Next Issue
Volume 19, June
Previous Issue
Volume 18, December
 
 

J. Theor. Appl. Electron. Commer. Res., Volume 19, Issue 1 (March 2024) – 37 articles

Cover Story (view full-size image): This study assessed the effectiveness of Midjourney, a diffusion-modeling-based AI system, in both fashion design and related commerce applications using the action research approach and the Functional, Expressive, and Aesthetic (FEA) Consumer Needs Model as the theoretical framework. Findings reveal this AI tool can assist fashion designers in creating both visually expressive attire and ready-to-wear products, meeting defined design criteria and consumer needs. Potential e-commercial applications of such AI systems were proposed, benefiting physical and digital fashion businesses. View this paper
  • Issues are regarded as officially published after their release is announced to the table of contents alert mailing list.
  • You may sign up for e-mail alerts to receive table of contents of newly released issues.
  • PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Reader to open them.
Order results
Result details
Section
Select all
Export citation of selected articles as:
13 pages, 617 KiB  
Article
The Effect of AI Agent Gender on Trust and Grounding
by Joo-Eon Jeon
J. Theor. Appl. Electron. Commer. Res. 2024, 19(1), 692-704; https://doi.org/10.3390/jtaer19010037 - 21 Mar 2024
Viewed by 1744
Abstract
Artificial intelligence (AI) agents are widely used in the retail and distribution industry. The primary objective was to investigate whether the gender of AI agents influences trust and grounding. This paper examined the influence of AI agent gender and brand concepts on trust [...] Read more.
Artificial intelligence (AI) agents are widely used in the retail and distribution industry. The primary objective was to investigate whether the gender of AI agents influences trust and grounding. This paper examined the influence of AI agent gender and brand concepts on trust and grounding within virtual brand spaces. For this purpose, it used two independent variables: brand concept (functional vs. experiential) and AI agent gender (male vs. female). The dependent variables included AI agent trust and grounding. The study revealed that in virtual brand spaces centered around a functional concept, male AI agents generated higher levels of trust than female AI agents, whereas, when focused on an experiential concept, female AI agents induced higher levels of grounding than male AI agents. Furthermore, the findings indicate that the association between customers’ identification with AI agents and recommendations for actual brand purchases is mediated by trust and grounding. These findings support the idea that users who strongly identify with AI agents are more inclined to recommend brand products. By presenting alternatives that foster the establishment and sustenance of a meaningful, sustainable relationship between humans and AI, this study contributes to research on human–computer interactions. Full article
(This article belongs to the Collection Customer Relationships in Electronic Commerce)
Show Figures

Figure 1

21 pages, 1010 KiB  
Article
Social Media Managers’ Performance: The Impact of the Work Environment
by Zaira Camoiras-Rodríguez and Concepción Varela-Neira
J. Theor. Appl. Electron. Commer. Res. 2024, 19(1), 671-691; https://doi.org/10.3390/jtaer19010036 - 18 Mar 2024
Viewed by 1884
Abstract
The continuous growth of social media is causing significant modifications in the business strategies developed by organizations. Using a structural equation modeling approach, this research analyzes how the work environment affects the social media managers thriving at work and task performance. The proposed [...] Read more.
The continuous growth of social media is causing significant modifications in the business strategies developed by organizations. Using a structural equation modeling approach, this research analyzes how the work environment affects the social media managers thriving at work and task performance. The proposed model is tested using a sample of 190 social media managers and 190 supervisors from 190 companies in the tourism sector. The results highlight the importance of proper design and implementation of social media marketing planning and top management support to enhance both thriving at work and the performance of social media managers. This research contributes to the literature on social media by examining how and when the work environment influences the attitudes and performance of social media managers, whose role is crucial in organizational performance. Simultaneously, it expands the literature on thriving, as knowledge about the impact of contextual factors on thriving is still limited. The results also demonstrate that managers can compensate for the lack of certain contextual or personal resources with other resources, providing insights into when the work environment is more beneficial in shaping positive attitudes and behaviors in employees. Full article
Show Figures

Figure 1

17 pages, 5303 KiB  
Article
Unlocking the Potential of Artificial Intelligence in Fashion Design and E-Commerce Applications: The Case of Midjourney
by Yanbo Zhang and Chuanlan Liu
J. Theor. Appl. Electron. Commer. Res. 2024, 19(1), 654-670; https://doi.org/10.3390/jtaer19010035 - 18 Mar 2024
Cited by 5 | Viewed by 4789
Abstract
The fashion industry has shown increasing interest in applying artificial intelligence (AI), yet there is a significant gap in exploring the potential of emerging diffusion-modeling-based AI image-generation systems for fashion design and commerce. Therefore, this study aims to assess the effectiveness of Midjourney, [...] Read more.
The fashion industry has shown increasing interest in applying artificial intelligence (AI), yet there is a significant gap in exploring the potential of emerging diffusion-modeling-based AI image-generation systems for fashion design and commerce. Therefore, this study aims to assess the effectiveness of Midjourney, one such AI system, in both fashion design and related commerce applications. We employed the action research approach with the Functional, Expressive, and Aesthetic (FEA) Consumer Needs Model as the theoretical framework. Our research comprised three stages: refining an initial idea into well-defined textual design concepts, facilitating concept development, and validating the preceding observations and reflections by creating a new line of hemp-based products that were evaluated by targeted consumers through an online survey. Findings reveal that this AI tool can assist fashion designers in creating both visually expressive attire and ready-to-wear products, meeting defined design criteria and consumer needs. Midjourney shows promise in streamlining the fashion design process by enhancing ideation and optimizing design details. Potential e-commercial applications of such AI systems were proposed, benefiting physical and digital fashion businesses. It is noted that, to date, the major limitations of using Midjourney encompass its restriction to only facilitating early fashion design stages and necessitating substantial involvement from designers. Full article
Show Figures

