User Purchase Research Articles

Advancing e-commerce user purchase prediction: Integration of time-series attention with event-based timestamp encoding and Graph Neural Network-Enhanced user profiling.

In recent years, the global e-commerce landscape has witnessed rapid growth, with sales reaching a new peak in the past year and expected to rise further in the coming years. Amid this e-commerce boom, accurately predicting user purchase behavior has become crucial for commercial success. We introduce a novel framework integrating three innovative approaches to enhance the prediction model's effectiveness. First, we integrate an event-based timestamp encoding within a time-series attention model, effectively capturing the dynamic and temporal aspects of user behavior. This aspect is often neglected in traditional user purchase prediction methods, leading to suboptimal accuracy. Second, we incorporate Graph Neural Networks (GNNs) to analyze user behavior. By modeling users and their actions as nodes and edges within a graph structure, we capture complex relationships and patterns in user behavior more effectively than current models, offering a nuanced and comprehensive analysis. Lastly, our framework transcends traditional learning strategies by implementing advanced meta-learning techniques. This enables the model to autonomously adjust learning parameters, including the learning rate, in response to new and evolving data environments, thereby significantly enhancing its adaptability and learning efficiency. Through extensive experiments on diverse real-world e-commerce datasets, our model demonstrates superior performance, particularly in accuracy and adaptability in large-scale data scenarios. This study not only overcomes the existing challenges in analyzing e-commerce user behavior but also sets a foundation for future exploration in this dynamic field. We believe our contributions provide significant insights and tools for e-commerce platforms to better understand and cater to their users, ultimately driving sales and improving user experiences.

How country of origin, perceived quality, and trust influence intention to purchase sars covid medications

To maintain business survival and continuous research and development in the medical product industry, investigating the factors that influence the public's intention to buy Sars Covid medications is a primary mission for all the related medical institutions. This research aimed to examine how product attributes (country of origin and perceived quality) influence user attitude (consumer trust) and user decision-making (the intention to buy medications). Researchers collected data from 800 Thai people who were previously infected with COVID-19 using a convenience and snowball sampling method. Data were analyzed using a path analysis technique. Results indicate that consumer trust was influenced by country of origin and perceived quality. Furthermore, the intention to buy Sars Covid medications was influenced by trust and perceived quality, but not country of origin. Finally, consumer trust mediated an association between country of origin and intention to buy the medications. These results provide supportive evidence to the proposed theoretical model which underlines the relationships between product attributes, user attitudes, and user purchase decisions on Sar Covid medications. Particularly, this research contributes to the understanding of how country of origin and perceived medication quality influence patient trust which paves the way for their decision to purchase the medications for their future consumption. Thus, recommendations have been provided to all related medical institutions to consider labeling the country of origin on the medication packages, promoting medication quality to the patients, and enhancing patient trust. Therefore, these can positively lead to high purchase decisions among the patients.

From data to design: AI practice in design decisions

Abstract Facing the increasingly fierce market competition, enterprises need to make correct marketing decisions. Based on the decision support system, cloud server, and SOA framework, the article establishes an enterprise intelligent marketing decision-making system by combining the TCP/IP communication protocol and designing a data warehouse to store the marketing decision-making data. The Apriori algorithm in association rules is used to generate marketing rules to assist marketing decision-making, the marketing data is classified using the random forest algorithm, and the sparrow search algorithm optimizes the parameters of the random forest model. In practice, simulation experiments were designed to analyze the performance of the random forest model and the marketing decision-making system, and they were applied to the marketing decision-making example of the e-commerce platform. It was found that the AUC value obtained when the number of binary trees of the random forest model was 75 was 0.836, and the number of conflicts per second of the system was only 0.41 when the number of concurrent users was 5*104. The use of association rules resulted in eight marketing decisions, with the highest probability of user purchase prediction reaching 98.54%. Based on the intelligent marketing decision system, it can help decision-makers better analyze market changes and provide decision support for enterprises to develop scientific and reasonable marketing strategies.

