Hasil untuk "Commerce"

Mahmood Hajli

Chang Liu, K. Arnett

J. Horner

T. Oliveira, Matilde Alhinho, P. Rita et al.

T. Nisar, G. Prabhakar

Lei Cui, Shaohan Huang, Furu Wei et al.

Conventional customer service chatbots are usually based on human dialogue, yet significant issues in terms of data scale and privacy. In this paper, we present SuperAgent, a customer service chatbot that leverages large-scale and publicly available e-commerce data. Distinct from existing counterparts, SuperAgent takes advantage of data from in-page product descriptions as well as user-generated content from e-commerce websites, which is more practical and cost-effective when answering repetitive questions, freeing up human support staff to answer much higher value questions. We demonstrate SuperAgent as an add-on extension to mainstream web browsers and show its usefulness to user’s online shopping experience.

Jetlir Duraj, Ishita Khan, Kilian Merkelbach et al.

Search in e-Commerce is powered at the core by a structured representation of the inventory, often formulated as a category taxonomy. An important capability in e-Commerce with hierarchical taxonomies is to select a set of relevant leaf categories that are semantically aligned with a given user query. In this scope, we address a fundamental problem of search query categorization in real-world e-Commerce taxonomies. A correct categorization of a query not only provides a way to zoom into the correct inventory space, but opens the door to multiple intent understanding capabilities for a query. A practical and accurate solution to this problem has many applications in e-commerce, including constraining retrieved items and improving the relevance of the search results. For this task, we explore a novel Chain-of-Thought (CoT) paradigm that combines simple tree-search with LLM semantic scoring. Assessing its classification performance on human-judged query-category pairs, relevance tests, and LLM-based reference methods, we find that the CoT approach performs better than a benchmark that uses embedding-based query category predictions. We show how the CoT approach can detect problems within a hierarchical taxonomy. Finally, we also propose LLM-based approaches for query-categorization of the same spirit, but which scale better at the range of millions of queries.

Ali Yusuf, Ab Razak Che Hussin, Abdelsalam H. Busalim

Purpose As a business paradigm, social commerce (s-commerce) has brought about a new stage of innovation, and by extension, has transmuted the power from seller to buyer. S-commerce is a combination a commercial and social activities in which individuals may spread word of mouth (WOM) about their shopping experiences and knowledge and provide information about product and services to their to their friends. This kind of social interactions among individuals has increased the potentials of eWOM communication. Given such a backdrop, this paper aims to look into the influence of eWOM engagement on consumers’ purchase intention in s-commerce, which may complement the current effort of the research community in this area. Design/methodology/approach This study used elaboration likelihood model, theory of reasoned action and social support theory to investigate the influence of eWOM engagement on consumers’ purchase intention in s-commerce. The study used 218 respondents to evaluate the proposed model using SmartPLS. Findings The empirical results indicate that information characteristics, consumer behavior and technological factors exert a positive influence on consumer purchase intentions. All hypotheses between attitude toward eWOM, information credibility, innovativeness, website quality and eWOM engagement are significant. Also, eWOM engagement has a significant positive influence on consumer purchase intention. However, information quality and social support does not have any significant relationship with eWOM engagement. Research limitations/implications This study seeks to address the dearth of research in the field of s-commerce, especially as it relates to eWOM. The study proposes a new model and empirically validates the hypothesized relationships. This research can serve as a stepping stone for future research in this field. Practical implications This study is one of the early studies focusing on the influence of eWOM engagement, especially in s-commerce. The study offers comprehensive and empirically validated factors pertaining to eWOM engagement in s-commerce. The results of this study are also important to practitioners and online companies’ managers. The study’s model has demonstrated the contextualization of what makes customers engage in eWOM and its influence in s-commerce. The study will also offer insights for firms on how to encourage eWOM engagement among customers. Originality/value A new eWOM engagement model in s-commerce is proposed with consideration on information characteristics, consumer behavior, technological and social factors. The model is validated afterwards.

Xuan Li, Yuting Peng, Xiaoxuan Sun et al.

