Pub Date : 2025-11-01Epub Date: 2025-11-12DOI: 10.1016/j.elerap.2025.101559
Pengcheng Liu, Jian Liu, Chunlin Luo
This study investigates an ex-post regulation policy to curb deceptive advertising in live-streaming selling. We develop a two-period game model incorporating post-purchase returns () and customer churn () to evaluate three advertising strategies: normal advertising in both periods without deception (); deception occurred in the second period (); and deception occurred in both periods (). We assess the efficacy of e-platform’s “Triple Compensation for Counterfeits” (TCC) policy to curb deceptive advertising. Furthermore, we examined the impact of shared liability on the efficacy of the “TCC” policy. The findings reveal that: (1) deceptive advertising increases with streamers’ influence, but decreases with commission rates. External penalties proved relatively inefficient. (2) The “TCC” policy eliminates , reduces ’s prevalence, yet fails to eradicate . (3) Shared liability weakens TCC’s efficacy, allowing to reemerge in equilibrium—though deceptive advertising remains less frequent than benchmark. The results provide a more reasonable plan for the platform to select regulatory objects.
{"title":"Evaluating the triple compensation for counterfeits policy: mitigating deceptive advertising in live-streaming selling","authors":"Pengcheng Liu, Jian Liu, Chunlin Luo","doi":"10.1016/j.elerap.2025.101559","DOIUrl":"10.1016/j.elerap.2025.101559","url":null,"abstract":"<div><div>This study investigates an ex-post regulation policy to curb deceptive advertising in live-streaming selling. We develop a two-period game model incorporating post-purchase returns (<span><math><mi>r</mi></math></span>) and customer churn (<span><math><mi>k</mi></math></span>) to evaluate three advertising strategies: normal advertising in both periods without deception (<span><math><mrow><mi>NN</mi></mrow></math></span>); deception occurred in the second period (<span><math><mrow><mi>NF</mi></mrow></math></span>); and deception occurred in both periods (<span><math><mrow><mi>FF</mi></mrow></math></span>). We assess the efficacy of e-platform’s “Triple Compensation for Counterfeits” (TCC) policy to curb deceptive advertising. Furthermore, we examined the impact of shared liability on the efficacy of the “TCC” policy. The findings reveal that: (1) deceptive advertising increases with streamers’ influence, but decreases with commission rates. External penalties proved relatively inefficient. (2) The “TCC” policy eliminates <span><math><mrow><mi>FF</mi></mrow></math></span>, reduces <span><math><mrow><mi>NF</mi></mrow></math></span>’s prevalence, yet fails to eradicate <span><math><mrow><mi>NF</mi></mrow></math></span>. (3) Shared liability weakens TCC’s efficacy, allowing <span><math><mrow><mi>FF</mi></mrow></math></span> to reemerge in equilibrium—though deceptive advertising remains less frequent than benchmark. The results provide a more reasonable plan for the platform to select regulatory objects.</div></div>","PeriodicalId":50541,"journal":{"name":"Electronic Commerce Research and Applications","volume":"74 ","pages":"Article 101559"},"PeriodicalIF":6.3,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145571234","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-11-01Epub Date: 2025-10-10DOI: 10.1016/j.elerap.2025.101550
Xi Chen , Hongying Du , Pengxin Zheng , Jian Mou
Technological advancements and the extensive collection of personal data have made the concept of information sensitivity increasingly significant. It has deeply permeated discussions on prominent topics such as privacy risks, data classification governance, and information security. Understanding the causes, mechanisms, and consequences of information sensitivity is of crucial importance. However, research findings on this topic remain fragmented, and conclusive results are lacking. This study aims to clarify the definition of information sensitivity in the digital age, synthesize relevant existing results, review its conceptual foundations and related methodologies, and provide suggestions for subsequent research. We reviewed the information systems literature to outline the dimensions, measurement methods, influencing factors, and consequences of information sensitivity. Our analysis reveals the research approaches and elements that shape information sensitivity. To guide future research, we propose an integrative framework regarding information sensitivity in the digital age, with a focus on AI-driven e-commerce scenarios.