Figure 1

21 pages, 2798 KiB  
Article
Mobile Payment Innovation Ecosystem and Mechanism: A Case Study of Taiwan’s Servicescapes
by Wai-Kit Ng, Shi Chen, Wei-Hung Chen, Chun-Liang Chen and Jhih-Ling Jiang
J. Theor. Appl. Electron. Commer. Res. 2024, 19(1), 633-653; https://doi.org/10.3390/jtaer19010034 - 15 Mar 2024
Viewed by 1572
Abstract
This paper examines how businesses in Taiwan’s servicescapes are adapting to the growing trend of mobile payments and innovation ecosystems. Through the analysis of four case studies, we uncover the strategies these firms employ to address the challenges posed by changing consumer payment [...] Read more.
This paper examines how businesses in Taiwan’s servicescapes are adapting to the growing trend of mobile payments and innovation ecosystems. Through the analysis of four case studies, we uncover the strategies these firms employ to address the challenges posed by changing consumer payment habits. Our research reveals that these companies are establishing efficient mechanisms within their ecosystems, supported by well-structured organizational frameworks. By leveraging innovation ecosystems, they are reshaping financial services and promoting collaborative growth among participants through technology, platforms, resource sharing, and knowledge exchange. This collaborative approach is driving significant changes in the sector, helping these businesses navigate through various challenges while fostering innovation and growth. Additionally, the scarcity of comprehensive observations of the digital payment ecosystem highlights the necessity for further exploration of actor interactions, regulatory mechanisms, and ecosystem management strategies. Such research efforts are crucial for enhancing our understanding of the evolving landscape of digital payments and innovation ecosystems, facilitating informed decision-making and promoting sustainable development in this dynamic industry. Full article
Show Figures

Figure 1

18 pages, 675 KiB  
Article
Influence of Electronic Word-Of-Mouth on Restaurant Choice Decisions: Does It Depend on Gender in the Millennial Generation?
by Giovanny Haro-Sosa, Beatriz Moliner-Velázquez, Irene Gil-Saura and María Fuentes-Blasco
J. Theor. Appl. Electron. Commer. Res. 2024, 19(1), 615-632; https://doi.org/10.3390/jtaer19010033 - 14 Mar 2024
Cited by 2 | Viewed by 2331
Abstract
Given the exponential growth of eWOM, especially among the millennial generation, an analysis of the consultation behaviour of online opinions is essential to better understanding the decision-making process. The aim of this proposal is to analyse how the motivations towards eWOM consultation contribute [...] Read more.
Given the exponential growth of eWOM, especially among the millennial generation, an analysis of the consultation behaviour of online opinions is essential to better understanding the decision-making process. The aim of this proposal is to analyse how the motivations towards eWOM consultation contribute to the final adoption of eWOM, especially in the restaurant context, exploring the relationship chain “motivations to consult eWOM—intention to consult eWOM—adoption to consult eWOM”. Moreover, studying the moderating effect of gender in this chain is argued. Based on a sample of 341 millennials with experience in reading online reviews and visiting restaurants, a causal model was estimated through PLS estimation in the geographic area of Ecuador. The results confirm that millennials’ motivations influence directly their intention to consult eWOM and indirectly on eWOM adoption. In addition, gender does not show a significant effect on the chain of effects. Given that virtual platforms have the potential to influence men and women equally, the communication efforts of restaurants focused on this target audience and carried out on social media must focus on aspects other than gender. Full article
Show Figures

Figure 1

18 pages, 1117 KiB  
Perspective
Fog Computing-Based Smart Consumer Recommender Systems
by Jacob Hornik, Chezy Ofir, Matti Rachamim and Sergei Graguer
J. Theor. Appl. Electron. Commer. Res. 2024, 19(1), 597-614; https://doi.org/10.3390/jtaer19010032 - 11 Mar 2024
Viewed by 1820
Abstract
The latest effort in delivering computing resources as a service to managers and consumers represents a shift away from computing as a product that is purchased, to computing as a service that is delivered to users over the internet from large-scale data centers. [...] Read more.
The latest effort in delivering computing resources as a service to managers and consumers represents a shift away from computing as a product that is purchased, to computing as a service that is delivered to users over the internet from large-scale data centers. However, with the advent of the cloud-based IoT and artificial intelligence (AI), which are advancing customer experience automations in many application areas, such as recommender systems (RS), a need has arisen for various modifications to support the IoT devices that are at the center of the automation world, including recent language models like ChatGPT and Bard and technologies like nanotechnology. This paper introduces the marketing community to a recent computing development: IoT-driven fog computing (FC). Although numerous research studies have been published on FC “smart” applications, none hitherto have been conducted on fog-based smart marketing domains such as recommender systems. FC is considered a novel computational system, which can mitigate latency and improve bandwidth utilization for autonomous consumer behavior applications requiring real-time data-driven decision making. This paper provides a conceptual framework for studying the effects of fog computing on consumer behavior, with the goal of stimulating future research by using, as an example, the intersection of FC and RS. Indeed, our conceptualization of the “fog-based recommender systems” opens many novel and challenging avenues for academic research, some of which are highlighted in the later part of this paper. Full article
Show Figures

Figure 1

16 pages, 483 KiB  
Article
How Personality Traits Affect Customer Empathy Expression of Social Media Ads and Purchasing Intention: A Psychological Perspective
by Serhan Demirci, Chia-Ju Ling, Dai-Rong Lee and Chien-Wen Chen
J. Theor. Appl. Electron. Commer. Res. 2024, 19(1), 581-596; https://doi.org/10.3390/jtaer19010031 - 7 Mar 2024
Viewed by 1958
Abstract
Consumers’ personality traits significantly influence their perceptions regarding social media advertising. While prior research on consumers’ purchasing intentions in social networking sites advertising has mainly focused on advertising valence antecedents, it is crucial to recognize that consumers’ susceptibility to advertising persuasion, particularly in [...] Read more.
Consumers’ personality traits significantly influence their perceptions regarding social media advertising. While prior research on consumers’ purchasing intentions in social networking sites advertising has mainly focused on advertising valence antecedents, it is crucial to recognize that consumers’ susceptibility to advertising persuasion, particularly in terms of empathic expression, varies based on a key criterion: whether consumers are driven to attain a specific desired state or are more inclined to avoid an undesirable state. Regulatory Focus Theory (RFT) posits that individuals operate under distinct motivational mechanisms that govern their determination to achieve desired goals, influencing how they process and evaluate advertising messages. In light of RFT, we conducted an online survey with 524 valid responses, utilizing partial least squares (PLS) for research model analysis. The findings revealed that promotion-focused individuals have positively influenced perceptions of social media ad effectiveness (informativeness, ad creativity, perceived relevance, and emotional appeal). In contrast, prevention-focused individuals negatively perceived social media ad effectiveness. Furthermore, this study highlighted that perceived relevance and emotional appeal have a more significant impact on attitudes toward expressing empathy than informativeness and ad creativity. Full article
Show Figures

