Modern E-commerce Research Articles

The Influential Mechanisms of Live-Streaming Hosts on Consumer Behavior

In recent years, with the rise of e-commerce live streaming, hosts promoting products have played a crucial role in connecting consumers with products and influencing consumer behavior intentions. This paper reviews the current state and trends in research on how these hosts affect consumer behavior intentions, exploring how their personal characteristics, interaction patterns, and discourse strategies impact consumer purchasing decisions. Through analysis from both quantitative and qualitative research perspectives, it reveals the influence mechanisms of these hosts in modern e-commerce environments. Additionally, it discusses the pivotal role of interactive information in e-commerce live streaming, including its ability to enhance purchase desire, enrich entertainment experiences, and improve consumer shopping experiences. While existing studies provide valuable insights, there are still research gaps, particularly in-depth studies on the influence of hosts in specific domains. The findings of this review are significant for understanding the central role of hosts in e-commerce live streaming and their impact on consumer behavior, providing a theoretical foundation and support for future research and practice.

The Impact of Short Videos and Live Streaming on E-commerce Consumers Purchasing Decisions

With the increasing popularity of online live broadcasts and short movies in e-commerce, the influence on customer purchasing behaviour has received extensive attention. This study seeks to investigate the influence of short films and live broadcasts on consumer purchasing decisions, with a particular emphasis on purchase intention, repeat purchase intention, and impulse consuming behaviour. The research used a literature review strategy to examine the particular influence of various live broadcast aspects on customer purchase decisions. This study discovered that short films and live broadcasts, due to their high engagement and immersive experience, may greatly improve customers' brand identity and happiness, resulting in increased buy and repeat purchase intentions. Furthermore, elements like real-time interaction, music and visual effects, and quick feedback can assist customers lower perceived risks and boost confidence in their purchase decisions. According to research findings, short films and live broadcasts are not only excellent marketing tools, but also essential strategic measures in modern e-commerce.

Performance assessment of a multi-level shuttle system: an optimisation-embedded simulation study on time and energy consumption

ABSTRACT In response to the dynamic demands of modern e-commerce and supply chains, this paper addresses the critical need for adaptability and efficiency through the implementation of automated storage and retrieval systems. By using an optimisation-embedded simulation methodology, the proposed study focuses on a multi-level shuttle system designed to overcome the inherent limitations of traditional storage systems. A comprehensive discrete event simulation model is developed to evaluate the performance of the multi-level shuttle system. This model includes calculations of travel time and energy consumption, taking also into account stochastic handling times associated with repetitive tasks. In addition, a dynamic programming algorithm is integrated in the simulation model to optimise the sequencing of storage and retrieval missions performed by the handling machine. The study systematically investigates various design and operational parameters, including warehouse configurations and capacity, simultaneous handling of multiple unit loads, and the dimensions of the optimisation sessions. For all configurations tested, the research demonstrates operational advantages in the simultaneous handling of two unit loads. Theoretical contributions extend the current state of simulation models for automated warehousing systems. For practitioners, the study provides empirical insights to support decision making in the configuration of automated warehouses.

Knowledge Graph-Based Integration of Conversational Advisors and Faceted Filtering

Abstract Modern e-commerce websites often provide users with a variety of components, such as faceted filters and conversational recommender systems, that act as product advisors to help them find relevant products. However, these components are often treated separately and presented as independent components, leading to increased cognitive load and disruption in the search process. Also, the reasoning behind the resulting product recommendations is often not transparent. To address these limitations, we propose a novel approach that relies on a knowledge graph structure to seamlessly integrate faceted filtering and conversational advisors based on graphical user interfaces (GUI). Concretely, the knowledge graph is used to suggest filter values and products based on the user’s answers in the advisor, and, conversely, to determine follow-up questions based on the user’s selected filter values. The user interface also visualizes and explains the underlying relationships between answers given to the advisor and relevant product features in the filter component in order to increase the transparency of the search process. We conducted two user studies with a total of 448 participants to compare a system that integrates the different components according to our approach with a baseline system in which the mechanisms operate separately. Sequence analysis of the logged interaction data provided insights into participants’ behavior as they interacted with both systems. The results indicate that displaying recommended products and related explanations directly in the filter component increases acceptance and trust in the system. Also, the combination of a conversational advisor with values displayed in a filter interface, along with explanations of the underlying relationships, significantly contributes to the knowledge and understanding of those product features that are important in terms of the current search goal.

