[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-86368-en":3,"doc-seo-86368-105":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":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},86368,962075006959,"Anda","https://ap-avatar.wpscdn.com/avatar/e0002397efbe92a78e?_k=1776741047341049297",8,"Research & Report","From Confounding to Learning: Dynamic Service Fee Pricing on Third-Party Platforms","Dynamic service-fee pricing on third-party platforms is studied under strategic agents and informational asymmetry: platforms observe supply-side features and the realized clearing outcomes but not the demand curve. With revenue-maximization objectives and only transacted price–quantity data available, the problem becomes a confounded demand learning task. An algorithm is developed with an optimal regret bound (up to problem-dependent terms), showing that adaptive actions can act as instrumental variables. Efficiency bounds for deep neural networks are provided, and simulations with Talabat and Lyft offline counterfactuals evaluate potential revenue impacts.","arXiv :2512 .22749v2 [ cs .LG] 12 Jul 2026  \nFrom Confounding to Learning: Dynamic Service Fee Pricing on  \nThird-Party Platforms  \nRui Ai∗ David Simchi-Levi∗ Feng Zhu∗  \nJuly 14, 2026  \nAbstract  \nWe study the pricing behavior of third-party platforms facing strategic agents. Assuming the platform is a revenue maximizer, it observes market features that generally affect demand. Since only transacted quantities and prices can be observed, this presents a general demand learning problem under confounding. Mathematically, we develop an algorithm with optimal rleegarret ofnabilit( √T ∧of  demσa2d,) .leOuradingretsultso a prheavseealtrathnatsitisounpplyin re-sidegret . noiTescehfunicnadllaym, enwetallyshowaffectsthatnthonei.i.d. actions can serve as instrumental variables for learning demand. We also propose a novel homeomorphic construction that allows us to establish estimation bounds without assuming star-shapedness, providing the first efficiency guarantee for learning demand with deep neural networks. Finally, we use simulations and offline counterfactuals from Talabat and Lyft data to illustrate the potential revenue implications of our approach.  \n1 Introduction  \nThird-party platforms now intermediate millions of transactions every day across food delivery, ticket resale, ride-hailing, and electric-vehicle charging [Feldman et al., 2018, Pires, 2025] . Each of these platforms earns revenue not from the underlying goods but from a service fee levied on every transaction—the per-ticket service fee on Ticketmaster, the per-kWh surcharge on PlugShare (e.g. ,¥0.8/kWh at a Beijing station), the order-processing service fee on DoorDash. Setting this fee is a quintessential revenue-management problem: too high and price-sensitive consumers leave for a competitor, too low and the platform’s margin erodes [Gao, 2018, Hagiu, 2009, Lin et al., 2020] . Setting the fee well requires the platform to know how transacted quantity responds to price—that is, to learn the demand curve—yet, as we explain next, the very data the platform collects make this learning problem fundamentally harder than it appears. Figure 1 illustrates the phenomenon across three concrete markets.  \nWhat makes the platform’s pricing problem distinctive—and intellectually rich—is an asymmetry of information. The platform observes the supply side perfectly: DoorDash sees the menus  \n∗ MIT. Email: {ruiai, dslevi, [fengzhu](fengzhu}@mit.edu)[}](fengzhu}@mit.edu)[@mit.edu](fengzhu}@mit.edu) .  \nFigure 1: Examples of service fees in practice: ticket marketplaces, electric vehicle charging platforms, and food delivery services.  \nand prices that restaurants list, PlugShare sees the tiered electricity rates posted by station operators, Ticketmaster sees the ask prices of individual sellers. Yet it never observes the demand curve of the consumers who eventually transact. All it can record is the realized price Pte and quantity Qetat which the market clears, and these two quantities are jointly determined by supply, demand, and the service fee the platform itself just chose. Naively regressing Qet on Pte to recover demand thus inherits a textbook confounding problem: when supply is stable, the regression can even produce a positive slope, contradicting basic price theory.  \nThe standard remedy for confounded observational data is the use of instrumental variables (IV) [Angrist and Imbens, 1995, Angrist and Krueger, 2001, Newey and Powell, 2003] . In a platform market, however, valid instruments are scarce: there is no natural exogenous shock, no random encouragement design, no policy variation to exploit. Our central methodological observation is that the platform does not need to look outside its own decision loop—the very action it is trying to optimize, the service fee at itself, can be used as an instrument. Because the platform commits to at before the demand shock ϵDt realizes, the conditional orthogonality between at and ϵDt holdseven though at is dynamic and chosen ad","cbCaitMceKuonFi0","https://ap.wps.com/l/cbCaitMceKuonFi0","pdf",1566941,4,1,58,"English","en",105,"# Introduction\n## Pricing and information asymmetry in platform markets\n## Confounding and instrumental-variable remedies\n## Actions as instruments (self-instrumental) approach\n## Regret analysis and supply-side randomness\n## Implications for market volatility and exploration\n## Strategic buyers and robustness considerations","[{\"question\":\"What makes learning demand from platform transaction data fundamentally challenging?\",\"answer\":\"The platform only observes realized prices and quantities that clear, which are jointly determined by supply, demand, and the platform’s own chosen service fee. As a result, naively regressing quantity on price suffers from a confounding problem.\"},{\"question\":\"How does the paper address confounding when traditional instrumental variables are unavailable?\",\"answer\":\"It proposes an actions-as-instruments approach: the platform’s own adaptive service-fee decisions are used as instruments, relying on conditional orthogonality between actions and demand shocks despite adaptive, non-i.i.d. behavior.\"},{\"question\":\"What role does supply-side randomness play in the feasibility of learning demand?\",\"answer\":\"The paper shows that the structure and variance of supply shocks determine the learning difficulty. When supply-side randomness is sufficiently informative, the regret bound improves and learning can become efficient.\"}]",1784211062,146,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":28},"from-confounding-to-learning-dynamic-service-fee-pricing-on-third-party-platforms","",{"@graph":36,"@context":85},[37,53,68],{"@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":20},"https://docshare.wps.com/document/from-confounding-to-learning-dynamic-service-fee-pricing-on-third-party-platforms/86368/",{"url":52,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"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","2026-07-28","2026-07-16",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 makes learning demand from platform transaction data fundamentally challenging?","Question",{"text":75,"@type":76},"The platform only observes realized prices and quantities that clear, which are jointly determined by supply, demand, and the platform’s own chosen service fee. As a result, naively regressing quantity on price suffers from a confounding problem.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the paper address confounding when traditional instrumental variables are unavailable?",{"text":80,"@type":76},"It proposes an actions-as-instruments approach: the platform’s own adaptive service-fee decisions are used as instruments, relying on conditional orthogonality between actions and demand shocks despite adaptive, non-i.i.d. behavior.",{"name":82,"@type":73,"acceptedAnswer":83},"What role does supply-side randomness play in the feasibility of learning demand?",{"text":84,"@type":76},"The paper shows that the structure and variance of supply shocks determine the learning difficulty. When supply-side randomness is sufficiently informative, the regret bound improves and learning can become efficient.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"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":20,"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"]