{"title":"Understanding information sensitivity in the digital era: A literature analysis and future research agenda","authors":"Xi Chen , Hongying Du , Pengxin Zheng , Jian Mou","doi":"10.1016/j.elerap.2025.101550","DOIUrl":"10.1016/j.elerap.2025.101550","url":null,"abstract":"<div><div>Technological advancements and the extensive collection of personal data have made the concept of information sensitivity increasingly significant. It has deeply permeated discussions on prominent topics such as privacy risks, data classification governance, and information security. Understanding the causes, mechanisms, and consequences of information sensitivity is of crucial importance. However, research findings on this topic remain fragmented, and conclusive results are lacking. This study aims to clarify the definition of information sensitivity in the digital age, synthesize relevant existing results, review its conceptual foundations and related methodologies, and provide suggestions for subsequent research. We reviewed the information systems literature to outline the dimensions, measurement methods, influencing factors, and consequences of information sensitivity. Our analysis reveals the research approaches and elements that shape information sensitivity. To guide future research, we propose an integrative framework regarding information sensitivity in the digital age, with a focus on AI-driven e-commerce scenarios.</div></div>","PeriodicalId":50541,"journal":{"name":"Electronic Commerce Research and Applications","volume":"74 ","pages":"Article 101550"},"PeriodicalIF":6.3,"publicationDate":"2025-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145324600","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-09-01Epub Date: 2025-07-18DOI: 10.1016/j.elerap.2025.101532
Jeongha Kim , Eric Hyoekkoo Kwon , Dongwon Lee , Kyumin Lee
The burgeoning resale market, encompassing both physical and digital domains, has attracted considerable attention, particularly within the nascent metaverse. A key characteristic of this market is the decentralized pricing mechanism, wherein resellers autonomously determine prices based on individual valuations. This often results in significant price volatility due to the absence of established pricing benchmarks within the metaverse ecosystem. This study investigates the multifaceted determinants of resale pricing within this context, employing data from a prominent metaverse platform. Our analysis demonstrates a positive impact on resale price premiums from several factors: owner wealth, speculative value, extended holding periods, and item popularity. Conversely, items exhibiting collector tendencies or those with limited sales histories are associated with lower price premiums. This research contributes to the existing literature by delineating the distinct influences of item-specific and owner-specific characteristics on resale pricing Furthermore, the utilization of metaverse-generated data not only mitigates traditional data acquisition challenges but also provides novel insights into the dynamics of pricing within this emerging digital environment. These findings offer valuable implications for stakeholders seeking to optimize pricing strategies and achieve competitive advantage within the metaverse resale market.
{"title":"Speculation or collection? The impact of owner and item characteristics on polarized price premium in metaverse resale markets","authors":"Jeongha Kim , Eric Hyoekkoo Kwon , Dongwon Lee , Kyumin Lee","doi":"10.1016/j.elerap.2025.101532","DOIUrl":"10.1016/j.elerap.2025.101532","url":null,"abstract":"<div><div>The burgeoning resale market, encompassing both physical and digital domains, has attracted considerable attention, particularly within the nascent metaverse. A key characteristic of this market is the decentralized pricing mechanism, wherein resellers autonomously determine prices based on individual valuations. This often results in significant price volatility due to the absence of established pricing benchmarks within the metaverse ecosystem. This study investigates the multifaceted determinants of resale pricing within this context, employing data from a prominent metaverse platform. Our analysis demonstrates a positive impact on resale price premiums from several factors: owner wealth, speculative value, extended holding periods, and item popularity. Conversely, items exhibiting collector tendencies or those with limited sales histories are associated with lower price premiums. This research contributes to the existing literature by delineating the distinct influences of item-specific and owner-specific characteristics on resale pricing Furthermore, the utilization of metaverse-generated data not only mitigates traditional data acquisition challenges but also provides novel insights into the dynamics of pricing within this emerging digital environment. These findings offer valuable implications for stakeholders seeking to optimize pricing strategies and achieve competitive advantage within the metaverse resale market.</div></div>","PeriodicalId":50541,"journal":{"name":"Electronic Commerce Research and Applications","volume":"73 ","pages":"Article 101532"},"PeriodicalIF":5.9,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144687297","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-09-01Epub Date: 2025-07-30DOI: 10.1016/j.elerap.2025.101535
