LLM for Secure Reserve Price Optimization in Real-time Bidding

LLM for Secure Reserve Price Optimization in Real-time Bidding | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article LLM for Secure Reserve Price Optimization in Real-time Bidding Wendi Wu, Shanghua Wen, Minglong Li, Kun Hu, Yongjun Dai, Jing Zhao* This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6765381/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 11 You are reading this latest preprint version Abstract Real-time bidding (RTB) plays a crucial role in display advertising, where ad exchanges (ADXs) set reserve prices to initiate auctions among demand-side platforms (DSPs). The optimization of reserve prices is critical for publishers, as it directly impacts revenue generation and market efficiency. However, existing research predominantly assumes fixed DSP bidding strategies, which fails to account for the dynamic nature of real-world scenarios where DSP behaviors evolve due to budget constraints, market fluctuations, and competitive dynamics, etc. This discrepancy between theoretical models and practical challenges underscores the need for more effective reserve price optimization methods. In this paper, we address this gap by proposing a novel framework that integrates large language models (LLMs) into the reward shaping process of reinforcement learning (RL). All user data utilized in this study underwent rigorous anonymization and complied with GDPR-aligned privacy protocols during collection and processing. Our approach leverages the advanced comprehension and reasoning capabilities of LLMs to design and fine-tune reward structures, enabling RL algorithms to respond effectively to diverse and dynamic DSP bidding strategies. We validate our method using real-world transaction data from CAINIAO's operational environment. Security-preserving mechanisms were implemented throughout the experimental pipeline to ensure transactional data integrity and prevent unauthorized access. Experimental results demonstrate that our framework achieves a 21.51% improvement in average income compared to state-of-the-art methods. Large language model Reinforcement learning Reward shaping Real-time bidding Display advertising Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 13 Aug, 2025 Reviews received at journal 16 Jun, 2025 Reviews received at journal 16 Jun, 2025 Reviews received at journal 09 Jun, 2025 Reviewers agreed at journal 04 Jun, 2025 Reviewers agreed at journal 04 Jun, 2025 Reviewers agreed at journal 02 Jun, 2025 Reviewers invited by journal 02 Jun, 2025 Editor assigned by journal 31 May, 2025 Submission checks completed at journal 30 May, 2025 First submitted to journal 28 May, 2025 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-6765381","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":464995332,"identity":"8d73e922-31f6-4639-ada0-588cd357446b","order_by":0,"name":"Wendi Wu","email":"","orcid":"","institution":"National University of Defense Technology","correspondingAuthor":false,"prefix":"","firstName":"Wendi","middleName":"","lastName":"Wu","suffix":""},{"id":464995334,"identity":"8043b6a4-05b1-48dc-abac-f338c63d4322","order_by":1,"name":"Shanghua Wen","email":"","orcid":"","institution":"National University of Defense Technology","correspondingAuthor":false,"prefix":"","firstName":"Shanghua","middleName":"","lastName":"Wen","suffix":""},{"id":464995335,"identity":"5533c2bd-c827-4e60-b4b7-02318fbb09aa","order_by":2,"name":"Minglong Li","email":"","orcid":"","institution":"National University of Defense Technology","correspondingAuthor":false,"prefix":"","firstName":"Minglong","middleName":"","lastName":"Li","suffix":""},{"id":464995336,"identity":"c4734238-af6d-4b0f-ac2b-c275dcc45c98","order_by":3,"name":"Kun Hu","email":"","orcid":"","institution":"National University of Defense Technology","correspondingAuthor":false,"prefix":"","firstName":"Kun","middleName":"","lastName":"Hu","suffix":""},{"id":464995337,"identity":"a2f39c30-fd68-4a2a-9669-3ac6399e2a9f","order_by":4,"name":"Yongjun Dai","email":"","orcid":"","institution":"National University of Defense Technology","correspondingAuthor":false,"prefix":"","firstName":"Yongjun","middleName":"","lastName":"Dai","suffix":""},{"id":464995338,"identity":"963f7726-cee9-45bc-a993-8902228c5f5b","order_by":5,"name":"Jing Zhao*","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA5ElEQVRIiWNgGAWjYDACCRA2YGDgh7IZG4jWIglUKnGAaC0gYHCAWC3ys5sfPrAouGO3+XaP4e0PDDayGw4wP3uATwvjnGPGBhIGz5K33TljbHGAIc14wwE2cwN8WpglEswkJAwOJ5vdyDEDOuxw4oYDPGwS+LSwSaR/A2sxngHW8p+wFh6JHLAtdgYSYC0HCGuRkMgpBvrlcILEjbRiizMGycYzD7OZ4dUiPyN942OJP4ft+Wckb7xRUWEn23e8+RleLSDADFSR2ABmgoKKmZB6IGD8wMBgT4S6UTAKRsEoGKkAAGpHR6Oni6P9AAAAAElFTkSuQmCC","orcid":"","institution":"National University of Defense Technology","correspondingAuthor":true,"prefix":"","firstName":"Jing","middleName":"","lastName":"Zhao*","suffix":""}],"badges":[],"createdAt":"2025-05-28 07:38:14","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6765381/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6765381/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":83877966,"identity":"aeedd223-a2fe-4c5b-9b78-b64990538170","added_by":"auto","created_at":"2025-06-04 04:09:26","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1359539,"visible":true,"origin":"","legend":"","description":"","filename":"LLMforRTBIJMLCnew.