The LSTM-EMPG Model for Next Basket Recommendation in E-commerce

Personalized recommendations play a crucial role in the modern e-commerce landscape, enabling businesses to meet customers' evolving preferences and boost sales. As customer preferences change, businesses are realizing the importance of suggesting what customers might want to buy next. However, existing approaches face challenges in capturing sequential patterns in user behavior and accurately utilizing previous purchase information. These challenges can be addressed using Long Short-Term Memory Networks (LSTMs). Nevertheless, LSTMs alone may not fully capture users' repetitive purchase behavior or consider the exact timing of purchases. To account for these limitations, Probabilistic Models such as the Modified Poisson Gamma model (MPG) can be employed. The research reported in this paper proposes and investigates a new approach for the next basket recommendation based on the integration of LSTM with an enhanced Modified Poisson Gamma model to enhance next basket recommendation accuracy in e-commerce. The enhanced model (EMPG) includes a refinement of the MPG model to increase its predictive accuracy, and its recommendations are then integrated with an LSTM network to optimize the LSTM’s predictions. The proposed hybrid LSTM-EMPG model has been evaluated on the Instacart dataset and has produced superior results compared to the Multi-period LSTM, the GRU-based model. DREAM (RNN), and DREAM (LSTM) in terms of predictive accuracy, achieving a higher precision and recall.

Telwind Web application with power to track orders placed by customers

Abstract : In the context of e-commerce, modules refer to various components or features that contribute to the functioning and success of an online store. Depending on the type of your company and your objectives, the significance of particular modules may differ. Nonetheless, the following essential e-commerce modules are often regarded crucial. The complete order lifecycle is managed by this module, including order placing, fulfillment, and tracking. Order processing, invoicing, order status updates, and interaction with shipping companies are some of its capabilities.To provide customers the greatest possible purchasing experience, modern e-commerce companies need a feature-rich collection of components. More flexibility is available when each functional area is divided into its own module.

Telwind Powered web application for tracking customer orders

Abstract : In the context of e-commerce, modules refer to various components or features that contribute to the functioning and success of an online store. Depending on the type of your company and your objectives, the significance of particular modules may differ. Nonetheless, the following essential e-commerce modules are often regarded crucial. The complete order lifecycle is managed by this module, including order placing, fulfillment, and tracking. Order processing, invoicing, order status updates, and interaction with shipping companies are some of its capabilities.To provide customers the greatest possible purchasing experience, modern e-commerce companies need a feature-rich collection of components. More flexibility is available when each functional area is divided into its own module. Keyword-ASP.net, Django, web application

AI Transforms Ecommerce Management and Regulation in Uzbekistan

This study investigates the integration of artificial intelligence (AI) into Uzbekistan's e-commerce sector, aiming to enhance business management, develop new models, and increase governmental regulatory effectiveness. By employing mathematical models based on a knowledge base and product logic principles, the research predicts and facilitates alternative management decisions, improving market monitoring and administrative procedures. The findings reveal that AI significantly enhances decision-making quality and regulatory efficiency, suggesting its potential as a cornerstone for modern e-commerce management strategies. This contributes to the advancement of the digital economy and the improvement of business and consumer conditions in Uzbekistan. Highlights: AI Integration: Enhances decision-making and administrative procedures in Uzbekistan's e-commerce sector. Mathematical Models: Uses knowledge bases and product logic to improve market monitoring and management decisions. Economic Impact: Contributes to the development of the digital economy, benefiting businesses and consumers. Keywords: Public Administration, E-commerce, Digital Economy, Artificial Intelligence, Regulatory Efficiency

RETRACTED: Empowering modern E-commerce consumers: Optimized deep learning for product image classification in home shopping

This article has been retracted. A retraction notice can be found at https://doi.org/10.3233/JIFS-219433.