Dujuan Wang , Yunuo Zhu , Yi Feng , T.C.E. Cheng
As customers are increasingly opting to reference reviews with images before making purchasing decisions, images have become an indispensable component of online reviews. However, research on the content of images remains insufficient. Combining deep learning and econometric modelling, we examine the impact of the richness of user-generated images in online reviews on review helpfulness. By analyzing 10,406 reviews and 21,776 images collected from TripAdvisor, we obtain the following findings: (1) an inverted U-shaped relationship exists between image richness in reviews and review helpfulness; and (2) the popularity of hotels moderates the image richness-review helpfulness link, where higher popularity leads to a flatter inverted U-shaped relationship. This work advances research on online reviews and demonstrates the application of deep learning techniques in tourism and hotel studies. It also provides practical guidance for hotel and platform managers.
{"title":"Power of visuals: The impact of user-generated image richness on the helpfulness of online reviews","authors":"Dujuan Wang , Yunuo Zhu , Yi Feng , T.C.E. Cheng","doi":"10.1016/j.elerap.2025.101535","DOIUrl":"10.1016/j.elerap.2025.101535","url":null,"abstract":"<div><div>As customers are increasingly opting to reference reviews with images before making purchasing decisions, images have become an indispensable component of online reviews. However, research on the content of images remains insufficient. Combining deep learning and econometric modelling, we examine the impact of the richness of user-generated images in online reviews on review helpfulness. By analyzing 10,406 reviews and 21,776 images collected from TripAdvisor, we obtain the following findings: (1) an inverted U-shaped relationship exists between image richness in reviews and review helpfulness; and (2) the popularity of hotels moderates the image richness-review helpfulness link, where higher popularity leads to a flatter inverted U-shaped relationship. This work advances research on online reviews and demonstrates the application of deep learning techniques in tourism and hotel studies. It also provides practical guidance for hotel and platform managers.</div></div>","PeriodicalId":50541,"journal":{"name":"Electronic Commerce Research and Applications","volume":"73 ","pages":"Article 101535"},"PeriodicalIF":6.3,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144770957","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-09-01Epub Date: 2025-07-02DOI: 10.1016/j.elerap.2025.101528
Hongke Zhao , Yaxian Wang , Hao Wei
Crowdfunding has gained significant scholarly attention, yet existing research primarily focuses on single-platform studies, limiting the generalizability of findings. We argue that investment motivations vary across platform types, influencing the effectiveness of altruistic and quality signals on crowdfunding performance. Using 114,095 projects from Indiegogo (reward-based) and 1,199,908 loan projects from Kiva (lending-based), we first conduct separate analyses within each platform to examine the impact of these signals. We then compare the marginal effects across platforms to assess how platform structure influences backer decision-making. Our results show that quality signals consistently enhance crowdfunding success but have a stronger influence in reward-based platforms, while the effect of altruistic signals varies, enhancing performance in lending-based platforms but diminishing it in reward-based platforms. Moreover, we identify a reciprocal inhibitory interaction between quality and altruistic signals, suggesting that emphasizing one type of signal may weaken the effectiveness of the other by diverting backers’ attention and influencing how they evaluate the project. These findings underscore the importance of platform differentiation in crowdfunding research and highlight the need to move beyond single-platform studies. Our study offers practical insights for crowdfunding initiators on how to tailor their campaigns based on platform-specific investor behavior.