User Purchase Intention Prediction Based on Improved Deep Forest

User Purchase Intention Prediction Based on Improved Deep Forest

Bi-preference Learning Heterogeneous Hypergraph Networks for Session-based Recommendation

Session-based recommendation intends to predict next purchased items based on anonymous behavior sequences. Numerous economic studies have revealed that item price is a key factor influencing user purchase decisions. Unfortunately, existing methods for session-based recommendation only aim at capturing user interest preference, while ignoring user price preference. Actually, there are primarily two challenges preventing us from accessing price preference. First, the price preference is highly associated to various item features (i.e., category and brand), which asks us to mine price preference from heterogeneous information. Second, price preference and interest preference are interdependent and collectively determine user choice, necessitating that we jointly consider both price and interest preference for intent modeling. To handle above challenges, we propose a novel approach Bi-Preference Learning Heterogeneous Hypergraph Networks (BiPNet) for session-based recommendation. Specifically, the customized heterogeneous hypergraph networks with a triple-level convolution are devised to capture user price and interest preference from heterogeneous features of items. Besides, we develop a Bi-Preference Learning schema to explore mutual relations between price and interest preference and collectively learn these two preferences under the multi-task learning architecture. Extensive experiments on multiple public datasets confirm the superiority of BiPNet over competitive baselines. Additional research also supports the notion that the price is crucial for the task.

Factors influencing TikTok-based user purchase intention: comparison between potential customers and repeat customers

PurposeThe purpose of this paper is to examine how different types of user experience in TikTok impact purchase intention via commitment to the influencer and commitment to the platform, with customer type included to determine moderating effects. Three types of user experience are considered: information experience, entertainment experience and parasocial-relationship-based experience.Design/methodology/approachThis study collected 458 valid questionnaires from TikTok users, employing the structural equation modeling approach to examine the proposed research model.FindingsInformation experience, entertainment experience and parasocial-relationship-based experience are found to critically stimulate user commitment to the influencer and commitment to the platform, in turn driving TikTok-based purchase intention. Tests incorporating customer type reveal that commitment to the influencer more strongly influences the purchase intention of repeat customers, with commitment to the platform more likely to stimulate purchase intention among potential customers.Research limitations/implicationsOn a theoretical level, the paper is among the first to examine TikTok-based user purchase intention with customer type as a moderator. On a practical level, the results can guide marketers to effectively promote products using TikTok and inspire TikTok managers to develop customized strategies to stimulate initial and repeat sales.Originality/valueTikTok is moving to the stage of commercialization and monetization by introducing e-commerce features. Although this move should cultivate particularly fertile ground for companies to sell products, TikTok user purchase behavior has yet to receive sufficient research attention, with little currently known about their purchase motivations. The current study uncovers the significant antecedents of users' purchase intention through TikTok, and further reveals the motivational differences among potential and repeat customers.

The future of TV-shopping: predicting user purchase intention through an extended technology acceptance model

The shoppable TV, which allows the purchase of products appearing in TV programmes directly, is a digital trend that is not implemented in most markets, but companies such as Amazon and NBC Universal have proposed the first sales systems. The aim of this research is to forecast the adoption intention of this technology by applying the Technology Acceptance Model. Structural equation modelling (PLS-SEM) has been applied to a sample of 283 participants. The results indicate that shopping enjoyment is particularly important in generating attitudes toward this type of consumption, and this increases the intention to use Shoppable TV.

Informational cascade, regulatory focus and purchase intention in online flash shopping

Online flash shopping has continued to gained popularity since its emergence. From the perspective of informational cascade, our study explores the psychological processes of consumer purchase decision-making in online flash sales. We investigate how external environment influences user purchase intention, as well as the psychological variables and cognitive aspects involved. Our analysis demonstrates that consumers’ propensity to imitate others and their positive perceptions of value markedly enhance their purchase intention, and that preorder size and consistency of product reviews significantly strengthen the psychology of imitation. Moreover, consumers’ regulatory focus moderates the effects of imitation, weakening self-information, and perceived value on purchase intention. Introducing the informational cascade perspective into online flash sales research, our study provides new insights into how information elements and perceived value influence consumers' impulse purchase intention. Using these insights, e-commerce retailers can develop strategies that foster a sense of urgency and excitement among consumers in online flash shopping. By ensuring consistency in customer reviews, and tactically highlighting essential product details such as pre-sale quantities, retailers can enhanced the perceived value of their products. Furthermore, meticulous management of sale duration, product assortment, and information visibility can strengthen purchase intention during flash sales. Our study enriches the understanding of consumer decision-making under the influences of herding and informational cascades.