Figure 1

20 pages, 640 KiB  
Article
Do Dynamic Signals Affect High-Quality Solvers’ Participation Behavior? Evidence from the Crowdsourcing Platform
by Xue Liu and Xiaoling Hao
J. Theor. Appl. Electron. Commer. Res. 2024, 19(1), 561-580; https://doi.org/10.3390/jtaer19010030 - 6 Mar 2024
Cited by 1 | Viewed by 913
Abstract
The emergence of the crowdsourcing platform enables seekers to obtain higher-quality services at lower costs. High-quality services are often provided by high-quality solvers, which is the key to the sustainable development of crowdsourcing platforms. Therefore, how to attract more high-quality solvers to participate [...] Read more.
The emergence of the crowdsourcing platform enables seekers to obtain higher-quality services at lower costs. High-quality services are often provided by high-quality solvers, which is the key to the sustainable development of crowdsourcing platforms. Therefore, how to attract more high-quality solvers to participate needs to be focused on. Most previous studies that used stock data to measure crowdsourcing performance failed to describe the contest process of high-quality solvers’ behavior. Different from the previous study, this paper explores the information signals that influence the participation of high-quality solvers in the dynamic process of crowdsourcing contests. Based on the creative projects of the Winvk platform, dynamic models affecting the participation of high-quality solvers are constructed from the perspective of reducing information asymmetry, and the effects of quality signals and intention signals are explored in depth. The results show that for logo design projects, clear information display and monetary mechanisms have a significant impact on alleviating information asymmetry and attracting the participation of high-quality solvers. Interestingly, the effect of market competition on high-quality solvers shows a U-shaped change. The research results provide a reference for enterprises to reduce information asymmetry, obtain high-quality solutions, and enrich the theoretical application in the field of crowdsourcing. Full article
Show Figures

Figure 1

23 pages, 2277 KiB  
Article
The Impact of Academic Publications over the Last Decade on Historical Bitcoin Prices Using Generative Models
by Adela Bâra and Simona-Vasilica Oprea
J. Theor. Appl. Electron. Commer. Res. 2024, 19(1), 538-560; https://doi.org/10.3390/jtaer19010029 - 6 Mar 2024
Cited by 2 | Viewed by 1766
Abstract
Since 2012, researchers have explored various factors influencing Bitcoin prices. Up until the end of July 2023, more than 9100 research papers on cryptocurrencies were published and indexed in the Web of Science Clarivate platform. The objective of this paper is to analyze [...] Read more.
Since 2012, researchers have explored various factors influencing Bitcoin prices. Up until the end of July 2023, more than 9100 research papers on cryptocurrencies were published and indexed in the Web of Science Clarivate platform. The objective of this paper is to analyze the impact of publications on Bitcoin prices. This study aims to uncover significant themes within these research articles, focusing on cryptocurrencies in general and Bitcoin specifically. The research employs latent Dirichlet allocation to identify key topics from the unstructured abstracts. To determine the optimal number of topics, perplexity and topic coherence metrics are calculated. Additionally, the abstracts are processed using BERT-transformers and Word2Vec and their potential to predict Bitcoin prices is assessed. Based on the results, while the research helps in understanding cryptocurrencies, the potential of academic publications to influence Bitcoin prices is not significant, demonstrating a weak connection. In other words, the movements of Bitcoin prices are not influenced by the scientific writing in this specific field. The primary topics emerging from the analysis are the blockchain, market dynamics, transactions, pricing trends, network security, and the mining process. These findings suggest that future research should pay closer attention to issues like the energy demands and environmental impacts of mining, anti-money laundering measures, and behavioral aspects related to cryptocurrencies. Full article
Show Figures

Figure 1

12 pages, 273 KiB  
Article
Who Are the Online Medication Shoppers? A Market Segmentation of the Swedish Welfare State
by John Magnus Roos, Magnus Jansson and Pernilla J. Bjerkeli
J. Theor. Appl. Electron. Commer. Res. 2024, 19(1), 526-537; https://doi.org/10.3390/jtaer19010028 - 5 Mar 2024
Cited by 1 | Viewed by 1325
Abstract
The present study aimed to explore the online shopping of medicines from demographic, geographic, psychographic, and behavioral factors. A quantitative survey design was used with a quote sample representing the Swedish population regarding age, gender, and residential area. In total, 1863 persons responded [...] Read more.
The present study aimed to explore the online shopping of medicines from demographic, geographic, psychographic, and behavioral factors. A quantitative survey design was used with a quote sample representing the Swedish population regarding age, gender, and residential area. In total, 1863 persons responded to a survey, including measures of age, gender, income, education, area of residence, personality traits (BFI-10), values (Rokeach Value Survey), self-estimated health-status, internet usage, online shopping in general, and online shopping of medicines. Firstly, the data were analyzed with chi-squares and independent t-tests. From these initial analyses, online shopping of medicines was associated with young age, female gender, high income and education, living in a big city, extraversion, several values of desirable end-states of existence (e.g., self-respect, a sense of accomplishment, and pleasure), internet usage, and general online shopping. Secondly, the significant (p < 0.05) variables from the initial analysis were included in a logistic regression analysis. This comprehensive model showed that online medication shoppers are best predicted by being female and the use of internet. Unlike what was previously known about medication shoppers, the typical online medication shopper appears to be driven by hedonistic values and self-actualization, rather than health status. We suggest that further research replicate this study outside and inside Sweden, and that health status is measured in a different way. Full article
19 pages, 3021 KiB  
Article
Public Perception of Online P2P Lending Applications
by Sahiba Khan, Ranjit Singh, H. Kent Baker and Gomtesh Jain
J. Theor. Appl. Electron. Commer. Res. 2024, 19(1), 507-525; https://doi.org/10.3390/jtaer19010027 - 1 Mar 2024
Viewed by 1616
Abstract
This study examines significant topics and customer sentiments conveyed in reviews of P2P lending applications (apps) in India by employing topic modeling and sentiment analysis. The apps considered are LenDenClub, Faircent, i2ifunding, India Money Mart, and Lendbox. Using Latent Dirichlet Allocation, we identified [...] Read more.
This study examines significant topics and customer sentiments conveyed in reviews of P2P lending applications (apps) in India by employing topic modeling and sentiment analysis. The apps considered are LenDenClub, Faircent, i2ifunding, India Money Mart, and Lendbox. Using Latent Dirichlet Allocation, we identified and labeled 11 topics: application, document, default, login, reject, service, CIBIL, OTP, returns, interface, and withdrawal. The sentiment analysis tool VADER revealed that most users have positive attitudes toward these apps. We also compared the five apps overall and on specific topics. Overall, LenDenClub had the highest proportion of positive reviews. We also compared the prediction abilities of six machine-learning models. Logistic Regression demonstrates high accuracy with all three feature extraction techniques: bag of words, term frequency-inverse document frequency, and hashing. The study assists borrowers and lenders in choosing the most appropriate application and supports P2P lending platforms in recognizing their strengths and weaknesses. Full article
(This article belongs to the Topic Online User Behavior in the Context of Big Data)
Show Figures