{"title":"How signal intensity of altruistic and strategic motivation affects crowdfunding performance? Matching among funders and platform types","authors":"Hongke Zhao , Yaxian Wang , Hao Wei","doi":"10.1016/j.elerap.2025.101528","DOIUrl":"10.1016/j.elerap.2025.101528","url":null,"abstract":"<div><div>Crowdfunding has gained significant scholarly attention, yet existing research primarily focuses on single-platform studies, limiting the generalizability of findings. We argue that investment motivations vary across platform types, influencing the effectiveness of altruistic and quality signals on crowdfunding performance. Using 114,095 projects from Indiegogo (reward-based) and 1,199,908 loan projects from Kiva (lending-based), we first conduct separate analyses within each platform to examine the impact of these signals. We then compare the marginal effects across platforms to assess how platform structure influences backer decision-making. Our results show that quality signals consistently enhance crowdfunding success but have a stronger influence in reward-based platforms, while the effect of altruistic signals varies, enhancing performance in lending-based platforms but diminishing it in reward-based platforms. Moreover, we identify a reciprocal inhibitory interaction between quality and altruistic signals, suggesting that emphasizing one type of signal may weaken the effectiveness of the other by diverting backers’ attention and influencing how they evaluate the project. These findings underscore the importance of platform differentiation in crowdfunding research and highlight the need to move beyond single-platform studies. Our study offers practical insights for crowdfunding initiators on how to tailor their campaigns based on platform-specific investor behavior.</div></div>","PeriodicalId":50541,"journal":{"name":"Electronic Commerce Research and Applications","volume":"73 ","pages":"Article 101528"},"PeriodicalIF":5.9,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144557391","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-09-01Epub Date: 2025-06-12DOI: 10.1016/j.elerap.2025.101520
Xueying Wang, Yuexian Zhang
In the realm of live-streaming, virtual streamers represent a significant area of industry expansion. Despite the widespread adoption of both human-backed and AI-backed virtual streamers in marketing campaigns, the differential effects of these two types remain underexplored. Through three experimental studies, this research systematically examines how virtual streamer types (AI-backed vs. human-backed) influence purchase intention, while elucidating the underlying mechanisms and boundary conditions. The findings demonstrate three key insights: First, human-backed virtual streamers exert significantly stronger impacts on purchase intention compared to their AI counterparts, with perceived usefulness serving as the critical mediator. Second, a two-sided message strategy outperforms positive unilateral messaging in amplifying virtual streamers’ effectiveness via enhanced perceived usefulness. Third, the live-streaming environment moderates this mechanism differentially: human-backed streamers prove more effective in real-life environments, whereas AI-backed streamers show superior performance in virtual environments. Both effects operate through the pathway of perceived usefulness. This study advances theoretical understanding of virtual streamer efficacy while providing actionable guidelines for businesses to optimize streamer selection strategies.
{"title":"The influence of virtual streamer on purchase intention: The moderated mediating effect of message strategy and live-streaming environment","authors":"Xueying Wang, Yuexian Zhang","doi":"10.1016/j.elerap.2025.101520","DOIUrl":"10.1016/j.elerap.2025.101520","url":null,"abstract":"<div><div>In the realm of live-streaming, virtual streamers represent a significant area of industry expansion. Despite the widespread adoption of both human-backed and AI-backed virtual streamers in marketing campaigns, the differential effects of these two types remain underexplored. Through three experimental studies, this research systematically examines how virtual streamer types (AI-backed vs. human-backed) influence purchase intention, while elucidating the underlying mechanisms and boundary conditions. The findings demonstrate three key insights: First, human-backed virtual streamers exert significantly stronger impacts on purchase intention compared to their AI counterparts, with perceived usefulness serving as the critical mediator. Second, a two-sided message strategy outperforms positive unilateral messaging in amplifying virtual streamers’ effectiveness via enhanced perceived usefulness. Third, the live-streaming environment moderates this mechanism differentially: human-backed streamers prove more effective in real-life environments, whereas AI-backed streamers show superior performance in virtual environments. Both effects operate through the pathway of perceived usefulness. This study advances theoretical understanding of virtual streamer efficacy while providing actionable guidelines for businesses to optimize streamer selection strategies.</div></div>","PeriodicalId":50541,"journal":{"name":"Electronic Commerce Research and Applications","volume":"73 ","pages":"Article 101520"},"PeriodicalIF":5.9,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144306605","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-09-01Epub Date: 2025-07-11DOI: 10.1016/j.elerap.2025.101531
Jongtae Yu