Развитие определения термина "маркетплейс" как ключевого элемента современной электронной коммерции

статья представляет собой глубокий анализ эволюции и понимания понятия "маркетплейс" в контексте электронной коммерции. Проведен анализ исторического пути развития торговли, выявляя моменты включения электронных маркетплейсов в научную мысль. Рассмотрены ранние работы, а также современные исследования, подчеркивая динамичность маркетплейсов в ходе современной экономике. Особое внимание уделяется разнообразию терминологии, используемой для описания маркетплейсов, и рассматриваются различные примеры таких терминов. Выявлено, что ни одно из существующих определений не учитывает специфики бизнес-моделей и стейкхолдеров самих маркетплейсов, что подчеркивает необходимость нового подхода. С научной точки зрения, исследование предлагает широкий обзор определений маркетплейса, создавая фундамент для будущих теоретических исследований в области электронной коммерции. Таким образом, данное исследование предоставляет не только практическую пользу для бизнеса, но и академическую ценность, способствуя развитию понимания эволюции и влияния маркетплейсов в современной экономике. the article constitutes a profound analysis of the evolution and understanding of the term "marketplace" in the context of electronic commerce. An analysis of the historical path of trade development was carried out, identifying moments of inclusion of electronic marketplaces in scientific thought. Early works, as well as contemporary studies, was reviewed, highlighting the dynamics of marketplaces in the context of the modern economy. Particular attention is paid to the variety of terminology used to describe marketplaces, and various examples of such terms are considered. It is revealed that none of the existing definitions take into account the specificities of marketplace business models and stakeholders, underscoring the need for a new approach. From a scientific standpoint, the study provides a broad overview of marketplace definitions, laying the groundwork for future theoretical research in the field of electronic commerce. Thus, this research provides not only practical utility for businesses but also academic value, contributing to the development of understanding the evolution and impact of marketplaces in the contemporary economy.

Analysis of the economic activity of an online store using web analytics tools

The modern e-commerce market is an economic environment with a high level of competition. That is why achieving commercial success in it largely depends on the ability of trade organizations to analyze and optimize their activities based on the data provided by web analytics services. The article highlights the importance of web analytics for evaluating and improving the performance of an online store. The opportunities provided by the two leading tools in this area, Google Analytics and Yandex Metrica, are reviewed. The focus is on conversion analysis, understanding the target audience and optimizing marketing efforts. The article offers a comprehensive approach to the use of web analytics in order to increase economic efficiency and ensure sustainable growth of economic performance indicators of an online store.

A hybrid evolutionary JAYA algorithm based on global optimization for 5G e-commerce logistics

With the increasing demand for logistics in modern society, how to achieve low-cost and efficient logistics delivery has become an urgent research topic. A hybrid evolutionary JAYA algorithm (H-JAYA) based on global optimization was designed to address the complex path planning problem of electric vehicles. This algorithm introduces a reverse learning mechanism to calculate the current optimal and worst individuals, while using differential perturbation mechanism and sine cosine operator to update the individual’s position. In addition, the study used the H-JAYA algorithm to construct a corresponding mathematical model for the optimization problem of electric vehicle paths. The results showed that in the three examples, the H-JAYA algorithm tested the optimal curve convergence speed, and it tended to stabilize after about 30 iterations. Meanwhile, in the RCDP5001 example, the total cost of the H-JAYA algorithm reached the lowest value of 623 yuan. The H-JAYA algorithm has significant advantages in solving the distribution path problem of electric vehicles, and can be well applied to practical logistics distribution, providing effective technical support for modern e-commerce logistics planning.