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6765381/v1_covered_7f95d184-f960-4f9e-8afb-194d5ae6b5a9.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"LLM for Secure Reserve Price Optimization in Real-time Bidding","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"international-journal-of-machine-learning-and-cybernetics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jmlc","sideBox":"Learn more about [International Journal of Machine Learning and Cybernetics](http://actavetscand.biomedcentral.com/)","snPcode":"13042","submissionUrl":"https://submission.nature.com/new-submission/13042/3","title":"International Journal of Machine Learning and Cybernetics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Large language model, Reinforcement learning, Reward shaping, Real-time bidding, Display advertising","lastPublishedDoi":"10.21203/rs.3.rs-6765381/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6765381/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eReal-time bidding (RTB) plays a crucial role in display advertising, where ad exchanges (ADXs) set reserve prices to initiate auctions among demand-side platforms (DSPs). The optimization of reserve prices is critical for publishers, as it directly impacts revenue generation and market efficiency. However, existing research predominantly assumes fixed DSP bidding strategies, which fails to account for the dynamic nature of real-world scenarios where DSP behaviors evolve due to budget constraints, market fluctuations, and competitive dynamics, etc. This discrepancy between theoretical models and practical challenges underscores the need for more effective reserve price optimization methods. In this paper, we address this gap by proposing a novel framework that integrates large language models (LLMs) into the reward shaping process of reinforcement learning (RL). All user data utilized in this study underwent rigorous anonymization and complied with GDPR-aligned privacy protocols during collection and processing. Our approach leverages the advanced comprehension and reasoning capabilities of LLMs to design and fine-tune reward structures, enabling RL algorithms to respond effectively to diverse and dynamic DSP bidding strategies. We validate our method using real-world transaction data from CAINIAO's operational environment. Security-preserving mechanisms were implemented throughout the experimental pipeline to ensure transactional data integrity and prevent unauthorized access. Experimental results demonstrate that our framework achieves a 21.51% improvement in average income compared to state-of-the-art methods.\u003c/p\u003e","manuscriptTitle":"LLM for Secure Reserve Price Optimization in Real-time Bidding","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-06-04 03:45:17","doi":"10.21203/rs.3.rs-6765381/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-08-14T03:19:24+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-17T01:27:54+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-16T07:48:58+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-10T02:43:05+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"277126721217663075484911293422529218047","date":"2025-06-05T01:26:34+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"74028220354023658002616797620187788480","date":"2025-06-05T01:21:36+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"47384391986689465368526292202175369250","date":"2025-06-02T04:43:24+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-06-02T04:35:30+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-05-31T08:13:30+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-05-31T03:02:28+00:00","index":"","fulltext":""},{"type":"submitted","content":"International Journal of Machine Learning and Cybernetics","date":"2025-05-28T07:24:48+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"international-journal-of-machine-learning-and-cybernetics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jmlc","sideBox":"Learn more about [International Journal of Machine Learning and Cybernetics](http://actavetscand.biomedcentral.com/)","snPcode":"13042","submissionUrl":"https://submission.nature.com/new-submission/13042/3","title":"International Journal of Machine Learning and Cybernetics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"bac0116c-b8eb-467d-92b4-a9e59d17faad","owner":[],"postedDate":"June 4th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2025-09-09T06:38:42+00:00","versionOfRecord":[],"versionCreatedAt":"2025-06-04 03:45:17","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6765381","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6765381","identity":"rs-6765381","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}