[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122816-en":3,"doc-seo-122816-105":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":4,"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},122816,3848291630094,"Emma Wilson","https://eur-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45",8,"Research & Report","Popularity, face and voice: Predicting and interpreting livestreamers' retail performance using machine learning techniques","Livestreaming commerce, a hybrid of e-commerce and self-media, reshapes traditional drivers of sales performance. This work builds a longitudinal firm-level dataset with 19,175 observations across an entire livestreaming subsector to study what drives success. Eight machine learning models are benchmarked for forecasting gross merchandise volume (GMV), with random forest achieving the highest accuracy. Explainable AI then reveals key role of event popularity, gender-specific differences between voice and appearance, uneven valuation of voice attributes, and three sales-growth stages linked to comment and engagement dynamics. A 3D-SHAP diagram further connects feature importance with predictors and the target variable.","Popularity, face and voice: Predicting and interpreting livestreamers’retail performance using machine learning techniques  \nXiong Xiong 1,3 , Fan Yang2 , Li Su3, *  \n1. School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, China  \n2. School of Economics and Management, Southeast University, Nanjing 211189, China  \n3. Department of Neuroscience, University of Sheffield, Sheffield S10 2TN, UK Corresponding author: Li Su  \nAbstract: Livestreaming commerce, a hybrid of e-commerce and self-media, has expanded the broad spectrum of traditional sales performance determinants. To investigate the factors that contribute to the success of livestreaming commerce, we construct a longitudinal firm-level database with 19,175 observations, covering an entire livestreaming subsector. By comparing the forecasting accuracy of eight machine learning models, we identify a random forest model that provides the best prediction of gross merchandise volume (GMV) . Furthermore, we utilize explainable artificial intelligence to open the black-box of machine learning model, discovering four new facts: 1) variables representing the popularity of livestreaming events are crucial features in predicting GMV. And voice attributes are more important than appearance; 2) popularity is a major determinant of sales for female hosts, while vocal aesthetics is more decisive for their male counterparts; 3) merits and drawbacks of the voice are not equally valued in the livestreaming market; 4) based on changes of comments, page views and likes, sales growth can be divided into three stages. Finally, we innovatively propose a 3D-SHAP diagram that demonstrates the relationship between predicting feature importance, target variable, and its predictors. This diagram identifies bottlenecks for both beginner and top livestreamers, providing insights into ways to optimize their sales performance.  \nKeywords: Livestreaming; Machine Learning; Forecasting; Popularity; Physical Attraction; Voice  \n1. Introduction  \nFrom traditional physical distribution to online shopping and now to e-commerce live streaming, the retail economy has undergone three wave of reforms (Zhang et al., 2023) . Livestreaming commerce is distinct from its predecessors as it carries the characteristics of both E-commerce and self-media (Aytan, 2021), potentially extending the spectrum of historical determinants of sales performance (Verbeke, 1997)(Chawla et al., 2020) . Unlike traditional retailers, livestreamers can conduct parasocial interactions via digital platform, thus building relationships with numerous potential buyers simultaneously. In comparison to traditional e-commerce, the physical appearance and voice of broadcasters may evoke anaesthetic and intimate feeling among customers, which can enhance their customer loyalty and stimulate their willingness to purchase.  \nThe nexus of livestreaming literature is Gross Merchandise Volume (GMV) and its determinants. By investigating the factors that contribute to GMV, researchers and practitioners can gain valuable insights into the underlying mechanisms of consumer behavior in the context of livestreaming ecommerce, as well as develop effective strategies to improve sales performance and predict the revenue of a live broadcast. Table 1 provides detailed information on the literature that focuses on livestreaming commerce.  \nTable 1  \nLiterature review of e-commerce live streaming (ELS) .  \n\n| Author | Topic | Main potential influencer | Data source | Obser\u003Cbr>vations | Methods |\n| --- | --- | --- | --- | --- | --- |\n| (Liu et al., 2022) | Investigates the effects of live-streaming interactivity, authenticity, and entertainment on purchase intention in the field ofELS | Interactivity, authenticity, and entertainment ofELS | Questionnaire | 357 | SOR |\n| (Xu et al., 2021) | Investigates the ways in which live streaming impacts consumer purchasing intentions in the cross-border ELS | A","cbCaikz69xQlvkkk","https://ap.wps.com/l/cbCaikz69xQlvkkk","pdf",1663935,1,25,"English","en",105,"# Introduction\n# Literature review of e-commerce live streaming (ELS)\n## Determinants of purchase intention and engagement","[{\"question\":\"How is livestreaming commerce different from earlier retail and e-commerce models in this study?\",\"answer\":\"Livestreaming commerce combines e-commerce and self-media characteristics, and streamers create parasocial interactions that build relationships with many potential buyers simultaneously.\"},{\"question\":\"Which machine learning model performs best for predicting GMV?\",\"answer\":\"The study compares eight models and identifies random forest as the best predictor of gross merchandise volume (GMV).\"},{\"question\":\"What does explainable AI reveal about the roles of popularity and voice/appearance?\",\"answer\":\"Explainable AI highlights that popularity features are crucial, voice attributes can be more important than appearance, popularity strongly affects female hosts’ sales, while vocal aesthetics matter more for male counterparts.\"}]","Popularity, face and voice: Predicting and interpreting livestreamers' retail performance using machine learning techniques | PDF",1785813061,63,{"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},"popularity-face-and-voice-predicting-and-interpreting-livestreamers-retail-performance-using-machine-learning-techniques","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"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/popularity-face-and-voice-predicting-and-interpreting-livestreamers-retail-performance-using-machine-learning-techniques/122816/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"How is livestreaming commerce different from earlier retail and e-commerce models in this study?","Question",{"text":75,"@type":76},"Livestreaming commerce combines e-commerce and self-media characteristics, and streamers create parasocial interactions that build relationships with many potential buyers simultaneously.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which machine learning model performs best for predicting GMV?",{"text":80,"@type":76},"The study compares eight models and identifies random forest as the best predictor of gross merchandise volume (GMV).",{"name":82,"@type":73,"acceptedAnswer":83},"What does explainable AI reveal about the roles of popularity and voice/appearance?",{"text":84,"@type":76},"Explainable AI highlights that popularity features are crucial, voice attributes can be more important than appearance, popularity strongly affects female hosts’ sales, while vocal aesthetics matter more for male counterparts.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"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":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":53,"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"]