E-commerce Research Articles

THE ROLE OF ARTIFICIAL INTELLIGENCE (AI) AND PRODUCT POPULARITY IN SHAPING CONSUMER BUYING BEHAVIOR ON INDONESIAN E-COMMERCE PLATFORMS

This study aims to bridge the gap in the literature by examining how artificial intelligence (AI) and product popularity play a role in shaping consumer purchasing behavior on Indonesian e-commerce platforms. The sample is users who make purchases of cosmetic products with AI features on Indonesian E-Commerce. Using multiple linear regression methods and SPSS 25 as a calculation tool. It was found that artificial intelligence and product popularity have a significant influence on consumer purchasing behavior in Indonesian E-Commerce.

Optimizing E-commerce Recommender Systems: A Comprehensive Review of Techniques and Future Directions

Abstract. This paper examines recommender systems in e-commerce by reviewing technologies and real-world applications and identifying the importance of big data analytics in recommender systems. In the study, three kinds of recommendation algorithms are discussed: collaborative filtering, content-based recommendation, and hybrid models. Collaborative filtering methods did well in the case of large-scale user data, but had cold-start and sparsity problems. Based on the content, recommended methods have strong personalized suggestion functions, but the information cocoon phenomenon is a risk, which decreases the contents diversity. Hybrid models are a combination approach between the two techniques, providing a flexible and robustness solution, but only a more complex computationally. This article also looks at the technology trends that have emerged lately, for example, the use of deep learning models, as well as the privacy-preserving techniques utilized in recommender systems. By analyzing and summarizing the existing research, this paper provides a reference basis for future optimization and application of recommender systems and points out potential research directions.

The role of online consumer reviews in shaping Chinese consumers' purchase intentions for energy-saving household appliances: a social communication theory perspective

With the primary sales channels for home appliances in China shifting from offline to online, e-commerce platforms hold significant potential to promote the purchase of energy-saving appliances. Therefore, this study investigates the factors influencing consumers' intentions to purchase energy-saving appliances in the context of online review interactions. Based on social communication theory, we identified four key elements in online review communication: information quality, information quantity, source credibility, and consumer attitudes toward online review. Additionally, we analyzed the mediating role of perceived information usefulness and the moderating role of consumer information processing capability. Data were gathered by using a structured questionnaire, and the respondents are comprised of consumers with experience purchasing energy-saving home appliances online., PLS-SEM was employed for the analysis of data. The findings suggest that the quality, quantity, and source credibility of online reviews, as well as consumers' attitudes towards online reviews, directly influence customers’ purchase intentions for energy-saving appliances. Moreover, a review of quantity and consumer attitudes impacts purchase intention through the perceived information usefulness. The moderating effect of consumers' information processing capability on the relationship between online reviews and perceived information usefulness is also confirmed. The results of the study explain the formation mechanism of consumers' willingness to buy energy-saving home appliances from the perspective of information dissemination, which offers valuable insights for e-commerce platforms and online marketers aiming to comprehend consumers' decision-making processes.

Satisfying Consumer Preferences: The Packaging Design of Guizhou Red Sour Soup

Red sour soup (RSS) is a traditional food with rich cultural connotations and nutritional value, unique to the Kaili region of Guizhou Province, China. However, the existing packaging design lacks cultural characteristics and visual appeal, which greatly limits its market potential. This study proposes a systematic research framework for RSS packaging design by integrating NLP, Kansei engineering, and semiotics. First, we mined consumers’ dual requirements by analyzing online reviews from e-commerce and tourism platforms using NLP and LDA. Second, we used Kansei engineering to construct a mapping model between consumers’ requirements and design elements. Notably, in the semantic space, we innovatively introduced the concept of a semantic network, considering the relationships between Kansei words for the first time. Finally, we proposed integrating the four dimensions of semiotics into the four stages of design, guiding the application of batik culture in packaging design. Based on this framework, we created a set of RSS packaging designs that integrate modern design concepts and traditional Miao cultural elements. The new design showed significant attractiveness in testing, with 100% of subjects preferring it, fully demonstrating the effectiveness and consumer acceptance of our approach. This study provides new methods and ideas for packaging in the food industry, which has positive significance for the modernized marketing of traditional foods.

