[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126652-en":3,"doc-seo-126652-105":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},126652,549768064778,"Finn","https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8",8,"Research & Report","Portfolio Selection Under Non-Gaussianity And Systemic Risk - A Machine Learning Based Forecasting Approach","The Sharpe-ratio-maximizing portfolio weakens under non-Gaussian return distributions and, by design, neglects systemic risk that can degrade out-of-sample performance. The work introduces a new portfolio performance ratio that addresses both issues simultaneously. It improves robustness to extreme market scenarios by generating many return scenarios through Monte Carlo simulation, driven by distributional machine-learning probabilistic forecasts in a big-data setting and a fitted copula.","Portfolio Selection Under Non-Gaussianity And Systemic Risk: A  \nMachine Learning Based Forecasting Approach􀀃  \nWeidong Liny Abderrahim Taamoutiz  \nAugust 11, 2023  \nABSTRACT  \nThe Sharpe-ratio-maximizing portfolio becomes questionable under non-Gaussian returns, and it rules out, by construction, systemic risk, which can negatively a§ect its out-of-sample performance. In the present work, we develop a new performance ratio that simultaneously addresses these two problems when building optimal portfolios. To robustify the portfolio optimization and better represent extreme market scenarios, we simulate a large number of returns via a Monte Carlo method. This is done by Örst obtaining probabilistic return forecasts through a distributional machine learning approach in a big data setting, and then combining them with a Ötted copula to generate return scenarios. Based on a large-scale comparative analysis conducted on the US market, the backtesting results demonstrate the superiority of our proposed portfolio selection approach against several popular benchmark strategies in terms of both proÖtability and minimizing systemic risk. This outperformance is robust to the inclusion of transaction costs.  \nKeywords: Portfolio optimization; probability forecasting; quantile regression neural network; extreme scenarios; big data.  \n􀀃 The authors would like to thank very much the Editor Professor Dick van Dijk and two anonymous reviewers for their very useful comments.  \ny Department of Finance, NEOMA Business School (Rouen) . Address: 1 Rue du MarÈchal Juin, Mont-SaintAignan, 76130, France. E-mail: [weidong.lin@neoma-bs.fr](weidong.lin@neoma-bs.fr)  \nz Corresponding author. Department of Economics, University of Liverpool Management School. Address: Chatham St, Liverpool L69 7ZH. E-mail: [Abderrahim.Taamouti@liverpool.ac.uk](Abderrahim.Taamouti@liverpool.ac.uk).  \nPortfolio Selection Under Non-Gaussianity And Systemic Risk: A Machine Learning Based Forecasting Approach  \nAbstract  \nThe Sharpe-ratio-maximizing portfolio becomes questionable under non-Gaussian returns, and it rules out, by construction, systemic risk, which can negatively affect its out-of-sample performance. In the present work, we develop a new performance ratio that simultaneously addresses these two problems when building optimal portfolios. To robustify the portfolio optimization and better represent extreme market scenarios, we simulate a large number of returns via a Monte Carlo method. This is done by first obtaining probabilistic return forecasts through a distributional machine learning approach in a big data setting, and then combining them with a fitted copula to generate return scenarios. Based on a large-scale comparative analysis conducted on the US market, the backtesting results demonstrate the superiority of our proposed portfolio selection approach against several popular benchmark strategies in terms of both profitability and minimizing systemic risk. This outperformance is robust to the inclusion of transaction costs.  \nKeywords: portfolio optimization; probability forecasting; quantile regression neural network; extreme scenarios; big data  \n1 Introduction  \n1.1 Motivation of the new performance measure  \nDeciding the best performance measure to use for constructing optimal portfolios is an evergreen question in asset allocation. Following the work of Roy (1952), Sharpe (1966) established the popular Sharpe ratio, initially termed as a reward-to-variability ratio, measuring the tradeoff between mean return and risk. However, this ratio suffers from several drawbacks as it inherently depends on the normality assumption of the return distribution. Such drawbacks include ignoring higher order moments of returns, but importantly using an inadequate measure of risk, namely standard deviation.  \nAlthough the Sharpe ratio has always been seen as a reward-to-risk performance measure, it is essentially a dispersion-type of ratio since its risk measure (i.e. st","cbCair4KiowapJaD","https://ap.wps.com/l/cbCair4KiowapJaD","pdf",1302812,1,54,"English","en",105,"# Introduction\n## Motivation of the new performance measure","[{\"question\":\"Why does the Sharpe-ratio-maximizing portfolio become questionable under non-Gaussian returns?\",\"answer\":\"Because it relies on assumptions tied to normal return distributions and uses standard deviation as the risk measure, which can be inadequate when distributional features like asymmetry and heavy tails are present.\"},{\"question\":\"How does the proposed approach address systemic risk when building optimal portfolios?\",\"answer\":\"It extends an unconditional risk-adjusted measure to incorporate systemic events, enabling the performance ratio to reflect non-Gaussian returns while allowing systemic breakdown scenarios.\"},{\"question\":\"How are return scenarios generated for robust portfolio optimization?\",\"answer\":\"The method first produces probabilistic return forecasts using a distributional machine learning model, then combines these forecasts with a fitted copula and uses Monte Carlo simulation to generate many return scenarios.\"}]","Portfolio Selection Under Non-Gaussianity And Systemic Risk - A Machine Learning Based Forecasting Approach | PDF",1785934046,136,{"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},"portfolio-selection-under-non-gaussianity-and-systemic-risk-a-machine-learning-based-forecasting-approach","",{"@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/portfolio-selection-under-non-gaussianity-and-systemic-risk-a-machine-learning-based-forecasting-approach/126652/",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},"Why does the Sharpe-ratio-maximizing portfolio become questionable under non-Gaussian returns?","Question",{"text":75,"@type":76},"Because it relies on assumptions tied to normal return distributions and uses standard deviation as the risk measure, which can be inadequate when distributional features like asymmetry and heavy tails are present.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed approach address systemic risk when building optimal portfolios?",{"text":80,"@type":76},"It extends an unconditional risk-adjusted measure to incorporate systemic events, enabling the performance ratio to reflect non-Gaussian returns while allowing systemic breakdown scenarios.",{"name":82,"@type":73,"acceptedAnswer":83},"How are return scenarios generated for robust portfolio optimization?",{"text":84,"@type":76},"The method first produces probabilistic return forecasts using a distributional machine learning model, then combines these forecasts with a fitted copula and uses Monte Carlo simulation to generate many return scenarios.","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},[93,97,101,105,110,115,120,123,128,131,135],{"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":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]