Figure 1

21 pages, 2379 KiB  
Article
Emerging Trends in Play-to-Earn (P2E) Games
by Andreea Raluca Duguleană, Cristina Roxana Tănăsescu and Mihai Duguleană
J. Theor. Appl. Electron. Commer. Res. 2024, 19(1), 486-506; https://doi.org/10.3390/jtaer19010026 - 1 Mar 2024
Cited by 2 | Viewed by 2367
Abstract
This research aims to establish the primary drivers influencing the development and consumers’ decision-making process in web3 games—decentralized games that function according to the play-to-earn paradigm. We observe several types of micro-economies developed within five play-to-earn games and highlight four roles consumers play [...] Read more.
This research aims to establish the primary drivers influencing the development and consumers’ decision-making process in web3 games—decentralized games that function according to the play-to-earn paradigm. We observe several types of micro-economies developed within five play-to-earn games and highlight four roles consumers play at any given time. Our study offers a different perspective on rational consumer behaviour in cryptocurrency-based games and paves the way to better understanding their dynamics and evolution. Results shed light on the construction of in-game economies and how individuals of a given type engage in different playing activities. Furthermore, we compare the key features of web3 games with those similar to classic online games and assess if the play-and-earn implementations represent an evolution from previous revenue models. Using our proposed methodology, researchers can compare and classify any P2E games. We conclude by establishing a set of actions that enable consumers to benefit from this new phenomenon. Full article
(This article belongs to the Section Digital Marketing and the Connected Consumer)
Show Figures

Figure 1

19 pages, 690 KiB  
Article
Authorized and Unauthorized Consumption of SVOD Content: Modeling Determinants of Demand and Measuring Effects of Enforcing Access Control
by Ignacio Redondo and Diana Serrano
J. Theor. Appl. Electron. Commer. Res. 2024, 19(1), 467-485; https://doi.org/10.3390/jtaer19010025 - 28 Feb 2024
Viewed by 1137
Abstract
Consumers are attracted by the increasing number of available SVOD platforms, but it would be too expensive to pay the subscription fees for all of them. To reduce costs, consumers can combine the use of proprietary subscriptions, non-proprietary subscriptions, and illegal streaming sites. [...] Read more.
Consumers are attracted by the increasing number of available SVOD platforms, but it would be too expensive to pay the subscription fees for all of them. To reduce costs, consumers can combine the use of proprietary subscriptions, non-proprietary subscriptions, and illegal streaming sites. In turn, platforms could enforce access control, a decision that might produce the desired reduction in non-proprietary subscriptions but also an undesired reduction in proprietary subscriptions. The effects of this decision and the determinants of SVOD content demand remain largely unexplored. We propose a baseline model where the SVOD content demand is driven by variety seeking, household financial situation, ethical evaluation, and social norms, as well as a change model where the subscription variation is driven by users’ trait reactance and perceived fairness of the decision. We conducted a survey on the current ways SVOD content is consumed and responses to a hypothetical access control enforcement, with four randomized versions of the authentication mode. Results confirmed many of the proposed determinants and showed a noteworthy reduction in proprietary subscriptions due to the control enforcement but no effect due to the authentication modes. All these findings may help improve future models of SVOD content consumption and better address the difficult challenge of converting unauthorized users into authorized ones. Full article
(This article belongs to the Section Digital Business Organization)
Show Figures

Figure 1

19 pages, 2221 KiB  
Article
The Impact of Recommendation System on User Satisfaction: A Moderated Mediation Approach
by Xinyue He, Qi Liu and Sunho Jung
J. Theor. Appl. Electron. Commer. Res. 2024, 19(1), 448-466; https://doi.org/10.3390/jtaer19010024 - 27 Feb 2024
Cited by 4 | Viewed by 3588
Abstract
A recommendation system serves as a key factor for improving e-commerce users’ satisfaction by providing them with more accurate and diverse suggestions. A significant body of research has examined the accuracy and diversity of a variety of recommendation systems. However, little is known [...] Read more.
A recommendation system serves as a key factor for improving e-commerce users’ satisfaction by providing them with more accurate and diverse suggestions. A significant body of research has examined the accuracy and diversity of a variety of recommendation systems. However, little is known about the psychological mechanisms through which the recommendation system influences the user satisfaction. Thus, the purpose of this study is to contribute to this gap by examining the mediating and moderating processes underlying this relationship. Drawing from the traditional task-technology fit literature, the study developed a moderated mediation model, simultaneously considering the roles of a user’s feeling state and shopping goal. We adopted a scenario-based experimental approach to test three hypotheses contained in the model. The results showed that there is an interaction effect between shopping goals and types of recommendation (diversity and accuracy) on user satisfaction. Specifically, when a user’s shopping goal aligns with recommendation results in terms of accuracy and diversity, the user satisfaction is enhanced. Furthermore, this study evaluated the mediating role of feeling right and psychological reactance for a better understanding of this interactive relationship. We tested the moderated mediation effect of feeling right and the psychological reactance moderated by the user shopping goal. For goal-directed users, accurate recommendations trigger the activation of feeling right, consequently increasing the user satisfaction. Conversely, when exploratory users face accurate recommendations, they activate psychological reactance, which leads to a reduction in user satisfaction. Finally, we discuss the implications for the study of recommendation systems, and for how marketers/online retailers can implement them to improve online customers’ shopping experience. Full article
(This article belongs to the Topic Consumer Psychology and Business Applications)
Show Figures

Figure 1

18 pages, 585 KiB  
Article
Investigating M-Payment Intention across Consumer Cohorts
by Amonrat Thoumrungroje and Lokweetpun Suprawan
J. Theor. Appl. Electron. Commer. Res. 2024, 19(1), 431-447; https://doi.org/10.3390/jtaer19010023 - 19 Feb 2024
Viewed by 1498
Abstract
This study investigates the widespread adoption of mobile payments (m-payments) and their impact on different generations, particularly post-COVID-19. We fill a gap in research by suggesting a new way to understand this phenomenon through the lens of social cognitive theory. We employed a [...] Read more.
This study investigates the widespread adoption of mobile payments (m-payments) and their impact on different generations, particularly post-COVID-19. We fill a gap in research by suggesting a new way to understand this phenomenon through the lens of social cognitive theory. We employed a multi-stage sampling technique, including purposive, quota, and snowball sampling, to ensure comparable group sizes for four generations and obtained usable survey data from 716 Thai online shoppers. The results reveal direct and indirect (through perceived values) significant relationships between technological self-efficacy and m-payment intention. While perceived values, which constitute functional, emotional, monetary, and social values, fully mediate the relationship between technological self-efficacy and m-payment intention in Gen B and Gen X consumers, it only partially mediates such a relationship in the Gen Y and Gen Z cohorts. Our findings also provide crucial theoretical and practical insights for digital commerce in the evolving landscape of m-payment adoption. Full article
Show Figures