With the rapid development of e-commerce, e-commerce platforms are facing an increasing number of fraud threats. Effectively identifying and preventing these fraudulent activities has become a critical research problem. Traditional fraud detection methods typically rely on supervised learning, which requires large amounts of labeled data. However, such data is often difficult to obtain, and the continuous evolution of fraudulent activities further reduces the adaptability and effectiveness of traditional methods. To address this issue, this study proposes an unsupervised e-commerce fraud detection algorithm based on SimCLR. The algorithm leverages the contrastive learning framework to effectively detect fraud by learning the underlying representations of transaction data in an unlabeled setting. Experimental results on the eBay platform dataset show that the proposed algorithm outperforms traditional unsupervised methods such as K-means, Isolation Forest, and Autoencoders in terms of accuracy, precision, recall, and F1 score, demonstrating strong fraud detection capabilities. The results confirm that the SimCLR-based unsupervised fraud detection method has broad application prospects in e-commerce platform security, improving both detection accuracy and robustness. In the future, with the increasing scale and diversity of datasets, the model's performance will continue to improve, and it could be integrated with real-time monitoring systems to provide more efficient security for e-commerce platforms.

Puneet S. Bagga, Vivek F. Farias, Tamar Korkotashvili et al.

With the rise of large language models (LLMs), generative engines are becoming powerful alternatives to traditional search, reshaping retrieval tasks. In e-commerce, for instance, conversational shopping agents now guide consumers to relevant products. This shift has created the need for generative engine optimization (GEO)--improving content visibility and relevance for generative engines. Yet despite its growing importance, current GEO practices are ad hoc, and their impacts remain poorly understood, especially in e-commerce. We address this gap by introducing E-GEO, the first benchmark built specifically for e-commerce GEO. E-GEO contains over 7,000 realistic, multi-sentence consumer product queries paired with relevant listings, capturing rich intent, constraints, preferences, and shopping contexts that existing datasets largely miss. Using this benchmark, we conduct the first large-scale empirical study of e-commerce GEO, evaluating 15 common rewriting heuristics and comparing their empirical performance. To move beyond heuristics, we further formulate GEO as a tractable optimization problem and develop a lightweight iterative prompt-optimization algorithm that can significantly outperform these baselines. Surprisingly, the optimized prompts reveal a stable, domain-agnostic pattern--suggesting the existence of a "universally effective" GEO strategy. Our data and code are publicly available at https://github.com/psbagga17/E-GEO.

Mohammad Olid Ali Akash, Priyangana Saha

In the modern, fast-moving world of e-commerce, many Android apps face challenges in providing a simple and secure shopping experience. Many of these apps, often enough, have complicated designs that prevent users from finding what they want quickly, thus frustrating them and wasting their precious time. Another major issue is that of security; with the limitation of payment options and weak authentication mechanisms, users' sensitive information can be compromised. This research presents a new e-commerce platform that responds to the above challenges with an intuitive interface and strong security measures. The platform makes online shopping easy with well-organized categories of products and a fast, efficient checkout process. It also gives priority to security by incorporating features such as Google authentication and SSL-secured payment gateways to protect user data and ensure secure transactions. This paper discusses how a focus on user-friendliness, security, and personalization steps up the game for e-commerce platforms, providing workable frameworks that match modern user needs and expectations. The findings show the e-commerce user experience can be remodelled by the platform, hence opening ways for future developments in that respect.

Li Zhao, Bing Fu, Sha Bai

While consumers experience shopping convenience through personalized recommendations, they are increasingly concerned about their consumption behavior being manipulated, leading to psychological resistance towards personalized recommendations. As such, research on how personalized recommendation services influence consumers’ perceptions of self-determination (which further influences their intentions to purchase) is called for. To address the gap, this current research adopts a self-determination perspective to investigate how the three basic psychological needs of self-determination (autonomy, competence, and relatedness) mediate the relationship between personalized recommendations and consumers’ purchase intentions. Moreover, this research examines whether the influence of personalized recommendations on consumers’ perceptions of self-determination is contingent upon product categories. The results of a hypothetical scenario experiments study demonstrate that competence and relatedness are critical mediators between recommendation novelty and purchase intention. The results also reveal that the impact of recommendation diversity on autonomy is contingent upon product categories, while the influence of recommendation novelty on relatedness is also contingent on product categories. This study contributes to the literature on personalized recommendations by providing an underlying mechanism for the influence of personalized recommendations on consumers’ purchase intention from the self-determination perspective, and especially by unravelling how the influence of personalized recommendations on consumers’ perceptions of self-determination is contingent upon product categories.