Research on the Information Interaction Design of Special Agricultural Products Apps from the Perspective of Rural Revitalization

Driven by the Rural Revitalization Strategy, the promotion and sale of special agricultural products have become an important means to enhance the rural economy. With the development of mobile internet, e-commerce platforms based on mobile apps provide new channels for the sale of these products. However, market research reveals that many platforms for special agricultural products face issues related to poor user experience and low user engagement in their information interaction design. Therefore, this paper, from the perspective of information interaction design, identifies pain points in existing app designs through literature review and case analysis, and explores methods to optimize the user experience of agricultural product apps. We gathered user needs and feedback, built user personas, designed interactive prototypes, and validated their effectiveness in terms of user experience, operational convenience, and information transmission efficiency through usability testing. The research results show that the prototype significantly improved information hierarchy, simplified interaction processes, and better met users' personalized needs. The information interaction design of special agricultural product apps should not only focus on functional requirements but also emphasize the emotional experience and cultural identity of users. Visual design should incorporate elements of rural cultural characteristics to enhance users' sense of identification and engagement. Future designs should emphasize the integration of interaction design with rural culture, further improving user experience through innovative information presentation methods and personalized services, thereby supporting the Rural Revitalization Strategy and the sustainable development of agricultural e-commerce.

Transforming Rural Entrepreneurship Through Digital Innovation: A Review on Opportunities, Barriers and Challenges

This paper delves into the transformative impact of digital innovation on rural entrepreneurship, highlighting the opportunities, barriers and challenges rural entrepreneurs face. Digital technologies, including e-commerce platforms, mobile applications, and social media, enable rural entrepreneurs to reach broader markets, enhance operational efficiencies, and develop innovative business models. Despite these benefits, the digital divide—characterised by inadequate technological infrastructure and low digital literacy—presents substantial barriers to these digital advancements. Further complicating the adoption of digital technologies are challenges such as a lack of technological expertise and financial constraints, which impede the full realisation of digital innovation in rural areas. This paper discusses various strategies to overcome the barriers to digital transformation in rural entrepreneurship. The key point among these strategies is the implementation of supportive policies encouraging digital adoption. Investment in digital infrastructure is crucial to bridge the technological gap and provide rural areas with the necessary tools to compete in the digital economy. Additionally, targeted educational programs are essential to improve digital literacy and provide rural entrepreneurs with the skills to effectively leverage digital technologies. The paper underscores the importance of a holistic approach, combining policy support, infrastructure development and education to empower rural entrepreneurs. By adopting these strategies, rural communities can achieve sustainable economic growth, enhance their competitiveness, and improve the quality of life for their residents. Ultimately, this paper aimed to provide a comprehensive understanding of the role of digital innovation in transforming rural entrepreneurship and offered practical solutions to foster inclusive and sustainable economic development.

Trends in Modern Typography Design: Visual Preferences on E-Commerce Platforms

In the digital era, typography design has become a fundamental element in shaping the visual identity and user experience of e-commerce platforms. Modern typography trends like minimalism, variable fonts, and responsive typography reflect a dynamic evolution aligned with user preferences and technological advancements. However, limited research addresses how typography influences users' visual preferences and engagement in the e-commerce context. This study aims to explore modern typography trends and their impact on user preferences while identifying elements that drive effective visual communication. To achieve these objectives, the research employs a mixed-method approach. A visual content analysis was conducted on typography used by leading e-commerce platforms, such as Amazon, Shopee, and Tokopedia, to identify prevailing design trends. A survey involving 150 active e-commerce users was conducted to understand their perceptions and preferences regarding typography design. Quantitative data from the survey were analyzed using statistical methods, while qualitative insights were interpreted to provide context. The results reveal that users prefer sans-serif fonts and minimalist designs due to their clarity, readability, and modern appeal. Variable fonts and dynamic typographic layouts were also noted for their ability to enhance engagement, though these trends appeal primarily to younger audiences. This study concludes that typography significantly influences user perception and interaction within e-commerce platforms. The findings contribute to the field of user experience design by offering actionable insights for designers and developers, aiming to create visually appealing and user-centered platforms.

