock index returns with volatility indices from January 2011 through July 2022.\"},{\"question\":\"How is model performance measured?\",\"answer\":\"Performance is evaluated using accuracy, the area under the ROC curve, and the F-measure.\"}]","A Comparison of Machine Learning Methods for Predicting the Direction of the US Stock Market - Using Volatility Indices | PDF",1785901045,30,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"a-comparison-of-machine-learning-methods-for-predicting-the-direction-of-the-us-stock-market-using-volatility-indices","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/a-comparison-of-machine-learning-methods-for-predicting-the-direction-of-the-us-stock-market-using-volatility-indices/125758/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What is the main goal of the study?","Question",{"text":75,"@type":76},"To evaluate whether volatility indices contain information useful for predicting the future direction of the US stock market.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which data are used to build and test the models?",{"text":80,"@type":76},"The dataset combines US market stock index returns with volatility indices from January 2011 through July 2022.",{"name":82,"@type":73,"acceptedAnswer":83},"How is model performance measured?",{"text":84,"@type":76},"Performance is evaluated using accuracy, the area under the ROC curve, and the F-measure.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":29,"slug":121},"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]