Diva Lúcia Vieira Costa, Claudia Rocha Mourthé

O design de moda é um sistema complexo, que possui como alicerce a gestão estratégica de informações provenientes da pesquisa e da utilização de dados para a criação de novos produtos do vestuário. Com a evolução da tecnologia, bem como as mudanças no mercado de moda e nas dinâmicas de vida das pessoas, surgem demandas personalizadas de consumo. Para que os processos do design de moda sejam adequados às demandas cada vez mais personalizadas, faz-se necessário revisitar pensamentos projetuais para a criação de produtos do vestuário. O objetivo deste artigo consiste em realizar a proposta de um framework para o design de moda, com ênfase nos processos de criação de novos produtos do vestuário para o contexto da customização em massa. Utilizou-se como metodologia as pesquisas bibliográfica e documental, para relacionar as bases teóricas do design de moda e da customização em massa com as práticas encontradas em diferentes setores da indústria têxtil e de confecção. Como resultado, o frameworkevidencia a necessidade da valorização do envolvimento do cliente, principalmente durante o processo de design. Isso irá possibilitar identificar tanto os componentes comuns, quanto as diferentes perspectivas que ampliarão o potencial criativo no design de produtos de vestuário para a customização em massa.

Perera, K.H, Kumara, A.S., Munasinghe, M.A.T.K.

The purpose of this paper is to explore the multi-dimensional determinants of voluntary tax compliance on the head of individual taxpayers. It critically appraises major theoretical frameworks and offers an extensive conceptual framework. The study is based on the qualitative methodology and performs the content analysis to synthesize information and form the conceptual model. VOSviewer software was used to conduct bibliometric analysis, spreadsheets were employed to study the data obtained and results were presented in terms of tables, graphs and figures to become more precise. The results also suggest that economic incentives, enforcement measures, human values, social obligation, and the perceptions of justice are a significant factor to influence voluntary compliance, and such personal values and ethical considerations become the key determinants, which supplement enforcement. The study advances the existing literature by incorporating personal values in the discussion of the topic of tax compliance in the context of developing countries, providing new perspectives to the policymakers aimed at developing a tax culture based on voluntary compliance with the help of clear, equitable and culturally competent policies.

Ting Chi

This study proposes and applies an extended technology acceptance model (TAM) that incorporates brand equity and website quality as determinants of perceived usefulness and perceived ease†of†use to predict Chinese consumer intention to use apparel mobile commerce (m-commerce). 786 eligible responses were collected via an online questionnaire survey. The psychometric properties of the proposed extended TAM model were examined and the multiple regression method was applied to test the hypotheses. All dimensions of brand equity (i.e., brand loyalty, brand association, brand perceived quality, and brand image) significantly affect Chinese consumer perceived ease of use of apparel m-commerce while brand loyalty, perceived quality, and image enhance consumer perceived usefulness. This suggests a greater need for attention to branding effect within an increasingly saturated apparel m-commerce channel. All dimensions of website quality (i.e., website system quality, information quality, and service quality) significantly influence consumer perceived usefulness of apparel m-commerce while website system quality and information quality increase perceived use easiness. These website qualities play an important role in meeting the needs of consumers who are looking for good usability of mobile shopping. Both perceived usefulness and perceived ease of use result in positive consumer attitudes toward shopping apparel via m-commerce channel. The positive attitude and perceived usefulness lead to a greater likelihood for Chinese consumers to use apparel m-commerce. The research model exhibits a high explanatory power, collectively accounting for 64.6% of the variance in Chinese consumer intention to use apparel m-commerce.

Amrutha Muralidhar, Yathindra Lakkanna

Over the past years, e-commerce platforms have expanded substantially, providing customers with convenient shopping experiences. To enhance e-commerce websites, it's essential to grasp user engagement and factors affecting conversion rates. This optimization is achieved by aligning platforms with user expectations, thereby fostering successful online shopping experiences, and contributing to sustained growth in the dynamic digital marketplace. In this paper, we conduct a comprehensive analysis focusing on user interactions, conversion metrics, and the entire user journey within an e-commerce platform. Our exploration spans exit rates and sessions across different devices and browsers, conversion rates for various traffic sources, and the user journey from product details to checkout. Findings suggest a need for targeted improvements in mobile optimization and browser compatibility, indicated by higher exit rates on mobile devices and varying rates on different browsers. The conversion rate analysis emphasizes the varying effectiveness of traffic sources, highlighting the potential of advertised mediums, while identifying areas for improvement in referral and affiliate traffic. Examining the user journey showed potential bottlenecks in the conversion process, the identified gap was between user interest and completed transactions. Our study suggests improving the checkout process strategically to streamline user transactions. These insights provide actionable guidance for businesses seeking to refine their platforms and optimize performance in the ever-evolving landscape of e-commerce.