СТАН НАУКОВОЇ ДУМКИ ЩОДО СПЕЦИФІКИ ЦИФРОВОГО МАРКЕТИНГУ В ДІЯЛЬНОСТІ ПІДПРИЄМСТВ ЕЛЕКТРОННОЇ КОМЕРЦІЇ

The aim of this article is to provide a comprehensive review of the development of scientific thought regarding the specific use of digital marketing tools in the activities of e-commerce enterprises. This includes an analysis of how various digital marketing tools, such as SEO, social media marketing, remarketing, video marketing, and others, impact customer acquisition, activation, retention, referral, and revenue generation in e-commerce businesses. The article examines the theoretical and practical aspects of these tools, their effectiveness, and their influence on business growth. Particular attention is given to the analysis of recent research and trends in this field, as well as recommendations for the optimal use of digital marketing strategies to achieve maximum results. By examining the evolution of these tools and their application, the article seeks to provide a thorough understanding of how digital marketing tools can be integrated into the e-commerce business model to ensure sustainable growth and competitive advantage in the market. This includes the utilization of frameworks such as AARRR (Acquisition, Activation, Retention, Referral, Revenue), which help in systematically managing various stages of user interaction and improving marketing strategies. The review focuses on the multifaceted nature of digital marketing, exploring how different tools can be employed at various stages of the customer journey. For instance, SEO and social media marketing are essential for attracting new users, while remarketing and email marketing play a crucial role in re-engaging existing customers. Video marketing and influencer marketing, on the other hand, help in building brand awareness and fostering customer loyalty. Moreover, the article delves into the synergistic effects of combining multiple digital marketing tools to enhance overall marketing efficacy. It discusses the importance of integrating data analytics and customer relationship management (CRM) systems to track and analyze user behavior, thus enabling more personalized and targeted marketing efforts. Through this detailed review, the article aims to shed light on the critical importance of digital marketing in the modern e-commerce landscape. It emphasizes the need for businesses to stay abreast of the latest developments and continuously adapt their marketing strategies to remain competitive. By leveraging the insights and recommendations provided, e-commerce enterprises can better navigate the complexities of digital marketing and achieve sustained growth and success.

ХАРАКТЕРИСТИКИ ІНФРАСТРУКТУРИ ЕЛЕКТРОННОЇ ТОРГІВЛІ: ВИКЛИКИ ТА ПЕРСПЕКТИВИ РОЗВИТКУ

The article highlights the interpretation of the term "electronic commerce" in the context of its institutional and component prismatic perception. Features of the functioning of electronic commerce in the modern global geo-economic climate are outlined. The results of the latest research and publications are analyzed. The influence of the pandemic climate, which treated the fundamental principles of traditional economic activity, was studied. Geopolitical threats caused by Russian aggression against Ukraine are considered. Indicators illustrating the importance of the field of digital entrepreneurship were analyzed. The information of the Forbes Advisor online platform of economic direction was processed, and the global e-commerce market in 2024 was studied. It is proved that the indicators of the mobility and adaptability of the e-commerce phenomenon are such attributive properties as: geographical distribution of the electronic potential of digital commerce, the concentrated advantage of American multinational corporations in the digital commerce market, the integrability of the digital commerce phenomenon. The results of the annual Global Digital Overview report, as of the beginning of 2023, were studied, and it was determined that the indicators of the information gap also characterize the architecture of the Ukrainian online market. The problem of information inequality, which arose in the context of the world's struggle with the devastating consequences of the COVID-19 pandemic, is considered. The fundamental differences of the modern form of digital commerce from the structure of traditional trade are analyzed. The specified nature of electronic commerce demonstrates the integrativeness, interconnectedness, and sensitive adaptability to the relevant mainstreams of the modern geo-economic climate inherited from globalization. Current trends in e-commerce architecture are illustrated, namely the leading actors of the global digital market – both state players and transnational corporations. A trend-based argumentation for trading efficiency of a new type of productivity is described, which can be illustrated by a triad of levels. The key components of the overall potential of modern e-commerce are highlighted - "social" and "mobile" trade. Significant threats and prospects for the development of the phenomenon of "electronic commerce" are highlighted.