Figure 1

19 pages, 602 KiB  
Article
Functional Framework for Multivariant E-Commerce User Interfaces
by Adam Wasilewski
J. Theor. Appl. Electron. Commer. Res. 2024, 19(1), 412-430; https://doi.org/10.3390/jtaer19010022 - 16 Feb 2024
Cited by 4 | Viewed by 2112
Abstract
Modern e-businesses heavily rely on advanced data analytics for product recommendations. However, there are still untapped opportunities to enhance user interfaces. Currently, online stores offer a single-page version to all customers, overlooking individual characteristics. This paper aims to identify the essential components and [...] Read more.
Modern e-businesses heavily rely on advanced data analytics for product recommendations. However, there are still untapped opportunities to enhance user interfaces. Currently, online stores offer a single-page version to all customers, overlooking individual characteristics. This paper aims to identify the essential components and present a framework for enabling multiple e-commerce user interfaces. It also seeks to address challenges associated with personalized e-commerce user interfaces. The methodology includes detailing the framework for serving diverse e-commerce user interfaces and presenting pilot implementation results. Key components, particularly the role of algorithms in personalizing the user experience, are outlined. The results demonstrate promising outcomes for the implementation of the pilot solution, which caters to various e-commerce user interfaces. User characteristics support multivariant websites, with algorithms facilitating continuous learning. Newly proposed metrics effectively measure changes in user behavior resulting from different interface deployments. This paper underscores the central role of personalized e-commerce user interfaces in optimizing online store efficiency. The framework, supported by machine learning algorithms, showcases the feasibility and benefits of different page versions. The identified components, challenges, and proposed metrics contribute to a comprehensive solution and set the stage for further development of personalized e-commerce interfaces. Full article
Show Figures

Figure 1

16 pages, 525 KiB  
Article
Consumption of Sustainable Denim Products: The Contribution of Blockchain Certified Eco-Labels
by Xingqiu Lou and Yingjiao Xu
J. Theor. Appl. Electron. Commer. Res. 2024, 19(1), 396-411; https://doi.org/10.3390/jtaer19010021 - 16 Feb 2024
Viewed by 2404
Abstract
Consumers’ growing interest in the environmental and social impacts of products has increased demand for sustainable fashion items, particularly denim. Emerging technologies such as blockchain technology and labeling certifications have been developed to address sustainability issues by improving supply chain transparency and efficiency. [...] Read more.
Consumers’ growing interest in the environmental and social impacts of products has increased demand for sustainable fashion items, particularly denim. Emerging technologies such as blockchain technology and labeling certifications have been developed to address sustainability issues by improving supply chain transparency and efficiency. This research investigates the trade-offs consumers make when purchasing sustainable denim jeans and the impact of sociodemographic factors on their decision-making process. Employing a conjoint analysis approach, four attributes were examined: price, brand name, types of materials, and eco-labeling. The results indicated that price is still the most influential factor, followed by material, brand name, and eco-label. Although eco-labeling is of little importance to consumers, it offers valuable insights for effective communication of sustainable practices. Consumers prefer denim with a blockchain eco-label, followed by a fair-trade certificate. This research enhances the understanding of consumer behavior toward sustainable consumption and offers strategic insights for denim producers and marketers. Full article
Show Figures

Figure 1

15 pages, 1465 KiB  
Article
Delving into Human Factors through LSTM by Navigating Environmental Complexity Factors within Use Case Points for Digital Enterprises
by Nevena Rankovic and Dragica Rankovic
J. Theor. Appl. Electron. Commer. Res. 2024, 19(1), 381-395; https://doi.org/10.3390/jtaer19010020 - 14 Feb 2024
Viewed by 976
Abstract
Meeting customer requirements in software project management, even for large digital enterprises, proves challenging due to unpredictable human factors. It involves meticulous planning and environmental factor analysis, ultimately benefiting both companies and customers. This paper came as a natural extension of our previous [...] Read more.
Meeting customer requirements in software project management, even for large digital enterprises, proves challenging due to unpredictable human factors. It involves meticulous planning and environmental factor analysis, ultimately benefiting both companies and customers. This paper came as a natural extension of our previous work where we left ourselves curious about what impact environmental complexity factors (ECFs) have in a use case point (UCP) approach. Additionally, we wanted to possibly decrease the mean magnitude relative error (MMRE) with deep learning models such as long-short-term-memory (LSTM) and gradient recurrent unit (GRU). The data augmentation technique was used to artificially increase the number of projects, since in the industry world, digital enterprises are not keen to share their data. The LSTM model outperformed the GRU and XGBoost models, while the average MMRE in all phases of the experiment for all models achieved 4.8%. Moreover, the post-agnostic models showed the overall and individual impact of eight ECFs, where the third ECF “team experience” on a new project has been shown as the most influential one. Finally, it is important to emphasize that effectively managing human factors within ECFs in UCPs can have a significant impact on the successful completion of a project. Full article
(This article belongs to the Section Digital Business Organization)
Show Figures

Figure 1

19 pages, 605 KiB  
Article
The Roles of Sales Technologies for Salespeople: Techno Demands and Resources Model Perspective
by Kangsun Shin, Seonggoo Ji, Ihsan Ullah Jan and Younghoon Kim
J. Theor. Appl. Electron. Commer. Res. 2024, 19(1), 362-380; https://doi.org/10.3390/jtaer19010019 - 13 Feb 2024
Viewed by 1309
Abstract
The purpose of this study is to examine the effects of a salesperson’s techno-demands and techno-resources created by new sales-related information technology on salespersons’ attitudinal and behavioral outcomes such as job burnout, job satisfaction, turnover intention, and sales performance. In order to test [...] Read more.
The purpose of this study is to examine the effects of a salesperson’s techno-demands and techno-resources created by new sales-related information technology on salespersons’ attitudinal and behavioral outcomes such as job burnout, job satisfaction, turnover intention, and sales performance. In order to test the proposed framework, data were collected from 305 salespeople in Korea. The results of a partial least squared structural equation modeling (PLS-SEM) analysis showed that techno-demands have a significant positive effect on salespeople’s job burnout and techno-resources have a significant positive effect on salespeople’s job satisfaction. Salespeople’s job burnout has a significant positive effect on salespeople’s turnover intention, whereas salespeople’s job satisfaction has a significant positive effect on salespeople’s sales performance. Finally, salespeople’s job satisfaction has a negative effect on turnover intention. Theoretically, this study develops a new comprehensive framework of the techno demands–resources model and is empirically tested in the context of salespeople. Managerially, the findings offer important insights to practitioners to leverage techno-resources to accelerate the sales technologies for sales activities. Full article
(This article belongs to the Section Digital Business Organization)
Show Figures