Himangshu Paul, Alexander Nikolaev

Must we trace and block all fake content in a social commerce network so that genuine users may enjoy fake-free information? Such efforts largely fail, because, as we get better at spam detection, spammers use the same advances for anti-detection. As a fundamentally new approach, we show that an online platform can aggregate and route user-generated content in a smart personalized way, which fosters and relies on "collective social responsibility". We introduce the notion of information aggregation domain, or simply, domain: composed for a given "central" node (user account), a domain is a connected set of nodes whose user-generated content is eligible to be used to meet the central node's information needs. Admitting malicious information sources - "bad citizen" nodes - into "good citizen" nodes' domains puts the good citizens at risk for disinformation attacks. We show how a platform can limit this risk by exploiting the social link structure between its nodes without the need to know which nodes are good or bad citizens. We introduce Relaxed Clique Percolation (RCP), a class of policies to compose personalized disinformation-resilient domains. Then, we define "RCP cores" and show how they can be used to efficiently compose resilient domains for all network nodes at once. Finally, we analyze the properties of RCP domains found in real-world social networks including Slashdot, Facebook, Flickr, and Yelp, to affirm that in practice, RCP domains turn out to be large and spatially diverse.

Irem Islek, Sule Gunduz Oguducu

Recommendation systems can provide accurate recommendations by analyzing user shopping history. A richer user history results in more accurate recommendations. However, in real applications, users prefer e-commerce platforms where the item they seek is at the lowest price. In other words, most users shop from multiple e-commerce platforms simultaneously; different parts of the user's shopping history are shared between different e-commerce platforms. Consequently, we assume in this study that any e-commerce platform has a complete record of the user's history but can only access some parts of it. If a recommendation system is able to predict the missing parts first and enrich the user's shopping history properly, it will be possible to recommend the next item more accurately. Our recommendation system leverages user shopping history to improve prediction accuracy. The proposed approach shows significant improvements in both NDCG@10 and HR@10.

Shuo Zhang, Boci Peng, Xinping Zhao et al.

The e-commerce platform has evolved rapidly due to its widespread popularity and convenience. Developing an e-commerce shopping assistant for customers is crucial to aiding them in quickly finding desired products and recommending precisely what they need. However, most previous shopping assistants face two main problems: (1) task-specificity, which necessitates the development of different models for various tasks, thereby increasing development costs and limiting effectiveness; and (2) poor generalization, where the trained model performs inadequately on up-to-date products. To resolve these issues, we employ Large Language Models (LLMs) to construct an omnipotent assistant, leveraging their adeptness at handling multiple tasks and their superior generalization capability. Nonetheless, LLMs lack inherent knowledge of e-commerce concepts. To address this, we create an instruction dataset comprising 65,000 samples and diverse tasks, termed as EshopInstruct. Through instruction tuning on our dataset, the assistant, named LLaSA, demonstrates the potential to function as an omnipotent assistant. Additionally, we propose various inference optimization strategies to enhance performance with limited inference resources. In the Amazon KDD Cup 2024 Challenge, our proposed method, LLaSA, achieved an overall ranking of 3rd place on ShopBench, including 57 tasks and approximately 20,000 questions, and we secured top-5 rankings in each track, especially in track4, where we achieved the best performance result among all student teams. Our extensive practices fully demonstrate that LLMs possess the great potential to be competent e-commerce shopping assistants.

Christian Herold, Michael Kozielski, Leonid Ekimov et al.

We introduce the LiLiuM series of large language models (LLMs): 1B, 7B, and 13B parameter models developed 100% in-house to fit eBay's specific needs in the e-commerce domain. This gives eBay full control over all aspects of the models including license, data, vocabulary, and architecture. We expect these models to be used as a foundation for fine-tuning and instruction-tuning, eliminating dependencies to external models. The LiLiuM LLMs have been trained on 3 trillion tokens of multilingual text from general and e-commerce domain. They perform similar to the popular LLaMA-2 models on English natural language understanding (NLU) benchmarks. At the same time, we outperform LLaMA-2 on non-English NLU tasks, machine translation and on e-commerce specific downstream tasks. As part of our data mixture, we utilize the newly released RedPajama-V2 dataset for training and share our insights regarding data filtering and deduplication. We also discuss in detail how to serialize structured data for use in autoregressive language modeling. We provide insights on the effects of including code and parallel machine translation data in pre-training. Furthermore, we develop our own tokenizer and model vocabulary, customized towards e-commerce. This way, we can achieve up to 34% speed-up in text generation on eBay-specific downstream tasks compared to LLaMA-2. Finally, in relation to LLM pretraining, we show that checkpoint averaging can further improve over the best individual model checkpoint.