This study explores how shifting from a general to a specific decision-making context influences the interaction between affect and cognition in online information sharing with e-commerce vendors. While previous research has primarily examined these factors separately, their interplay—especially in relation to situational context—remains underexplored. To address this gap, two studies were conducted: a scenario-based survey and a controlled experiment. The first study found that in a general decision-making context, individuals tend to rely on heuristic processing, investing minimal cognitive effort due to perceived low relevance, limited accuracy requirements, and the absence of specific objectives. In contrast, in a specific decision-making context, cognitive evaluation played a greater role in determining whether to share personal information, while the influence of affect decreased. The second study examined how inconsistencies in cognitive evaluations between a general and a specific situation shape the role of affect in specific decision-making contexts. Participants were assigned to one of three experimental conditions (consistency, upward inconsistency, and downward inconsistency) and assessed the impact of affect, perceived benefits, and privacy risks on information sharing. The findings revealed that in inconsistency conditions, the influence of cognitive evaluations related to benefits and privacy risks weakened significantly. Moreover, the impact of affect varied across experimental conditions depending on the level of perceived risk. These results highlight the critical role of situational factors—such as goals, engagement levels, and perceived relevance—in shaping online information-sharing behavior.
{"title":"Examining the interplay of affect and cognition in online information disclosure in E-commerce: insights from two empirical studies","authors":"Jongtae Yu","doi":"10.1016/j.elerap.2025.101531","DOIUrl":"10.1016/j.elerap.2025.101531","url":null,"abstract":"<div><div>This study explores how shifting from a general to a specific decision-making context influences the interaction between affect and cognition in online information sharing with e-commerce vendors. While previous research has primarily examined these factors separately, their interplay—especially in relation to situational context—remains underexplored. To address this gap, two studies were conducted: a scenario-based survey and a controlled experiment. The first study found that in a general decision-making context, individuals tend to rely on heuristic processing, investing minimal cognitive effort due to perceived low relevance, limited accuracy requirements, and the absence of specific objectives. In contrast, in a specific decision-making context, cognitive evaluation played a greater role in determining whether to share personal information, while the influence of affect decreased. The second study examined how inconsistencies in cognitive evaluations between a general and a specific situation shape the role of affect in specific decision-making contexts. Participants were assigned to one of three experimental conditions (consistency, upward inconsistency, and downward inconsistency) and assessed the impact of affect, perceived benefits, and privacy risks on information sharing. The findings revealed that in inconsistency conditions, the influence of cognitive evaluations related to benefits and privacy risks weakened significantly. Moreover, the impact of affect varied across experimental conditions depending on the level of perceived risk. These results highlight the critical role of situational factors—such as goals, engagement levels, and perceived relevance—in shaping online information-sharing behavior.</div></div>","PeriodicalId":50541,"journal":{"name":"Electronic Commerce Research and Applications","volume":"73 ","pages":"Article 101531"},"PeriodicalIF":5.9,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144670253","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-09-01Epub Date: 2025-08-08DOI: 10.1016/j.elerap.2025.101536
Ji Li, Xv Liang, Shunzhi Xv
Online retailers are seeking innovative strategies to boost consumer purchases. Previous research has primarily focused on the factors that affect the actual use of BNPL and its impact on consumption, yet neglected the potential presentation effect of a BNPL payment option itself on nudging product consumption. This study examines how the presentation of a BNPL option in e-commerce platforms influences purchase intentions. Five experiments and a supplementary secondary data analysis show that, just adding a BNPL payment option could alleviate consumers’ perceived financial constraints, thereby enhancing their purchase intention. This effect is particularly striking because it affects even those who have no intention of using BNPL or do not possess such accounts, which can be attributed to the high accessibility of BNPL. Furthermore, our study rules out the confounding influence of psychological budget and alternative explanations of increased choice on perceived control and product trust. Examining the moderating effects of purchase type (material vs. experiential) and consumers’ future self-continuity (high vs. low) provides online retailers with more targeted strategies. These insights provide an understanding of how digital nudges, particularly adding a payment option, can subtly shape consumption in e-commerce environments. Our research extends the existing literature on BNPL and consumption, offering practical managerial implications for online retailers to design the payment policy.