Figure 1

22 pages, 573 KiB  
Article
Similarities and Disparities of e-Commerce in the European Union in the Post-Pandemic Period
by Rodica Manuela Gogonea, Liviu Cătălin Moraru, Dumitru Alexandru Bodislav, Loredana Maria Păunescu and Carmen Florentina Vlăsceanu
J. Theor. Appl. Electron. Commer. Res. 2024, 19(1), 340-361; https://doi.org/10.3390/jtaer19010018 - 8 Feb 2024
Cited by 3 | Viewed by 1505
Abstract
The emergence of the COVID-19 pandemic has resulted in notable transformations of the commerce landscape, particularly in the realm of electronic commerce. This sector has experienced a precipitous advancement, characterized by substantial modifications of online business under-takings, encompassing both products and services. The [...] Read more.
The emergence of the COVID-19 pandemic has resulted in notable transformations of the commerce landscape, particularly in the realm of electronic commerce. This sector has experienced a precipitous advancement, characterized by substantial modifications of online business under-takings, encompassing both products and services. The aim of the current research was to explore the similarities and differences between European Union member states in the context of e-commerce in the post-pandemic period, taking into consideration the population’s level of education, the risk of poverty, as well as households’ access to the internet. The analysis was conducted for the year 2021, which represented the most recent year for which data were available, and was based on the application of the hierarchical cluster methodology, which included the Ward method and the Robust Tests of Equality of Means (Welch and Brown–Forsythe). Five clusters resulted, which included a minimum of three countries and a maximum of nine. The present study focused on examining the similarities and disparities within clusters, as well as among countries belonging to those clusters. These observed similarities and disparities are believed to be the outcome of various indicators that influence the realm of electronic commerce, and they are contingent upon the economic development level of each country and their ability to cope with the challenges posed by the COVID-19 pandemic. The information obtained in this study pertains to the future of electronic commerce in the sense of identifying premises that allow the development and application of development strategies. Full article
(This article belongs to the Section e-Commerce Analytics)
Show Figures

Figure 1

25 pages, 893 KiB  
Article
A Game-Theoretic Analysis of the Adoption of Patient-Generated Health Data
by M. Tolga Akçura, Zafer D. Ozdemir and Hakan Tarakci
J. Theor. Appl. Electron. Commer. Res. 2024, 19(1), 315-339; https://doi.org/10.3390/jtaer19010017 - 8 Feb 2024
Viewed by 993
Abstract
Patient-generated health data (PGHD) have great potential to improve clinical outcomes. As providers consider whether and how to incorporate PGHD into their clinical workflows, platforms by Apple and Amazon stand to fundamentally alter the landscape. With the aim to examine the conditions under [...] Read more.
Patient-generated health data (PGHD) have great potential to improve clinical outcomes. As providers consider whether and how to incorporate PGHD into their clinical workflows, platforms by Apple and Amazon stand to fundamentally alter the landscape. With the aim to examine the conditions under which providers would adopt PGHD and possibly sign on with a platform, we analyzed the incentives and optimal strategies of two healthcare providers, a monopoly platform, and consumers using stylized game-theoretic models and solve for potential equilibria. We found that consumer surplus always increased with PGHD adoption, but social welfare may drop. The larger provider had more incentive to adopt PGHD than the smaller provider, but these incentives were reversed in the case of platform adoption. Accordingly, the platform enrolled the smaller provider first and possibly both providers. The emergence of the platform raised provider surplus, potentially at the expense of the consumers, despite offering its service to them for free. These results illustrate the importance of economic incentives regarding whether and how PGHD could be incorporated into our current healthcare system. Full article
Show Figures

Figure 1

18 pages, 2764 KiB  
Article
Financial Anti-Fraud Based on Dual-Channel Graph Attention Network
by Sizheng Wei and Suan Lee
J. Theor. Appl. Electron. Commer. Res. 2024, 19(1), 297-314; https://doi.org/10.3390/jtaer19010016 - 2 Feb 2024
Cited by 5 | Viewed by 1706
Abstract
This article addresses the pervasive issue of fraud in financial transactions by introducing the Graph Attention Network (GAN) into graph neural networks. The article integrates Node Attention Networks and Semantic Attention Networks to construct a Dual-Head Attention Network module, enabling a comprehensive analysis [...] Read more.
This article addresses the pervasive issue of fraud in financial transactions by introducing the Graph Attention Network (GAN) into graph neural networks. The article integrates Node Attention Networks and Semantic Attention Networks to construct a Dual-Head Attention Network module, enabling a comprehensive analysis of complex relationships in user transaction data. This approach adeptly handles non-linear features and intricate data interaction relationships. The article incorporates a Gradient-Boosting Decision Tree (GBDT) to enhance fraud identification to create the GBDT–Dual-channel Graph Attention Network (GBDT-DGAN). In a bid to ensure user privacy, this article introduces blockchain technology, culminating in the development of a financial anti-fraud model that fuses blockchain with the GBDT-DGAN algorithm. Experimental verification demonstrates the model’s accuracy, reaching 93.82%, a notable improvement of at least 5.76% compared to baseline algorithms such as Convolutional Neural Networks. The recall and F1 values stand at 89.5% and 81.66%, respectively. Additionally, the model exhibits superior network data transmission security, maintaining a packet loss rate below 7%. Consequently, the proposed model significantly outperforms traditional approaches in financial fraud detection accuracy and ensures excellent network data transmission security, offering an efficient and secure solution for fraud detection in the financial domain. Full article
Show Figures

