[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125860-en":3,"doc-seo-125860-105":31,"detail-sidebar-cat-0-en-105":93},{"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":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},125860,1099523882367,"Hazel","https://ap-avatar.wpscdn.com/davatar_9964176cb1d06d4a9deccf72a44ae3dc",8,"Research & Report","CRISIS ALERT - Forecasting Stock Market Crisis Events Using Machine Learning Methods","A data-driven approach predicts US stock market crisis events by modeling next-day crash likelihood using machine learning. The work compiles daily financial indicators from Bloomberg covering 2000–2022, then splits data into training (until end of 2013) and testing (2014–2022). Using 75 explanatory variables and crisis labels based on extreme lower-tail log-returns, the study preprocesses missing values and applies log-return transformations. Model comparison concludes Extreme Gradient Boosting achieves the strongest crisis forecasting performance via selected classification metrics.","1  \nCRISIS ALERT:  \nForecasting Stock Market Crisis Events Using Machine Learning Methods  \nXingyi Andrew, Yue Chen, Salintip Supasanya  \n1. Introduction  \nHistorically, the economic recession often came abruptly and disastrously. For instance, during the 2008 financial crisis (the Great Recession), the S&P 500 fell 46.13% from October 2007 to March 2009. Millions of jobs and small businesses were swept away by the depression involuntarily. If we could detect the signals of the crisis earlier, we could have taken preventive measures. Therefore, driven by such motivation, we use advanced machine learning techniques we learned in class, including Random Forest and Extreme Gradient Boosting, to predict any potential market crashes mainly in the US market. Also, we would like to compare the performance of these methods and examine which model is better for forecasting US stock market crashes. Specifically, we are referring to a paper called “Forecasting stock market crisis events using deep and statistical machine learning techniques” as our guidance. We apply our models on the daily financial market data, which tend to be more responsive with higher reporting frequencies. We consider 75 explanatory variables, including general US stock market indexes, S&P 500 sector indexes, as well as market indicators that can be used for the purpose of crisis prediction. Finally, we conclude, with selected classification metrics, that the Extreme Gradient Boosting method performs the best in predicting US stock market crisis events.  \n2. Data Collection and Processing  \n2.1 Data Collection  \nIn order to train the model for stock market crisis prediction, we collect various financial indicators from the Bloomberg Terminal. The dataset includes 5775 observations and covers the period from 01/04/2000 to 02/18/2022, measured on a daily basis.  \nOur data consists of some major financial crises that have happened in the US, including (Williams, 2022):  \n● The US dot-com bubble (March 2000)  \n● Stock market downturn (October 2002)  \n● Global financial crisis (November 2007)  \n● Stock market selloff (August 2015)  \n● Cryptocurrency crash (February 2018)  \n● Stock market crash (March 2020)  \nDue to the timeline of listed market crashes, we split our data into two parts: a training dataset, including the data until the end of 2013, and a testing dataset, spanning over the years 2014–2022. The training dataset is used for fitting the model while the testing dataset is used for validating the fitted model.  \n2  \nWe examine the following 19 variables to represent different components of the US economy.  \n\n| Stock markets | Sector markets | Exchange rates | Additional variables |\n| --- | --- | --- | --- |\n| Dow Jones\u003Cbr>Industrial Average | Energy Select Sector | Chinese Yuan to U. S. Dollar | VIX Index |\n| S&P 500 | Technology Select Sector | Japan Yen to U. S. Dollar | Gold Price |\n| Nasdaq Composite | Financial Select Sector | U. S. Dollars to Euro | Oil Price |\n| Hang Seng Index | Consumer Discretionary Select Sector | U. S. Dollars to British Pound | Effective Federal Funds Rate |\n|  | Health Care Select Sector |  | Investment-grade Bond Yield |\n|  |  |  | US 10-year Bond Yield |\n\nTable 1. Examined exploratory variables.  \nThe three US stock market indexes, Dow Jones Industrial Average, S&P 500, and Nasdaq Composite, represent blue-chip, 500 largest market-capitalization, and technology-heavy companies in the US, respectively, which portray the US stock market in the full picture. The Hang Seng Index is a Hong Kong stock market index representing a foreign market that is highly correlated with the US market. The selected five S&P sector markets are important components of the US economy. The four exchange rates are the major players in the foreign exchange market which are influential on the US market. The VIX index measures the volatility of the US stock market, reflecting investors’ fear; this index tends to peak when there are crisis events coming. ","cbCaibXeenbOruBk","https://ap.wps.com/l/cbCaibXeenbOruBk","pdf",673108,5,1,14,"English","en",105,"# Introduction\n# Data Collection and Processing\n## Data Collection\n## Data processing\n# Dependent Variables\n## Crisis event definition","[{\"question\":\"How are crisis events defined for the prediction task?\",\"answer\":\"A crisis event is defined when the next trading day’s stock-index log-return (Dow Jones, S\\u0026P 500, or Nasdaq Composite) falls below the first percentile of its empirical log-return distribution, which is updated forward in time.\"},{\"question\":\"What data and time span are used to train and test the models?\",\"answer\":\"Daily financial indicators from Bloomberg are collected for 01/04/2000 to 02/18/2022, totaling 5,775 observations. The data are split into training up to the end of 2013 and testing across 2014–2022.\"},{\"question\":\"Which machine learning methods are compared, and what is the final best performer?\",\"answer\":\"The study compares Random Forest and Extreme Gradient Boosting for forecasting US stock market crisis events. Extreme Gradient Boosting delivers the best predictive performance based on selected classification metrics.\"}]","CRISIS ALERT - Forecasting Stock Market Crisis Events Using Machine Learning Methods | PDF",1785901633,35,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":88,"head_meta":90,"extra_data":92,"updated_unix":29},"crisis-alert-forecasting-stock-market-crisis-events-using-machine-learning-methods","",{"@graph":37,"@context":87},[38,55,70],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":54},"https://docshare.wps.com/document/crisis-alert-forecasting-stock-market-crisis-events-using-machine-learning-methods/125860/",4,{"url":53,"name":13,"@type":56,"author":57,"headline":13,"publisher":59,"fileFormat":62,"inLanguage":24,"description":14,"dateModified":63,"datePublished":64,"encodingFormat":62,"isAccessibleForFree":65,"interactionStatistic":66},"DigitalDocument",{"name":9,"@type":58},"Person",{"url":42,"name":60,"@type":61},"DocShare","Organization","application/pdf","2026-08-22","2026-08-05",true,{"@type":67,"interactionType":68,"userInteractionCount":20},"InteractionCounter",{"@type":69},"ViewAction",{"@type":71,"mainEntity":72},"FAQPage",[73,79,83],{"name":74,"@type":75,"acceptedAnswer":76},"How are crisis events defined for the prediction task?","Question",{"text":77,"@type":78},"A crisis event is defined when the next trading day’s stock-index log-return (Dow Jones, S&P 500, or Nasdaq Composite) falls below the first percentile of its empirical log-return distribution, which is updated forward in time.","Answer",{"name":80,"@type":75,"acceptedAnswer":81},"What data and time span are used to train and test the models?",{"text":82,"@type":78},"Daily financial indicators from Bloomberg are collected for 01/04/2000 to 02/18/2022, totaling 5,775 observations. The data are split into training up to the end of 2013 and testing across 2014–2022.",{"name":84,"@type":75,"acceptedAnswer":85},"Which machine learning methods are compared, and what is the final best performer?",{"text":86,"@type":78},"The study compares Random Forest and Extreme Gradient Boosting for forecasting US stock market crisis events. Extreme Gradient Boosting delivers the best predictive performance based on selected classification metrics.","https://schema.org",{"og:url":53,"og:type":89,"og:title":13,"og:site_name":60,"og:description":14},"article",{"robots":91,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":94},[95,99,103,107,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":96,"show_sort_weight":97,"slug":98},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":100,"show_sort_weight":101,"slug":102},"Literature",80,"literature",{"id":54,"doc_module":4,"doc_module_name":47,"category_name":104,"show_sort_weight":105,"slug":106},"Exam",70,"exam",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":20,"slug":139},19,"General","general"]