Analysis of the Application of AIGC in Modern E-Commerce Poster Design

Analysis of the Application of AIGC in Modern E-Commerce Poster Design

Social Media Changes the Market Based on Marketing

The primary goal of this essay is to examine the effects of social media's ongoing development on the market against the backdrop of the explosive growth of MLM-based information. It focuses on comparing the success of the early traditional e-commerce online shopping media "Amazon" and "Taobao" and the success of the modern e-commerce online shopping media "TikTok." By analyzing the operation mode of "Taobao" and "TikTok" and comparing the changes of user data and transaction amount. It can be concluded that users will constantly put forward new needs with the continuous update of technology, and social media will constantly solve the needs of customers to update. This update will continue to maintain and enhance the convenience offered by social media online shopping, and continue to attract new users. From the perspective of marketing, social media constantly solves the needs of consumers and provides interactivity, which makes people more willing to purchase and evaluate products and feedback merchants through social media. For merchants, studying such topics can quickly find and use social media more in line with consumer needs to "interact" and increase their sales channels and quantity.

LGM-GNN: A Local and Global Aware Memory-Based Graph Neural Network for Fraud Detection

Graphs have been widely adopted to accomplish fraud detection tasks because of their inherently favorable structure to capture the intricate features in many complicated scenarios, especially in some modern e-commerce situations that have various relation attributes like transactions. These works tend to utilize the direct aggregate information about neighbor nodes of the target node or the aggregation of the neighbor information after the conditional filter and mostly use local information but ignore global information. However, in some cases, local abnormal points are detected in the global view, so global information is very important for fraud detection. In this paper, we propose a local and global aware memory-based graph neural network for fraud detection (LGM-GNN). It first obtains the preliminary node embedding through relation-aware embedding and then interactively aggregates the local and global memory network to fuse and utilize the local and global information. Finally, the node embeddings of different levels are aggregated through the hierarchical information aggregator. Extensive experiments show our proposed LGM-GNN outperforms other SOAT methods on two real-world fraud detection datasets.

Mathematical model for portraits of members in large-scale department stores

Abstract The traditional retail industry be affected of the rapid development of modern e-commerce industry. To improve the shopping mall member portrait has become an effective way for operators to refine management and give full play to the value of members. We hope that the member system analysis based on data mining can provide reliable basis for establishing stable member relationship and planning promotional activities. In this paper, based on the real data provided by large department stores, adopting software such as MATLAB and SPSS, using probability statistics, data crawler and other related knowledge to description of a member of a large department store. Firstly, through the relationship models between members’ consumption characteristics model, it is concluded that the profit contribution of members to shopping malls is higher than that of non-members. Through the members’ purchasing power model, it is concluded that different strategies can be adopted for different levels of members. Through the members’ life cycle and state division model, we got the value of the member’s life cycle is about 799, and the state division threshold is 4.5594. Through the members’ preferences and commodity joint rate, we got that promotional activities play a leading role in the activation of members. Finally, according to the preferences of members, combined with business profits, we can choose the following three kinds of goods to promote: 30768d8b, d55deeb5, 6feea3f5.

Classification and Synthesis of the Main Dropshipping Disàdvantages to Eliminate them using Software Agents

Dropshipping is one of the most used models of modern e-commerce. However, some of its disadvantages can have a negative impact on business. The main disadvantages of dropshipping are identified and those that are expected to be eliminated at the pricing stage by implementing special software using software agents are distinguished. As a result of the work carried out, a set of the most significant disadvantages has synthesized based on the most important criteria for buyers and a hypothesis was put forward regarding the minimization of their negative impact. The resulting software may be adapted for use by dropshipping retail companies.

A Systematic Requirement Analysis for Dynamic Pricing in Retail E-Commerce

Abstract: Retail e-commerce has been exploding recently, with billions of people using the internet to buy goods and services. Due to the vast number of vendors selling similar products to consumers and the high degree of price transparency enjoyed by purchasers, the e-commerce sector is fiercely competitive. Vendors frequently use dynamic pricing, also known as discount pricing, to ensure they generate a healthy profit. In this paper, we present a systematic analysis of the requirements for a modern e-commerce dynamic pricing system. We cover the business, stakeholder, functional, and non-functional requirements of ecommerce dynamic pricing. We additionally offer a generic architecture blueprint based on what we have learned about the requirements for dynamic pricing