[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-81978-en":3,"doc-seo-81978-105":30,"detail-sidebar-cat-0-en-105":92},{"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":13,"seo_description":14,"update_tm":28,"read_time":29},81978,1099514068035,"Ezra","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Large Behavior Model A Promptable Digital Twin of the Retail Customer","Customer behavior modeling underpins recommendation, marketing, and decision support, yet many methods either prioritize prediction accuracy without explaining decisions or simulate users without grounding them in observed behavioral data. This work introduces a Large Behavioral Model (LBM) that learns customer decision making from large-scale retail transactions using a unified Person–Environment formulation. Customer state is built from historical purchasing profiles, while product context is incorporated via retrieval-augmented generation. Training combines continued pre-training, supervised decision generation, and reinforcement learning with verifiable rewards for evidence-based calibration.","arXiv :2607 .06993v2 [ cs .AI] 10 Jul 2026  \nLarge Behavior Model: A Promptable Digital Twin of  \nthe Retail Customer  \nWachiravit Modecrua, Krittin Pachtrachai, Touchapon Kraisingkorn Amity Research and Application Center (ARAC),  \nAmity AI Holdings Co. , Ltd.  \n{wachiravit, krittin, [touchapon}@amity.co](touchapon}@amity.co)  \nJuly 13, 2026  \nAbstract  \nCustomer behavior modeling underpins recommendation, marketing, and decision support, yet existing approaches either optimize predictive accuracy without explaining decisions or simulate users without grounding them in real behavioral data. We present the Large Behavioral Model (LBM) that learns customer decision making directly from large-scale retail transactions through a unified Person–Environment formulation. Customer state is represented by a behavioral profile derived from historical purchases, while product context is incorporated through retrieval-augmented generation. The model is trained using continued pre-training on verbalized behavioral data, supervised fine-tuning for decision generation, and reinforcement learning with verifiable rewards for evidence-based calibration.  \nWe evaluate the proposed framework on purchase prediction, hard-negative discrimination, basket completion, promotion response, and cross-domain voucher redemption. The model consistently outperforms frontier general-purpose language models on in-domain retail tasks while demonstrating strong zero-shot and fine-tuned transfer across retailers and decision domains. Ablation studies show that continued pre-training is the primary driver of behavioral generalization, retrieval is most effective when applied during both training and inference, and reinforcement learning improves reliance on explicit behavioral evidence over generic language-model priors. These results demonstrate that behavioral knowledge encoded in transaction histories can be effectively learned by language models, providing a scalable foundation for customer digital twins and behavior simulation.  \n1 Introduction  \nUnderstanding and predicting human decision-making is a long-standing problem in fields including economics, marketing, recommender systems, and artificial intelligence. Accurate behavioral models enable a wide range of applications, such as personalized recommendation, demand forecasting, promotion planning, pricing optimization, and market research [1–3] . Despite decades of research, faithfully modeling the behavior of an individual remains challenging because decisions arise from the interaction between relatively stable personal preferences and the context in which choices are made. This perspective is consistent with Lewin’s field theory, which characterizes behavior as a function of both the person and the environment [4] . Consequently, models that capture only population-level patterns often fail to explain why two seemingly similar customers make different decisions under the same circumstances.  \nIn retail, this challenge is particularly evident. Large retailers routinely make pricing, promotion, and assortment decisions for millions of customers, yet their understanding of customer preferences is still largely informed by surveys, focus groups, and consumer panels [3,5] . Although these methods remain indispensable in marketing research, they are expensive, slow to update, and typically cover only a small fraction of the customer population. More importantly, stated preferences collected through questionnaires often differ from revealed preferences observed through actual purchasing behavior, motivating the increasing use of transaction data for behavioral modeling [6] . Consequently, retailers possess abundant behavioral data but relatively limited tools for transforming those observations into faithful simulations of individual customer decisions.  \nTo address this limitation, previous research has developed a wide range of behavioral models. Classical discrete choice models estimate purchasing probabi","cbCairiddyIHeBT7","https://ap.wps.com/l/cbCairiddyIHeBT7","pdf",398467,7,1,17,"English","en",105,"# Abstract\n# 1 Introduction","[{\"question\":\"What problem does the Large Behavioral Model (LBM) address in customer behavior modeling?\",\"answer\":\"LBM targets the gap where existing approaches either optimize predictive accuracy without explaining decisions or simulate users without grounding them in real behavioral data from retail transactions.\"},{\"question\":\"How does LBM represent customer state and incorporate product context?\",\"answer\":\"Customer state is represented by a behavioral profile derived from historical purchases, and product context is integrated through retrieval-augmented generation.\"},{\"question\":\"Which training strategies are used to improve evidence-based decision generation?\",\"answer\":\"LBM uses continued pre-training on verbalized behavioral data, supervised fine-tuning for decision generation, and reinforcement learning with verifiable rewards to calibrate toward explicit behavioral evidence.\"}]",1784177387,43,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"large-behavior-model-a-promptable-digital-twin-of-the-retail-customer","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":21},"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/large-behavior-model-a-promptable-digital-twin-of-the-retail-customer/81978/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04","2026-07-16",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What problem does the Large Behavioral Model (LBM) address in customer behavior modeling?","Question",{"text":76,"@type":77},"LBM targets the gap where existing approaches either optimize predictive accuracy without explaining decisions or simulate users without grounding them in real behavioral data from retail transactions.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does LBM represent customer state and incorporate product context?",{"text":81,"@type":77},"Customer state is represented by a behavioral profile derived from historical purchases, and product context is integrated through retrieval-augmented generation.",{"name":83,"@type":74,"acceptedAnswer":84},"Which training strategies are used to improve evidence-based decision generation?",{"text":85,"@type":77},"LBM uses continued pre-training on verbalized behavioral data, supervised fine-tuning for decision generation, and reinforcement learning with verifiable rewards to calibrate toward explicit behavioral evidence.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},"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":107,"slug":138},19,"General","general"]