Strategi Inovasi Marketing Lembaga Pendidikan Islam Menghadapi Revolusi Industri 5.0 dengan Menggunakan SWOT Analysis (Studi Kasus KB-TK-SD IT AL Mubarokah, Rancaekek, Bandung)

The research employs a qualitative method with a descriptive approach, analyzing data inductively without hypotheses. Data were obtained through in-depth observations of marketing strategies, and analysis was conducted to illustrate how these strategies can be improved. The findings suggest that to maintain and enhance quality, KB-TK-SD IT Al-Mubarokah needs to strengthen its marketing strategies and adapt to digital transformation and societal needs. KB-TK-SD IT Al-Mubarokah, a privately accredited primary school located in Bandung, West Java, uses SWOT analysis to evaluate its marketing strategies. The analysis reveals that the school’s key strengths lie in product quality and optimal digital marketing, while weaknesses include inconsistent digital services and conventional sales methods. Opportunities for growth involve leveraging digital technology and e-commerce platforms, while threats include intense competition and the need for effective communication. The proposed strategies involve leveraging strengths to exploit opportunities, addressing weaknesses through digitalization, and optimizing responses to competitive threats. By implementing these strategies, KB-TK-SD IT Al-Mubarokah aims to strengthen its competitive position and attract more students.

Analysis of the Influence of Perceived Enjoyment and Perceived Usefulness on Impulse Buying in Live Streaming on Online Marketplaces

Impulsive buying behavior in the digital age is rapidly evolving with the emergence of live streaming technology on e-commerce platforms. This technology enables direct real-time interaction between sellers and buyers, often triggering spontaneous purchases. Live streaming features offer an engaging shopping experience by allowing consumers to view product demonstrations and interact directly, supporting impulsive buying behavior. This study analyzes the roles of perceived enjoyment and perceived usefulness influence variables between visual appeal and social presence in influencing impulsive purchases during live streaming sessions on Shopee. Using a quantitative method, data was collected from 241 respondents through a questionnaire and analyzed using Structural Equation Modeling (SEM). The results indicate that live streaming strengthens social interaction and visual appeal, enhancing perceived enjoyment and perceived usefulness, which in turn increases the tendency for impulsive buying. This research provides insights for marketers to design effective e-commerce strategies to capitalize on the phenomenon of impulsive buying through interactive and visually appealing live streaming technology, optimizing user experience and sales conversions.

E-Commerce Platform Development for Small Businesses: A Framework for Success

Objectives: It is necessary to distinguish the concept of organizational performance from the broader concept of organizational effectiveness (Santos and Brito, 2012). The term "business or organizational performance" refers to both operational and financial outcomes in this study. Methods: However, as human resource management evolves toward e-HRM, HRM functions become less complex and easier to manage, while simultaneously improving overall employee and organizational performance. Findings: As a result of eHRM, human resource professionals are now more forward-thinking and only one click away from increasing their effectiveness. Conclusion: The purpose of this study is to discuss the purpose and methodology of the study, as well as the literature review and discussion of the findings and future directions.

Research on Product Classification and Demand Prediction Based on ALSTM-CNN

The rapid development of e-commerce platforms has prompted a large number of retailers to join and store goods through logistics warehouses provided by the platform, which are then centrally managed by the platform. In this context, the rise of artificial intelligence and machine learning technology has brought revolutionary impact to the e-commerce industry. Under this framework, accurate sales forecasting has become the core link. This article aims to integrate machine learning models and time series analysis, aiming to improve the accuracy of sales data prediction. This article is based on the K-Means algorithm for unsupervised multi-level clustering, determining the optimal K value through elbow rules and contour coefficients. After labeling the classification data with class labels, objectively evaluate the clustering effect by combining the Calinski Harabasz index and visualizing SKUs after each clustering. Finally, using evaluation metric 1-wmape, the performance of ARIMA-ANN, BiLSTM, GRU, CNN-LSTM, Stack LSTM, and three tree models in predicting SKU sales was compared. We compared the accuracy of 15 day recursive prediction and 15 day one-time output, and selected sliding window sizes of 3, 5, 7, and 14. After comparison, it was determined that the BiLSTM model performed best in predicting 15 day sales volume and a 3-day sliding time window under multiple sample categories; ARIMA-ANN performs the best in recursive prediction of 15 day sales volume in a few sample categories. By adjusting the ARIMA parameters through ACF and PACF, the maximum predictive performance is ensured.

