[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119507-en":3,"doc-seo-119507-105":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":20,"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},119507,13056703019662,"Evangeline","https://ap-avatar.wpscdn.com/avatar/be000253a8e92610077?_k=1778726343310543188",8,"Research & Report","Analyzing Option Chain Bid–Ask Spreads with Machine Learning - Conference Paper","This paper investigates the determinants of option bid–ask spreads using machine learning techniques. A cross-sectional dataset of Apple Inc. (AAPL) call options is used with relative bid–ask spread as the target variable. Linear models are compared with ensemble methods including Random Forests and XGBoost, and nonlinear approaches achieve substantially higher out-of-sample fit. The most influential variables are moneyness, implied volatility, and time to expiration, while volume and open interest add limited incremental predictive power. Findings link spread behavior to market microstructure, capital constraints, and regulatory requirements such as FINRA Rule 4210.","Technological University Dublin  \nARROW@TU Dublin  \n\n| SAML-25 Workshop on Statistical and Machine Learning | Research Institutes/Centres/Groups |\n| --- | --- |\n| 2025-06-05\u003Cbr>Analyzing Option Chain Bid–Ask Spreads with Machine Learning\u003Cbr>Brian Byrne\u003Cbr>Technological University Dublin, College of Business, [brian.byrne@tudublin.ie](brian.byrne@tudublin.ie)\u003Cbr>Qianru Shang\u003Cbr>Technological University Dublin, College of Business, [qianru.shang@tudublin.ie](qianru.shang@tudublin.ie)\u003Cbr>Follow this and additional works at: [https://arrow.tudublin.ie/saml](https://arrow.tudublin.ie/saml)\u003Cbr> Part of the Statistics and Probability Commons |  |\n\nRecommended Citation  \nByrne, Brian and Shang, Qianru, \"Analyzing Option Chain Bid–Ask Spreads with Machine Learning\" (2025) . SAML-25 Workshop on Statistical and Machine Learning. 3.  \n[https://arrow.tudublin.ie/saml/3](https://arrow.tudublin.ie/saml/3)  \nThis Conference Paper is brought to you by the EUt+ Academic Press a free to read and publish press of the European University of Technology.  \nThis work is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 4.0 International License.  \nAnalyzing Option Chain Bid–Ask Spreads with Machine Learning  \nBrian Byrne  \n[brian.byrne@tudublin.ie](brian.byrne@tudublin.ie)[ ](brian.byrne@tudublin.ie)Technological University Dublin Dept. of Accounting, Economics and Finance Dublin, Ireland  \nQianru Shang  \n[qianru.shang@tudublin.ie](qianru.shang@tudublin.ie)[ ](qianru.shang@tudublin.ie)Technological University Dublin Department of Management Dublin, Ireland  \nAbstract  \nThis paper investigates the determinants of option bid–ask spreads using machine learning techniques. We analyze a cross-sectional dataset of Apple Inc. (AAPL) call options, focusing on the relative bid–ask spread as the target variable. By comparing linear models with ensemble methods such as Random Forests and XGBoost, we find that nonlinear machine learning methods significantly outperform traditional OLS regression. The most influential factors are moneyness, implied volatility, and time to expiration, while volume and open interest have limited predictive power. Results suggest that spreads are driven by a mix of market microstructure dynamics, capital constraints, and regulatory requirements such as FINRA Rule 4210 . Our findings highlight the value of ML in financial microstructure modeling and offer insights relevant to traders, regulators, and liquidity providers.  \nKeywords  \nOption markets, Bid–ask spread, Moneyness, Liquidity, Machine learning, Market microstructure  \n1 Introduction  \nOption markets exhibit both pricing complexity and liquidity frictions. The bid–ask spread serves as a transaction cost and a proxy for liquidity. While equity market spreads are well understood, options introduce additional complexities due to strike granularity, hedging costs, and capital requirements.  \nFor example, margin rules from FINRA and the OCC impose significant capital charges on uncovered positions, particularly in deep out-of-the-money (DOTM) options, distorting liquidity provision. We study these features empirically using AAPL call options data and show how machine learning (ML) models can reveal hidden nonlinear relationships not captured by linear regression.  \n2 Data and Methodology  \nWe collect end-of-day AAPL call option data from Yahoo Finance for April 1, 2025 . The dataset includes roughly 1,000 contracts across a wide spectrum of strike prices and maturities. The target variable is the relative bid–ask spread, computed as (ask−bid)/mid, a percentage spread commonly used in liquidity research.  \nKey explanatory variables include:  \n• Moneyness (􀀨/􀀠 ): Options near-the-money are expected to have lower spreads.  \n• Days to Expiration (DTE): Short-dated options often display wider spreads.  \n• Implied Volatility (IV): Higher IV can signal hedging difficulty or asymmetric information.  \n• Volume and Open Interest (OI): Conventional liquidity proxies.  ","cbCaigpGnHlEKZQx","https://ap.wps.com/l/cbCaigpGnHlEKZQx","pdf",377938,1,2,"English","en",105,"# Introduction\n# Data and Methodology\n# Results and Discussion\n# Conclusion\n# References","[{\"question\":\"What is the main objective of the study?\",\"answer\":\"The study examines what drives option bid–ask spreads and evaluates whether machine learning can uncover relationships missed by linear regression.\"},{\"question\":\"How is the target variable for prediction defined?\",\"answer\":\"The target is the relative bid–ask spread, computed as (ask−bid)/mid, expressed as a percentage commonly used in liquidity research.\"},{\"question\":\"Which model types outperform OLS, and why?\",\"answer\":\"Random Forests and XGBoost outperform OLS by capturing nonlinear interactions and threshold effects across option contracts.\"}]","Analyzing Option Chain Bid–Ask Spreads with Machine Learning - Conference Paper | PDF",1785724698,5,{"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},"analyzing-option-chain-bidask-spreads-with-machine-learning-conference-paper","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,47,50],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":21},"https://docshare.wps.com/document/","Document",{"item":48,"name":12,"@type":43,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/analyzing-option-chain-bidask-spreads-with-machine-learning-conference-paper/119507/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-04","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What is the main objective of the study?","Question",{"text":75,"@type":76},"The study examines what drives option bid–ask spreads and evaluates whether machine learning can uncover relationships missed by linear regression.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is the target variable for prediction defined?",{"text":80,"@type":76},"The target is the relative bid–ask spread, computed as (ask−bid)/mid, expressed as a percentage commonly used in liquidity research.",{"name":82,"@type":73,"acceptedAnswer":83},"Which model types outperform OLS, and why?",{"text":84,"@type":76},"Random Forests and XGBoost outperform OLS by capturing nonlinear interactions and threshold effects across option contracts.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,109,114,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":29,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"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":29,"slug":137},19,"General","general"]