Modeling User Demand Evolution for Next-Basket Prediction

Users' purchase behaviors are complex and dynamic, which are usually driven by various personal demands evolving with time. According to psychology and economic theories, user demands can be satisfied with a sequence of purchase behaviors, resulting in a basket of items. However, most of the existing works simply predict the next basket from a shallow perspective of (purchase) sequence data modeling without deep insight into the underlying factors which drive user purchase behaviors. In fact, filling a basket with multiple items is a process to incrementally satisfy a user's demand. Therefore, the key challenges to predict a user's next basket lie in (1) how to track the changes of the user's demand, and (2) how to satisfy her demand at a given moment. To this end, we propose an Evolving DEmand SAtisfaction (EvoDESA) model to model a user's demand evolution for next-basket prediction. In EvoDESA, a demand evolution module learns the dynamics of user demand over a sequence of basket-purchase behaviors. Then, a next-basket planning module effectively packs an optimal combination of items to best satisfy the user's current demand. Extensive experiments on three real-world transaction datasets demonstrate the considerable superiority of EvoDESA over the state-of-the-art approaches.

The Impact of Beauty We Media Bloggers on Users Purchase Intention

With the improvement of peoples material living standards and the soaring happiness index, more and more people have begun to pay attention to their appearance, so the demand for beauty products is increasing, promoting the growth of the beauty market industry. The popularity of TikTok and other social platforms led to the endless emergence of beauty we-media blogger. They have gradually become key opinion leaders in the beauty industry, and users also need the guidance of beauty we-media bloggers when buying cosmetics. This study takes TikTok platform as an example to explore the impact of beauty we-media bloggers on users purchase intentions. This paper analyzes data through systematic sampling, a questionnaire survey, and SPSS. Finally, the research proves that the influence of beauty makeup we-media bloggers on users purchase intention has three aspects: positive, negative, and irrelevant.

A Survey of Sequential Pattern Based E-Commerce Recommendation Systems

E-commerce recommendation systems usually deal with massive customer sequential databases, such as historical purchase or click stream sequences. Recommendation systems’ accuracy can be improved if complex sequential patterns of user purchase behavior are learned by integrating sequential patterns of customer clicks and/or purchases into the user–item rating matrix input of collaborative filtering. This review focuses on algorithms of existing E-commerce recommendation systems that are sequential pattern-based. It provides a comprehensive and comparative performance analysis of these systems, exposing their methodologies, achievements, limitations, and potential for solving more important problems in this domain. The review shows that integrating sequential pattern mining of historical purchase and/or click sequences into a user–item matrix for collaborative filtering can (i) improve recommendation accuracy, (ii) reduce user–item rating data sparsity, (iii) increase the novelty rate of recommendations, and (iv) improve the scalability of recommendation systems.

A study of the purchase intention of insect protein food as alternative foods for fitness proteins

The purpose of this study is to investigate the influencing factors for fitness enthusiasts' willingness to purchase insect protein foods as fitness protein replacements. Using structural equation modeling, a model was developed to understand the factors influencing the purchase intention of insect alternative foods. We conducted an online survey of 968 fitness enthusiasts in China. In accordance with the data processing results, perceived value appears to be one of the most significant factors that contribute to consumers' purchase intention, attitude, and satisfaction with their purchase decisions. Furthermore, satisfaction has the potential to improve user attitudes and increase user purchase intentions. As a whole, this study extends research on insect protein alternatives as a potential alternative product for bodybuilding supplements. Moreover, make some recommendations to producers, designers, and promoters.