Reputation vs. price: Sequential recommendations based on cue diagnosticity theory

Sequential recommendations have been widely used in e-commerce platforms to effectively capture consumers' dynamic preferences and provide them with preferred products. Traditional models usually use ratings and product attributes for sequential recommendations to satisfy consumers’ more personalized needs. Consumers also rely on reviews from other consumers to form a general impression of the product or retailer before making their purchase decisions. Such impressions can be treated as reputations of the product or retailer. Inspired by cue diagnosticity theory, we divide the attributes related to product purchase into low- and high-scope cues. High-scope cues, including reputations, are not easily changed because they are formed over a long period by numerous consumers, whereas low-scope cues, such as price, can be easily changed by retailers. We propose an innovative Sequential Recommendation model by Integrating Low-scope cues and High-scope cues (SRILH). We design a cue-extraction layer to extract high-scope cues from consumer online reviews and a hierarchical cue-aware attention layer to learn the joint effect of low- and high-scope cues. We evaluate the performance of the proposed model using three real-world datasets, and our experimental results validate its effectiveness and robustness. Our research contributes to sequential recommendations research by uncovering the joint effects of cues on consumer behavior and by providing valuable insights into the dynamics of cue preference formation in recommendation systems. We also extend the empirical literature on cue diagnosticity theory by drawing conclusions from the micro and individual perspectives to shed light on how different cues impact consumer choices. The interpretable visualization results provide managerial insights for retailers and manufacturers to improve their products.

An Accurate Construction Method of E-commerce User Profile Based on Artificial Intelligence Algorithm and Big Data Analysis

User’s basic attributes, behavior characteristics, value attributes, social attributes, interest attributes, psychological attributes, and other factors will lead to poor user experience, information overload, interference, and other negative effects. In order to develop more accurate marketing strategies, optimize user experience, and improve the conversion rate and user satisfaction of e-commerce platforms, an accurate construction method of e-commerce user profile based on artificial intelligence algorithm and big data analysis is proposed. Based on big data analysis technology, the basic attributes, behavior characteristics, value attributes, social attributes, interest attributes, and psychological attributes of e-commerce users are collected and integrated from multiple dimensions. The improved sequential pattern mining algorithm (PBWL) is applied to mine the frequent sequential pattern in the e-commerce user behavior, and to reveal the user’s behavior habit. The comprehensive attribute representation of e-commerce users is obtained by combining the LINE network model and the convolutional neural network. The firefly K-means clustering algorithm is used to cluster the e-commerce users, group the users based on the similarity of user attribute information, create different types of user clusters, and achieve the accurate construction of an e-commerce user profile. The experimental results show that this method can build an accurate e-commerce user profile and provide strong support for personalized recommendation and precision marketing of e-commerce platforms. This method can dig deeply into the behavior habits of e-commerce users and accurately reflect their interest preferences and consumption characteristics. This method can quickly and stably cluster e-commerce users, and the clustering effect of user profiles is optimal. This method can also divide the data into meaningful groups according to the user’s consumption behavior, and reveal the characteristics and values of different groups.

Challenges Facing Electronic Banking Supervision Comparative Legal Study

Objectives: The primary objective of this research is to examine the impact of the widespread adoption of electronic commerce, particularly in the banking sector, and to identify the advantages and challenges associated with this transition. As electronic banking continues to replace traditional banking methods, understanding the implications and potential issues becomes essential to support the growth and effectiveness of these systems. Methods: This study will analyze data on the adoption and growth of electronic banking, alongside identifying common issues that arise from its implementation. Through a comparative analysis of traditional and electronic banking, the study aims to highlight specific challenges that electronic banks face, especially in terms of regulatory supervision and customer security. Results: The research findings suggest that while electronic banking provides numerous benefits, including convenience and increased accessibility, it also introduces new challenges. These challenges often revolve around ensuring proper supervision and regulation to protect users and maintain trust in digital banking systems. Conclusion: In conclusion, the shift from traditional to electronic banking brings significant opportunities but also demands attention to emerging problems, particularly those concerning oversight. Addressing these issues through effective regulation and supervision will be crucial to ensure a secure and sustainable electronic banking future.