{"title":"Just show the option: adding a BNPL payment option in online shopping can nudge purchase intention","authors":"Ji Li, Xv Liang, Shunzhi Xv","doi":"10.1016/j.elerap.2025.101536","DOIUrl":"10.1016/j.elerap.2025.101536","url":null,"abstract":"<div><div>Online retailers are seeking innovative strategies to boost consumer purchases. Previous research has primarily focused on the factors that affect the actual use of BNPL and its impact on consumption, yet neglected the potential presentation effect of a BNPL payment option itself on nudging product consumption. This study examines how the presentation of a BNPL option in e-commerce platforms influences purchase intentions. Five experiments and a supplementary secondary data analysis show that, just adding a BNPL payment option could alleviate consumers’ perceived financial constraints, thereby enhancing their purchase intention. This effect is particularly striking because it affects even those who have no intention of using BNPL or do not possess such accounts, which can be attributed to the high accessibility of BNPL. Furthermore, our study rules out the confounding influence of psychological budget and alternative explanations of increased choice on perceived control and product trust. Examining the moderating effects of purchase type (material vs. experiential) and consumers’ future self-continuity (high vs. low) provides online retailers with more targeted strategies. These insights provide an understanding of how digital nudges, particularly adding a payment option, can subtly shape consumption in e-commerce environments. Our research extends the existing literature on BNPL and consumption, offering practical managerial implications for online retailers to design the payment policy.</div></div>","PeriodicalId":50541,"journal":{"name":"Electronic Commerce Research and Applications","volume":"73 ","pages":"Article 101536"},"PeriodicalIF":6.3,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144829973","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-09-01Epub Date: 2025-07-09DOI: 10.1016/j.elerap.2025.101524
Shuai Jiang , Xiaoxin Pan , Yanhong Guo , Chuanren Liu , Hui Xiong
Financial analysts play a key role in financial decision-making, but the reliability of their recommendations can fluctuate dramatically depending on changes in analyst competence and contextual dynamics, posing a significant challenge to investors seeking guidance. This study unveils a novel explainable deep learning architecture, termed Quality Attribution Network (QuANet), which innovates by integrating a Generalized Additive Model framework, amplifying prediction accuracy and facilitating an in-depth understanding of how distinct variables contribute to the quality of analyst recommendations. Further, QuANet incorporates an attention mechanism to discern salient features, thereby ensuring that critical analyst, rating, and stock information receives appropriate weight. Empirical validation on extensive datasets corroborates QuANet’s superiority over existing benchmarks across diverse quality prediction metrics. Enhancing predictive capability translates into tangible gains for investment strategies, underscoring the model’s practical applicability. Additionally, QuANet’s attribution capabilities enable nuanced differentiation between analysts, pinpointing those endowed with genuine expertise within the financial advisory landscape. In sum, this research advances the analytical toolkit for assessing analyst recommendations by introducing a model that harmonizes predictive prowess with interpretative clarity. Investors stand to benefit from the transparent insights generated, facilitating the extraction of valuable knowledge from analyst recommendations to inform judicious investment decisions.