A Study on User Behavior of E-commerce Platforms based on Data Analysis

With the popularity of the Internet and the rapid development of mobile technology, e-commerce platforms have become one of the main channels for people's shopping and transactions. On e-commerce platforms, users' behavioral data are widely recorded and stored, which provides a rich data resource for studying user behavior. Studying data analysis of user behavior on e-commerce platforms helps to understand users' behavior patterns and provides a scientific basis for e-commerce platforms to optimize marketing strategies, improve user experience and realize personalized recommendations. The article elaborates on the data collection and processing work from three aspects: data source selection and acquisition, pre-processing and cleaning, data feature extraction and variable selection, and studies the user behavior of e-commerce platform from three perspectives: user purchasing behavior, user browsing behavior, and user commenting behavior, to promote the development and enhance the competitiveness of e-commerce platform.

The Impact of Consumer Purchase Behavior towards User Purchase at E-commerce (Tokopedia)

With the rapid growth of e-commerce, businesses face the challenge of optimizing their strategies to attract and retain customers, while avoiding the common pitfall of burning money due to inefficient practices. Therefore, the treatment for digital customers is different of offline customers. This thesis explores the 7 main factors why users are convenient in shopping via Tokopedia. Through a comprehensive review of literature, the thesis provides insights into the concept of consumers' reasons, needs and why it’s convenient to purchase via Tokopedia. The thesis then tries to give another insight into delivering the best services to its consumers by not only focusing on promotion but from another variable. In particular, the thesis focuses on the impact of trustworthiness, recommendation, promotion, brand ambassador, brand reputation, advertising, and delivery toward consumer purchase using quantitative methods. Quantitative data is obtained through a questionnaire survey with 350 respondents across Jakarta. The thesis will deliver new insights for Tokopedia for the further strategy to not only focus on promotion. The findings of the thesis demonstrate that Tokopedia strategy can focus on developing a more consumer-centric approach bigger than promotion.

Pricing method of electric-thermal heterogeneous shared energy storage service

Energy storage system (ESS) has been considered as a pivotal technology enjoying a wide range of applications in different levels of power systems. However, the investment of ESS is still relatively high. Thus, shared energy storage (SES) is consequently recognized as a promising business model. Considering the dynamic virtual energy storage characteristics of heat network, this paper proposes a power-thermal heterogeneous SES model to meet the practical need of participants. Firstly, a quasi-dynamic model of heat energy transport is conducted to analyze the virtual energy storage potential of heat network. Then, the power-thermal heterogeneous SES model is developed to describe the formation mechanism of ESS supply and demand with heat network as the schedulable energy storage resource. Furthermore, a pricing method of electric-thermal heterogeneous SES is proposed. The upper-level problem of it targets at maximizing the benefits of the SES operator, while the lower-level problem aims to minimize the costs of users. Simultaneously, the service price and user purchase capacity can be obtained as optimization variables. Finally, case studies are adapted to verify the rationality and validity of the proposed model.

An Exploration of Motivations for Users Purchase Intention in Live-Streaming E-Commerce from a Perspective of Social Impact Theory

Live-streaming (LS) e-commerce has become popular since it appeared in China in 2019. In light of this, this research explored the motivations for peoples purchase intention in LS under the theoretical framework of the Social Impact Theory (SIT). 160 questionnaires were collected and analyzed. Additionally, relevant analysis on the platform Douyin was conducted. Results showed that streamers, other customers, and the LS platform contribute to affecting peoples purchase intention. Specifically speaking, the strength of streamers (how professional and popular they are) influences peoples trust; the number of other customers and their comments mediated peoples purchase intention; the immediacy of Douyin (how the platform makes the communication and purchase easier) also has an impact on the purchase intention