E-commerce among grain traders and its impact on marketing

The study investigated the determinants of adopting E-commerce among maize traders, focusing on the Savings Grains App. E-commerce implications on marketing effectiveness and the value co-creation opportunities were also analyzed. Primary data was sourced from 130 maize traders. Descriptive statistics, probit regression, and inverse probability weighted regression adjustment (IPWRA) were applied to analyze the data. Perceived usefulness, perceived cost, perceived ease of use, perceived innovativeness, perceived complexity, and household size were identified as factors that significantly influence traders’ adoption of E-commerce. These findings reinforce and expand existing theories on adoption intentions within agripreneurship. Moreover, traders using the e-commerce platform reported an increase of 4702 kg in sales volume and GH¢ 239.1 (US$ 26.8) in sales revenue compared to non-adopters. The study further highlighted value co-creation as a catalyst for enhanced sales volume, revenue, and user satisfaction, underscoring its potential as a sustainable strategy within e-commerce frameworks. The insights gained contribute to understanding the transformative role of sustainable technology in boosting growth and resilience in agricultural trade.

Hyper-Personalization with AI and Edge Computing: The Future of Customer Experience in E-commerce and Retail

Advancements in Artificial Intelligence (AI) and edge computing are reshaping what is possible in the world of hyper-personalization, currently powering customer experience in e-commerce and retail. In this study we explore when AI algorithms and edge computing frameworks enable real time, individualized customer interactions resulting in deeper engagement and higher loyalty. This study uses a quantitative research design to explore data driven personalization techniques with datasets from leading retail and ecommerce platforms. To evaluate the scalability and responsiveness of hyper-personalization technologies, a combination of machine learning models and terms edge computing infrastructures is methodologically analyzed. Through case studies of top tier e-commerce platforms, results show that integration of AI and edge computing can reduce latency in customer interactions by up to 70%, while upgrading conversion rates by roughly 30%. These findings emphasize the added value of creating real time customer experience driven sales and customer loyalty leveraging real time customer insights enabled by AI at the edge. This work presents a novel framework that enables scalable, secure hyper personalization in e-commerce to overcome existing limitations in data processing speed and privacy compliance. It offers actionable recommendations for retailers that look to adopt AI driven, edge enabled hyper personalization techniques for enhancing customer engagement and operational efficiency.

Entropy-Based Ensemble of Convolutional Neural Networks for Clothes Texture Pattern Recognition

Automatic clothes pattern recognition is important to assist visually impaired people and for real-world applications such as e-commerce or personal fashion recommendation systems, and it has attracted increased interest from researchers. It is a challenging texture classification problem in that even images of the same texture class expose a high degree of intraclass variations. Moreover, images of clothes patterns may be taken in an unconstrained illumination environment. Machine learning methods proposed for this problem mostly rely on handcrafted features and traditional classification methods. The research works that utilize the deep learning approach result in poor recognition performance. We propose a deep learning method based on an ensemble of convolutional neural networks where feature engineering is not required while extracting robust local and global features of clothes patterns. The ensemble classifier employs a pre-trained ResNet50 with a non-local (NL) block, a squeeze-and-excitation (SE) block, and a coordinate attention (CA) block as base learners. To fuse the individual decisions of the base learners, we introduce a simple and effective fusing technique based on entropy voting, which incorporates the uncertainties in the decisions of base learners. We validate the proposed method on benchmark datasets for clothes patterns that have six categories: solid, striped, checkered, dotted, zigzag, and floral. The proposed method achieves promising results for limited computational and data resources. In terms of accuracy, it achieves 98.18% for the GoogleClothingDataset and 96.03% for the CCYN dataset.

