[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85399-en":3,"doc-seo-85399-105":29,"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":13,"seo_description":14,"update_tm":27,"read_time":28},85399,1099513958607,"Jiven","https://ap-avatar.wpscdn.com/avatar/100002390cf8733938c?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778829742770036399",8,"Research & Report","Vehicle Rebalancing Under Adherence Uncertainty","Ride-hailing platforms often face spatial–temporal supply–demand mismatches from uneven passenger demand and decentralized, uncoordinated driver choices. Existing fleet rebalancing approaches typically assume drivers always follow recommendations, and recent adherence-aware work often uses static or sequential update assumptions. The Adherence-Aware Vehicle Rebalancing (AAVR) model generates simultaneous fleet-wide repositioning recommendations while explicitly modeling driver preferences and dynamically evolving adherence under uncertainty. An upper-bound relaxation yields a tractable, real-time optimization. Simulations on the NYC taxi dataset show AAVR improves served demand, reduces waiting time, raises platform and driver profits, and increases adherence probability.","arXiv :2412 . 16632v3 [ ee ss . SY] 12 Jul 2026  \nVehicle Rebalancing Under Adherence Uncertainty  \nAvalpreet Singh Brara,∗, Rong Sua , Christos G. Cassandrasb , Max Ngc ,  \nYuling Lid , Gioele Zardinie  \na School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore b Division of Systems Engineering, Boston University, USA  \nc Uber Technologies, Inc., San Francisco, CA, USA  \nd School of Automation and Electrical Engineering, University of Science and Technology Beijing, China e Laboratory for Information and Decision Systems, Massachusetts Institute of Technology, USA  \nAbstract  \nRide-hailing platforms frequently face spatiotemporal supply-demand imbalances caused by both uneven passenger demand across locations and decentralized, uncoordinated driver decision-making. To mitigate these inefficiencies, existing fleet rebalancing methods provide repositioning recommendations to idle drivers, but most assume that drivers always follow the assigned recommendations. Some recent studies relax this assumption by incorporating driver destination preferences or modeling adherence using static adherence probabilities. In reality, driver adherence evolves dynamically through repeated interactions with the recommender system. Existing adherence-aware methods typically generate recommendations sequentially by updating recommendations after observing each driver’s response and do not jointly capture driver preferences, dynamically evolving adherence, and simultaneous fleet-wide recommendation generation. We address this gap through the proposed Adherence-Aware Vehicle Rebalancing (AAVR) model, which generates simultaneous fleetwide repositioning recommendations while explicitly accounting for driver preferences and dynamically evolving adherence. This formulation gives rise to a computationally intractable optimization problem. We derive a tractable reformulation based on an upper-bound relaxation, enabling real-time recommendation generation for large-scale ride-hailing systems. Extensive simulations on the NYC taxi dataset under dynamic adherence updates demonstrate that AAVR consistently outperforms state-of-the-art vehicle rebalancing strategies, improving served demand by 26.72%, reducing passenger waiting time by 26.45%, increasing platform and driver profits by 25.90% and 28.75%, respectively, and improving the fleet’s adherence probability by 30 .06% . These results demonstrate that explicitly accounting for evolving driver adherence improves both immediate operational performance and longerterm adherence to platform recommendations.  \nKeywords: vehicle rebalancing, human factors, adherence dynamics  \nPreprint submitted to Transportation Research Part C: Emerging Technologies July 14, 2026  \n1. Introduction  \nUrban mobility systems face persistent congestion and inefficient use of road resources, particularly as travel demand becomes increasingly concentrated across space and time. Ride-hailing services offer a flexible Mobility-on-Demand (MoD) solution, yet their performance is fundamentally constrained by spatiotemporal supply–demand imbalances (Zardiniet al. , 2022) . Vehicle rebalancing aims to address this issue by repositioning idle drivers to locations with anticipated demand shortages. Most existing rebalancing models assume full driver compliance with platform recommendations. In practice, however, drivers may acceptor reject these suggestions based on individual destination preferences and their trust in the recommender system. Moreover, such trust is not static but evolves over time in response to past experiences. To capture these behavioral dynamics, we propose an Adherence-Aware Vehicle Rebalancing (AAVR) framework that incorporates driver-level adherence decisions and explicitly accounts for uncertainty in realized supply.  \n1.1. Literature Review  \nVehicle rebalancing has been widely studied as a core mechanism for mitigating spatial supply–demand imbalance in mobility-on-demand sys","cbCaiciI5mwMchRg","https://ap.wps.com/l/cbCaiciI5mwMchRg","pdf",1400144,1,34,"English","en",105,"# Introduction\n## Literature Review","[{\"question\":\"What problem does AAVR address in ride-hailing fleets?\",\"answer\":\"AAVR targets spatiotemporal supply–demand imbalances caused by uneven passenger demand and decentralized driver decision-making that may not match platform recommendations.\"},{\"question\":\"How does AAVR differ from prior adherence-aware rebalancing methods?\",\"answer\":\"AAVR jointly captures driver preferences, dynamically evolving adherence, and simultaneous fleet-wide recommendation generation, rather than generating recommendations sequentially with static or simplified adherence modeling.\"},{\"question\":\"What evidence shows AAVR’s effectiveness?\",\"answer\":\"Extensive simulations on the NYC taxi dataset under dynamic adherence updates show AAVR outperforms state-of-the-art strategies by increasing served demand, reducing passenger waiting time, improving platform and driver profits, and raising fleet adherence probability.\"}]",1784203133,86,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"vehicle-rebalancing-under-adherence-uncertainty","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/vehicle-rebalancing-under-adherence-uncertainty/85399/",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":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","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 problem does AAVR address in ride-hailing fleets?","Question",{"text":75,"@type":76},"AAVR targets spatiotemporal supply–demand imbalances caused by uneven passenger demand and decentralized driver decision-making that may not match platform recommendations.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does AAVR differ from prior adherence-aware rebalancing methods?",{"text":80,"@type":76},"AAVR jointly captures driver preferences, dynamically evolving adherence, and simultaneous fleet-wide recommendation generation, rather than generating recommendations sequentially with static or simplified adherence modeling.",{"name":82,"@type":73,"acceptedAnswer":83},"What evidence shows AAVR’s effectiveness?",{"text":84,"@type":76},"Extensive simulations on the NYC taxi dataset under dynamic adherence updates show AAVR outperforms state-of-the-art strategies by increasing served demand, reducing passenger waiting time, improving platform and driver profits, and raising fleet adherence probability.","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},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":45,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":45,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":45,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]