A User Purchase Behavior Prediction Method Based on XGBoost

With the increasing use of electronic commerce, online purchasing users have been rapidly rising. Predicting user behavior has therefore become a vital issue based on the collected data. However, traditional machine learning algorithms for prediction require significant computing time and often produce unsatisfactory results. In this paper, a prediction model based on XGBoost is proposed to predict user purchase behavior. Firstly, a user value model (LDTD) utilizing multi-feature fusion is proposed to differentiate between user types based on the available user account data. The multi-feature behavior fusion is carried out to generate the user tag feature according to user behavior patterns. Next, the XGBoost feature importance model is employed to analyze multi-dimensional features and identify the model with the most significant weight value as the key feature for constructing the model. This feature, together with other user features, is then used for prediction via the XGBoost model. Compared to existing machine learning models such as K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Random Forest (RF), and Back Propagation Neural Network (BPNN), the eXtreme Gradient Boosting (XGBoost) model outperforms with an accuracy of 0.9761, an F1 score of 0.9763, and a ROC value of 0.9768. Thus, the XGBoost model demonstrates superior stability and algorithm efficiency, making it an ideal choice for predicting user purchase behavior with high levels of accuracy.

Building a 4E interview-grounded theory model: A case study of demand factors for customized furniture.

With the lifestyle change, users' demand for furniture has shown a trend for personalization and diversification. The customized furniture market is growing rapidly and gradually becoming an indispensable choice for lifestyle items. The present qualitative study sought to identify the influencing factors and relationships of user demand for customized furniture. This study constructed a 4E semi-structured interview guide, which means that interviews were conducted from 4 dimensions: essential information, information extraction, user experience, and product expectation. The interview results were coded and analyzed in combination with grounded theory. Based on the identified 38 concepts and 10 categories, we obtain 4 main categories: fundamental condition, operation behaviour, sensory value and emotional value. For the factors that affect the demand of customized furniture users, customized furniture enterprises can start from 2 levels of publicity and product design to meet user demand and improve the user purchase probability.

Optimal Planning of Hybrid Electricity–Hydrogen Energy Storage System Considering Demand Response

In recent years, the stability of the distribution network has declined due to the large proportion of the uses of distributed generation (DG) with the continuous development of renewable energy power generation technology. Meanwhile, the traditional distribution network operation mode cannot keep the balance of the source and load. The operation mode of the active distribution network (ADN) can effectively reduce the decline in operation stability caused by the high proportion of DG. Therefore, this work proposes a bi-layer model for the planning of the electricity–hydrogen hybrid energy storage system (ESS) considering demand response (DR) for ADN. The upper layer takes the minimum load fluctuation, maximum user purchase cost satisfaction, and user comfort as the goals. Based on the electricity price elasticity matrix model, the optimal electricity price formulation strategy is obtained for the lower ESS planning. In the lower layer, the optimal ESS planning scheme is obtained with the minimum life cycle cost (LCC) of ESS, the voltage fluctuation of ADN, and the load fluctuation as the objectives. Finally, the MOPSO algorithm is used to test the model, and the correctness of the proposed method is verified by the extended IEEE-33 node test system. The simulation results show that the fluctuation in the voltage and load is reduced by 62.13% and 37.06%, respectively.

A household-scale life cycle assessment model for understanding the food-energy-water nexus

The household is an important locus of decision-making regarding food, energy, and water (FEW) consumption. Changes in household FEW consumption behaviors can lead to significant reductions in environmental impacts, but it can be difficult for consumers to compare the relative impacts of their consumption quantitatively, or to recognize the indirect impacts of their household consumption patterns. We describe two novel tools designed to address this problem: A hybrid life cycle assessment (LCA) framework to translate household consumption of food, energy, and water into key environmental impacts including greenhouse gas emissions, energy use, and water use; and a novel software application called HomeTracker that implements the framework by collecting household FEW data and providing environmental impact feedback to households. We explore the question: How can a life cycle assessment-based software application facilitate collection and translation of household consumption data to meaningful environmental impact metrics? A case study in Lake County, Illinois is presented to illustrate use of the HomeTracker application. Output data describing environmental impacts attributable to household FEW consumption in the study area are shown in order to illustrate key features and trends observed in the case study population. The framework and its associated output data can be used to support experimental research at the household scale, allowing for examination of what users purchase and consume over an extended period of time as well as increased understanding of household behavior trends and environmental impacts, and as future work.