[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117058-en":3,"doc-seo-117058-105":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},117058,3848291630094,"Emma Wilson","https://eur-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45",8,"Research & Report","Machine Learning Execution Time in Asset Pricing","Machine learning models in finance often deliver improved return predictability, yet training and prediction can be computationally expensive and may prevent timely market responses. This study evaluates model execution time across training and prediction phases in empirical asset pricing, analyzing ten models. Two strategies are introduced to reduce execution time: feature reduction and using fewer time observations. Results show XGBoost as a leading performer with low execution time and strong out-of-sample performance, while time-reduction strategies cut execution time up to 18x and slightly improve investment performance.","Machine Learning Execution Time in Asset Pricing  \nUmit Demirbaga‡  \nYue Xu§  \nThis version: November 2, 2023  \n‡Department of Medicine, University of Cambridge; European Bioinformatics Institute (EMBL-EBI); Department of Computer Engineering, Bartin University. Email: [ud220@cam.ac.uk](ud220@cam.ac.uk).  \n§ Department of Finance, Business School, Durham University. Email: [xu.yue@durham.ac.uk](xu.yue@durham.ac.uk).  \nMachine Learning Execution Time in Asset Pricing  \nAbstract  \nIn the fast-paced world of finance, where timely decisions can yield substantial gains or losses, machine learning models with time-consuming training and prediction may miss crucial market timing opportunities. This study examines the machine learning model execution time including both training and prediction phases, in empirical asset pricing.  \nWe conduct a comprehensive analysis of machine learning execution time, examining ten models and introducing two strategies to save time: feature reduction and the reduction of time observations. Our findings reveal that XGBoost stands out as a top performer, demonstrating relatively low execution times compared to other machine learning models, with exceptional accuracy, boasting an out-of-sample R2 of 0 .78 anda Sharpe ratio of 1 .76. Furthermore, feature reduction and shorter time observations reduce execution time by as much as 18 times while also slightly enhancing investment performance. This research underscores the vital interplay between model accuracy and execution time to make accurate and prompt investment decisions in practice.  \nKeywords: Execution Time; Asset Pricing; Machine Learning; XGBoost; Investment Performance  \nJEL Classification: C52; C55; C58; G12; G17  \nThis version: November 2, 2023 .  \nI . Introduction  \nRecent studies highlight the improved precision in return predictability when incorporating machine learning methods into financial predictions (Gu et al. (2020); Bianchi et al. (2021); Bali et al. (2021)) . While accuracy has often been the primary focus in evaluating machine learning models in asset pricing, an equally critical factor that deserves attention is the machine learning model execution time. The concept of execution time, in the context of machine learning implementation, encompasses the temporal duration required to complete the entire lifecycle of a machine learning model. This includes critical phases, including model training, hyperparameter optimization, and evaluation during testing. To facilitate comprehension, we split this time into two main parts: training time and prediction time.  \nTime is an invaluable resource in the fast-paced world of finance, where timely decisions can lead to substantial gains or losses. The rapid evolution of financial markets demands real-time responses, and machine learning models that consume excessive time for training and prediction might miss critical market timing opportunities. Machine learning models that exhibit prolonged times may compromise the timeliness of decision-making, rendering their valuable insights less actionable.  \nBeyond market timing, the execution time of machine learning models carries economic implications. The cost of time encompasses multiple dimensions, including labor costs for analysts and the expenses associated with running resource-intensive computations. For example, high-performance computing (HPC) services often entail charges based on processing time, making efficient algorithms financially prudent. By optimizing the time, financial institutions can mitigate the financial burden associated with prolonged computation, ensuring that computational resources are used effectively.  \nThere are a large number of characteristics in empirical asset pricing, as is common in measuring equity risk premiums (e.g. , De Bondt and Thaler (1985); Fama and French (1992); Jegadeesh and Titman (1993); Amihud (2001); Ang et al. (2006); Daniel and Titman  \n(2006)) . The high dimensionality of financial data can a","cbCaiudadMIQqcIP","https://ap.wps.com/l/cbCaiudadMIQqcIP","pdf",843476,1,45,"English","en",105,"# Introduction\n## Execution time in machine learning for asset pricing\n## Time as a scarce resource in financial decision-making\n## Economic implications of execution time\n## Evaluation approach and modeling setup","[{\"question\":\"What does the paper mean by machine learning execution time in asset pricing?\",\"answer\":\"Execution time refers to the total time needed to complete a model’s lifecycle, including training, hyperparameter optimization, and testing evaluation. The study further splits it into training time and prediction time.\"},{\"question\":\"Which machine learning model performs best in the study?\",\"answer\":\"XGBoost stands out as the top performer, showing relatively low execution times and strong predictive accuracy. It reports an out-of-sample R2 of 0.78 and a Sharpe ratio of 1.76.\"},{\"question\":\"How can execution time be reduced according to the paper?\",\"answer\":\"The paper introduces two time-saving strategies: feature reduction and reducing the number of time observations used for training and prediction. These methods reduce execution time by up to 18 times and can slightly enhance investment performance.\"}]","Machine Learning Execution Time in Asset Pricing | PDF",1785673487,113,{"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},"machine-learning-execution-time-in-asset-pricing","",{"@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/machine-learning-execution-time-in-asset-pricing/117058/",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","2026-08-02",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 does the paper mean by machine learning execution time in asset pricing?","Question",{"text":75,"@type":76},"Execution time refers to the total time needed to complete a model’s lifecycle, including training, hyperparameter optimization, and testing evaluation. The study further splits it into training time and prediction time.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which machine learning model performs best in the study?",{"text":80,"@type":76},"XGBoost stands out as the top performer, showing relatively low execution times and strong predictive accuracy. It reports an out-of-sample R2 of 0.78 and a Sharpe ratio of 1.76.",{"name":82,"@type":73,"acceptedAnswer":83},"How can execution time be reduced according to the paper?",{"text":84,"@type":76},"The paper introduces two time-saving strategies: feature reduction and reducing the number of time observations used for training and prediction. These methods reduce execution time by up to 18 times and can slightly enhance investment performance.","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"]