{"title":"Transparent prediction of financial analyst recommendation quality using generalized additive model","authors":"Shuai Jiang , Xiaoxin Pan , Yanhong Guo , Chuanren Liu , Hui Xiong","doi":"10.1016/j.elerap.2025.101524","DOIUrl":"10.1016/j.elerap.2025.101524","url":null,"abstract":"<div><div>Financial analysts play a key role in financial decision-making, but the reliability of their recommendations can fluctuate dramatically depending on changes in analyst competence and contextual dynamics, posing a significant challenge to investors seeking guidance. This study unveils a novel explainable deep learning architecture, termed Quality Attribution Network (QuANet), which innovates by integrating a Generalized Additive Model framework, amplifying prediction accuracy and facilitating an in-depth understanding of how distinct variables contribute to the quality of analyst recommendations. Further, QuANet incorporates an attention mechanism to discern salient features, thereby ensuring that critical analyst, rating, and stock information receives appropriate weight. Empirical validation on extensive datasets corroborates QuANet’s superiority over existing benchmarks across diverse quality prediction metrics. Enhancing predictive capability translates into tangible gains for investment strategies, underscoring the model’s practical applicability. Additionally, QuANet’s attribution capabilities enable nuanced differentiation between analysts, pinpointing those endowed with genuine expertise within the financial advisory landscape. In sum, this research advances the analytical toolkit for assessing analyst recommendations by introducing a model that harmonizes predictive prowess with interpretative clarity. Investors stand to benefit from the transparent insights generated, facilitating the extraction of valuable knowledge from analyst recommendations to inform judicious investment decisions.</div></div>","PeriodicalId":50541,"journal":{"name":"Electronic Commerce Research and Applications","volume":"73 ","pages":"Article 101524"},"PeriodicalIF":5.9,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144595731","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-09-01Epub Date: 2025-06-30DOI: 10.1016/j.elerap.2025.101527
Jungmin Hwang , Hakyeon Lee
Individual preferences change over time. While sequential recommenders have gained attention for accommodating changing user preferences, they have struggled to identify users’ preferences at a granular, component-wise level. This paper introduces a novel approach called preference tracing, inspired by the concept of knowledge tracing, originally developed in the educational domain. Knowledge tracing dynamically estimates a student’s knowledge state through interactions with question–answer pairs and knowledge components, predicting the likelihood of correctly answering an exercise based on the estimated knowledge state. Similarly, preference tracing continuously estimates a user's preference state as they engage with content over time, predicting whether a user will enjoy a specific movie based on the estimated preference state. Our empirical evaluations demonstrate that Bayesian knowledge tracing (BKT)-based preference tracing not only delivers comparable predictive performance but also effectively captures users’ preference states at a component-wise level. Moreover, deep learning-based knowledge tracing (DLKT)-based preference tracing, which operates without predefined movie components, outperforms recent deep learning-based recommendation models, unveiling its potential to provide more accurate and nuanced recommendations.
{"title":"From knowledge tracing to preference tracing: Capturing dynamic user preferences for personalized recommendation","authors":"Jungmin Hwang , Hakyeon Lee","doi":"10.1016/j.elerap.2025.101527","DOIUrl":"10.1016/j.elerap.2025.101527","url":null,"abstract":"<div><div>Individual preferences change over time. While sequential recommenders have gained attention for accommodating changing user preferences, they have struggled to identify users’ preferences at a granular, component-wise level. This paper introduces a novel approach called preference tracing, inspired by the concept of knowledge tracing, originally developed in the educational domain. Knowledge tracing dynamically estimates a student’s knowledge state through interactions with question–answer pairs and knowledge components, predicting the likelihood of correctly answering an exercise based on the estimated knowledge state. Similarly, preference tracing continuously estimates a user's preference state as they engage with content over time, predicting whether a user will enjoy a specific movie based on the estimated preference state. Our empirical evaluations demonstrate that Bayesian knowledge tracing (BKT)-based preference tracing not only delivers comparable predictive performance but also effectively captures users’ preference states at a component-wise level. Moreover, deep learning-based knowledge tracing (DLKT)-based preference tracing, which operates without predefined movie components, outperforms recent deep learning-based recommendation models, unveiling its potential to provide more accurate and nuanced recommendations.</div></div>","PeriodicalId":50541,"journal":{"name":"Electronic Commerce Research and Applications","volume":"73 ","pages":"Article 101527"},"PeriodicalIF":5.9,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144606170","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号