Figure 1

25 pages, 3464 KiB  
Article
A Two-Stage Nonlinear User Satisfaction Decision Model Based on Online Review Mining: Considering Non-Compensatory and Compensatory Stages
by Shugang Li, Boyi Zhu, Yuqi Zhang, Fang Liu and Zhaoxu Yu
J. Theor. Appl. Electron. Commer. Res. 2024, 19(1), 272-296; https://doi.org/10.3390/jtaer19010015 - 1 Feb 2024
Cited by 4 | Viewed by 1354
Abstract
Mining user satisfaction decision stages from online reviews is helpful for understanding user preferences and conducting user-centered product improvements. Therefore, this study develops a two-stage nonlinear user satisfaction decision model (USDM). First, we use word2vec technology and lexicon-based sentiment analysis to mine the [...] Read more.
Mining user satisfaction decision stages from online reviews is helpful for understanding user preferences and conducting user-centered product improvements. Therefore, this study develops a two-stage nonlinear user satisfaction decision model (USDM). First, we use word2vec technology and lexicon-based sentiment analysis to mine the sentiment polarity of each product attribute in the reviews. Then, we develop KANO mapping rules using utility functions to classify consumer preferences based on attribute importance. Based on this, a two-stage nonlinear USDM is developed to describe post-purchase evaluation behavior. In the first non-compensatory stage, consumers determine their initial satisfaction level based on the performance of basic attributes. If the performance of these attributes is poor, it is almost impossible for users to be satisfied. In the compensatory stage, the performance of the remaining attributes collectively affects final satisfaction through participation in user utility calculation. With the use of reviews from JD.com, we develop a genetic algorithm to determine feasible solutions for the USDM and verify its validity and robustness. The USDM is proven to be effective in predicting user satisfaction compared to other classic models and machine learning algorithms. This study provides a universal pattern for user satisfaction decisions and extends the study on preference analysis. Full article
(This article belongs to the Topic Online User Behavior in the Context of Big Data)
Show Figures

Figure 1

23 pages, 1861 KiB  
Article
Value Co-Creation on TV Talent Shows: Cases from Mainland China, Taiwan and Hong Kong
by Wai-Kit Ng, Cheng-Ming Yang and Chun-Liang Chen
J. Theor. Appl. Electron. Commer. Res. 2024, 19(1), 249-271; https://doi.org/10.3390/jtaer19010014 - 31 Jan 2024
Viewed by 1683
Abstract
Through the actions and interactions of video platform users, talent shows have expanded from the entertainment sphere to the social sphere and become an everyday part of life. Watching talent shows on online platforms, especially through participation in multi-platform interaction, is an ever [...] Read more.
Through the actions and interactions of video platform users, talent shows have expanded from the entertainment sphere to the social sphere and become an everyday part of life. Watching talent shows on online platforms, especially through participation in multi-platform interaction, is an ever developing and innovative field in many regions. This study adopts a multiple case analysis approach. We analyze and compare three cases of talent shows, examining aspects of their value co-creation, digital platform, dynamic capability and value network through an exploration of a series of creative activities on digital video platforms. Talent shows provide a unique environment in which different actors interact, co-exist and co-create value, i.e., another form of O2O marketing. These actors include producers, entertainment companies, sponsors and fans, and fan value co-creation currently takes many different forms, which are experienced, engaged and interacted with through different platforms. The findings contribute to examining the underlying dynamics of TV talent shows, in addition to explaining how they are achieving sustainable advantages in the media market. Furthermore, this study aims to understand the service ecosystem of network talent shows from the perspective of industrial innovation strategy; consequently, this research can help to promote the implications of this new form of digital content services and its innovation strategies. Full article
(This article belongs to the Section Digital Business Organization)
Show Figures

Figure 1

17 pages, 2022 KiB  
Article
Demystifying the Combined Effect of Consistency and Seamlessness on the Omnichannel Customer Experience: A Polynomial Regression Analysis
by Wei Gao and Ning Jiang
J. Theor. Appl. Electron. Commer. Res. 2024, 19(1), 232-248; https://doi.org/10.3390/jtaer19010013 - 29 Jan 2024
Cited by 1 | Viewed by 1406
Abstract
Although channel consistency and seamlessness have been regarded as two critical factors in conducting omnichannel business, their combined effect has yet to be revealed. By employing a polynomial regression, this study disentangles the combined effect of channel consistency and seamlessness on customer experience [...] Read more.
Although channel consistency and seamlessness have been regarded as two critical factors in conducting omnichannel business, their combined effect has yet to be revealed. By employing a polynomial regression, this study disentangles the combined effect of channel consistency and seamlessness on customer experience in the omnichannel context. The results indicate that enhancing channel consistency and seamlessness simultaneously can improve the omnichannel customer experience. The combined effect of a high (low) level of channel consistency and a low (high) level of channel seamlessness on the omnichannel customer experience is also positive. Data vulnerability can strengthen the combined effect of channel consistency and seamlessness on customer experience in the omnichannel context. This study not only uncovers the complex influences of different combinations of channel consistency and seamlessness but also provides new insights into conducting omnichannel retail for practitioners. Full article
(This article belongs to the Section Digital Marketing and the Connected Consumer)
Show Figures

Figure 1

23 pages, 2556 KiB  
Article
Have Your Cake and Eat It? Price Discount Programs under the Membership Free Shipping Policy in Online Retailing
by Zhipeng Tang, Guowei Hua, Tai Chiu Edwin Cheng, Xiaowei Li and Jingxin Dong
J. Theor. Appl. Electron. Commer. Res. 2024, 19(1), 209-231; https://doi.org/10.3390/jtaer19010012 - 26 Jan 2024
Viewed by 1124
Abstract
Online retailers offer free shipping services, such as threshold free shipping (TFS) and membership free shipping (MFS), to promote sales and provide a better shopping experience to consumers in online retailing. Although MFS attracts more member-consumers, it encourages consumers to place more small [...] Read more.
Online retailers offer free shipping services, such as threshold free shipping (TFS) and membership free shipping (MFS), to promote sales and provide a better shopping experience to consumers in online retailing. Although MFS attracts more member-consumers, it encourages consumers to place more small orders than TFS, which significantly increases the operational costs of the online retailer. To address this issue, we propose two price discount policies under the MFS service, namely the limited-time discount and the threshold discount. Then, we build analytical models under these two policies to explore the impacts of offering price discounts on the retailer’s profit and consumers’ welfare. We find that no matter which discount policy is adopted, consumers are more likely to consolidate several small orders from different time periods into a big one to obtain the discount. The economies of scale generated by consumers consolidating their orders under these discount policies can help reduce online retailers’ operational costs. Therefore, regardless of any discount policy offered by the online retailer under the MFS service, consumers will place more big orders and more member-consumers are attracted, i.e., the online retailer can have its cake and eat it too. Our research findings provide decision-making insights for practitioners who offer free shipping services and price discounts to consumers in online retailing. Full article
(This article belongs to the Section e-Commerce Analytics)
Show Figures