Comprehensive Survey on E-Commerce and Blockchain

The rapid growth of e-commerce has led to an increasing demand for secure, transparent, and efficient transactions. This project presents an e-commerce platform built on blockchain technology, aiming to address the challenges of traditional online marketplaces, such as fraud, data breaches, and intermediaries' fees. By leveraging blockchain's inherent characteristics— immutability, transparency, and security—our platform facilitates seamless transactions between buyers and sellers, reducing reliance on intermediaries and lowering operational costs.  Key Features of the Platform Include:  Payment Processing: Integration of cryptocurrencies enables fast and secure payments, facilitating cross- border transactions without the need for banks or other intermediaries.  Product Authenticity: Tokenization of physical products as digital assets ensures authenticity and traceability, particularly valuable in industries like fashion, luxury goods, and art.  Customer Data Privacy: Customers retain control over their personal information, deciding what data to share with merchants, enhancing privacy, and ensuring compliance with global data regulations.  Loyalty Programs and Rewards: Digital tokens and reward points can be issued that are transparent, transferable, and usable across various platforms, making loyalty programs more versatile and valuable.  Decentralized Reviews and Ratings: The integrity of product reviews is ensured by using blockchain to prevent manipulation, making customer feedback more trustworthy. To demonstrate the feasibility of the platform, we implement features such as user registration, product listing, secure payment processing using cryptocurrency, and an efficient dispute resolution mechanism. Through a user-friendly interface and robust backend architecture, this blockchain-based e-commerce solution aims to redefine the online shopping experience, providing enhanced security, lower costs, and greater trust for all participants in the ecosystem.

Enhancing User Experience through AI-Driven Personalization in User Interfaces

Artificial intelligence (AI) has revolutionized user interface (UI) design by introducing personalization techniques that cater to individual user preferences, behaviors, and contexts. This research explores the integration of AI-driven personalization in user interfaces to enhance user experience (UX), focusing on adaptive design, predictive analytics, and real-time customization. By leveraging machine learning algorithms and behavioral data, AI enables interfaces to evolve dynamically, aligning with the unique needs of each user. This study investigates the role of personalization in improving engagement, satisfaction, and efficiency across various applications, such as e-commerce platforms, healthcare systems, and educational tools. Additionally, it examines the challenges of implementing personalized interfaces, including privacy concerns, data ethics, and algorithmic bias. By addressing these challenges, the research aims to develop best practices for ethical AI integration in user-centered design. The findings contribute to the growing body of knowledge on AI’s transformative potential in creating intuitive, efficient, and user-friendly interfaces, ultimately redefining the standards for digital interaction.

Corpus-Based Word Usage in Social Media Marketing and E-Commerce: Developing Word Lists and a Proposedly Designed Teaching

This study aims to explore the frequently used words in 41 research articles and 12 related books from 2000 to 2024 in the context of social media marketing and e-commerce, focusing on general words, academic words, and specialized words. The investigation also leads to an in-depth examination of collocation words using Antconc software's N-gram feature. Then, the collected words were grouped for designing the proposed design for teaching English for students majoring in social media marketing and e-commerce. In addition, grammatical usage was analyzed to provide a comprehensive picture of frequently used grammatical structure for supporting the effectiveness of a proposedly designed teaching. The investigation focuses on a large dataset of 1,675,230 tokens and 39,931 types, with keyword tokens numbering 818,111 and keyword types numbering 1,791. The vocabulary distribution contains 21.36% K1 words, 7.89% K2 words, and 18.27% from the Academic Word List (AWL), with off-word lists accounting for 52.48%. Key findings emphasize the importance of terms such as social media marketing, e-commerce, and marketing strategies, indicating the key role of social platforms and digital media in contemporary advertising practices. Furthermore, the examination of n-grams and academic vocabulary emphasizes the value of data-driven strategies, technological innovation, and consumer behavior observations. Specialized vocabulary highlights developing trends and innovations in this industry. The findings also enhance the understanding of the growing language of social media and e-commerce marketing, providing insights into current industry trends and terminology. This analysis provides the foundation for developing targeted educational instruments and methods to improve communication and effectiveness in digital marketing environments.