Figure 1

21 pages, 326 KiB  
Article
Evolution of Men’s Image in Fashion Advertising: Breaking Stereotypes and Embracing Diversity
by María Jesús Carrasco-Santos, Carmen Cristófol-Rodríguez and Ismael Begdouri-Rodríguez
J. Theor. Appl. Electron. Commer. Res. 2024, 19(1), 188-208; https://doi.org/10.3390/jtaer19010011 - 24 Jan 2024
Viewed by 2718
Abstract
This research study explores the representation of men in fashion advertising and investigates whether societal and fashion evolution has contributed to a departure from traditional stereotypes. The research methodology comprised three phases: content analysis, surveys, and in-depth interviews with an expert panel, examining [...] Read more.
This research study explores the representation of men in fashion advertising and investigates whether societal and fashion evolution has contributed to a departure from traditional stereotypes. The research methodology comprised three phases: content analysis, surveys, and in-depth interviews with an expert panel, examining how men’s clothing has been communicated in fashion over a span of 50 years, with a focus on three renowned brands: Lacoste, Burberry, and Hugo Boss. The findings reveal a notable shift in fashion advertising targeting men, characterized by increased racial diversity among models and a more diverse depiction of attitudes and poses. However, homosexual or bisexual couples remain largely unrepresented. The study highlights the influence of advertising on shaping the image of the “new man”, evident through the diminishing gender boundaries in clothing and accessories and the persistent struggle to break free from stereotypes. The study underscores the significance of ongoing efforts to promote diversity and inclusivity in fashion advertising. Full article
16 pages, 7366 KiB  
Article
The Future of Electronic Commerce in the IoT Environment
by Antonina Lazić, Saša Milić and Dragan Vukmirović
J. Theor. Appl. Electron. Commer. Res. 2024, 19(1), 172-187; https://doi.org/10.3390/jtaer19010010 - 24 Jan 2024
Cited by 2 | Viewed by 2174
Abstract
The Internet of Things (IoT) was born from the fusion of virtual and physical space and became the initiator of many scientific fields. Economic sustainability is the key to further development and progress. To keep up with the changes, it is necessary to [...] Read more.
The Internet of Things (IoT) was born from the fusion of virtual and physical space and became the initiator of many scientific fields. Economic sustainability is the key to further development and progress. To keep up with the changes, it is necessary to adapt economic models and concepts to meet the requirements of future smart environments. Today, the need for electronic commerce (e-commerce) has become an economic priority during the transition between Industry 4.0 and Industry 5.0. Unlike mass production in Industry 4.0, customized production in Industry 5.0 should gain additional benefits in vertical management and decision-making concepts. The authors’ research is focused on e-commerce in a three-layer vertical IoT environment. The vertical IoT concept is composed of edge, fog, and cloud layers. Given the ubiquity of artificial intelligence in data processing, economic analysis, and predictions, this paper presents a few state-of-the-art machine learning (ML) algorithms facilitating the transition from a flat to a vertical e-commerce concept. The authors also propose hands-on ML algorithms for a few e-commerce types: consumer–consumer and consumer–company–consumer relationships. These algorithms are mainly composed of convolutional neural networks (CNNs), natural language understanding (NLU), sequential pattern mining (SPM), reinforcement learning (RL for agent training), algorithms for clicking on the item prediction, consumer behavior learning, etc. All presented concepts, algorithms, and models are described in detail. Full article
Show Figures

Figure 1

20 pages, 8257 KiB  
Article
A Consumer Behavior Analysis Framework toward Improving Market Performance Indicators: Saudi’s Retail Sector as a Case Study
by Monerah Alawadh and Ahmed Barnawi
J. Theor. Appl. Electron. Commer. Res. 2024, 19(1), 152-171; https://doi.org/10.3390/jtaer19010009 - 17 Jan 2024
Viewed by 3025
Abstract
Studying customer behavior and anticipating future trends is a challenging task, as customer behavior is complex and constantly evolving. To effectively anticipate future trends, businesses need to analyze large amounts of data, use sophisticated analytical techniques, and stay up-to-date with the latest research [...] Read more.
Studying customer behavior and anticipating future trends is a challenging task, as customer behavior is complex and constantly evolving. To effectively anticipate future trends, businesses need to analyze large amounts of data, use sophisticated analytical techniques, and stay up-to-date with the latest research and industry trends. In this paper, we propose a comprehensive framework to identify trends in consumer behavior using multiple layers of processing, including clustering, classification, and association rule learning. The aim is to help a major retailer in Saudi Arabia better understand customer behavior by utilizing the power of big data analysis. The proposed framework is presented as being generalized to gain insight into the generated big data and enable data-driven decision-making in other relevant domains. We developed this framework in collaboration with a large supermarket chain in Saudi Arabia, which provided us with over 1,000,000 sales transaction records belonging to around 30,000 of their loyal customers. In this study, we apply our proposed framework to those data as a case study and present our initial results of consumer clustering and association rules for each cluster. Moreover, we analyze our findings to figure out how we can further utilize intelligence to predict customer behavior in clustered groups. Full article
(This article belongs to the Topic Online User Behavior in the Context of Big Data)
Show Figures

Figure 1

17 pages, 761 KiB  
Article
It’s Not Always about Wide and Deep Models: Click-Through Rate Prediction with a Customer Behavior-Embedding Representation
by Miguel Alves Gomes, Richard Meyes, Philipp Meisen and Tobias Meisen
J. Theor. Appl. Electron. Commer. Res. 2024, 19(1), 135-151; https://doi.org/10.3390/jtaer19010008 - 12 Jan 2024
Viewed by 1613
Abstract
Alongside natural language processing and computer vision, large learning models have found their way into e-commerce. Especially, for recommender systems and click-through rate prediction, these models have shown great predictive power. In this work, we aim to predict the probability that a customer [...] Read more.
Alongside natural language processing and computer vision, large learning models have found their way into e-commerce. Especially, for recommender systems and click-through rate prediction, these models have shown great predictive power. In this work, we aim to predict the probability that a customer will click on a given recommendation, given only its current session. Therefore, we propose a two-stage approach consisting of a customer behavior-embedding representation and a recurrent neural network. In the first stage, we train a self-supervised skip-gram embedding on customer activity data. The resulting embedding representation is used in the second stage to encode the customer sequences which are then used as input to the learning model. Our proposed approach diverges from the prevailing trend of utilizing extensive end-to-end models for click-through rate prediction. The experiments, which incorporate a real-world industrial use case and a widely used as well as openly available benchmark dataset, demonstrate that our approach outperforms the current state-of-the-art models. Our approach predicts customers’ click intention with an average F1 accuracy of 94% for the industrial use case which is one percentage point higher than the state-of-the-art baseline and an average F1 accuracy of 79% for the benchmark dataset, which outperforms the best tested state-of-the-art baseline by more than seven percentage points. The results show that, contrary to current trends in that field, large end-to-end models are not always needed. The analysis of our experiments suggests that the reason for the performance of our approach is the self-supervised pre-trained embedding of customer behavior that we use as the customer representation. Full article
(This article belongs to the Topic Online User Behavior in the Context of Big Data)
Show Figures

Figure 1

Previous Issue
Next Issue
Back to TopTop