User Purchase Research Articles

A fuzzy recommendation system for predicting the customers interests using sentiment analysis and ontology in e-commerce

In Electronic commerce, customer reviews play a significant role in purchase making decision. Most of the existing recommendation systems consider the customer reviews, user purchase history and product rating for predicting the recommended product. Since the users interest are varying over time, the existing recommendation systems lack in finding the current relevant items to the customers. To overcome this problem, this article proposes a new fuzzy logic-based product recommendation system which dynamically predicts the most relevant products to the customers in online shopping according to the users’ current interests. A novel algorithm has been proposed in this paper for computing the sentimental score of the product with associated end user target category. Finally, the proposed fuzzy rules and ontology-based recommendation system uses ontology alignment for making decisions that are more accurate and predict dynamically based on the search context. The experimental results of the proposed recommendation system show better performance than the existing product recommendation systems in terms of prediction accuracy of the relevant products for target users and in the time taken to provide such recommendations.

A/B testing as an effective instrument for adaptation of the user interface at the iterative model of developing applications for mobile devices

Changing the user interface always entails risks of decreasing application ergonomics and user churn. The purpose of this work is to find methods for changing the user interface without the need to use and increase the number of active users. Using Alpha/Beta testing and analysis of application metrics, it is possible to include design in each iteration and remotely manage the application configuration, which improves the user interface of the application. The way to integrate the UI modification and adaptation phase into an iterative software development model is proposed in this article. The successful user interface improvement experiments that have improved application metrics are described. In this work, the problem was highlighted, lack of information and control over user purchases, which negatively affected the number of purchases. A hypothesis is put forward that the user must have an effective visualization and control tool in the application. As a result of the experiment, the hypothesis was confirmed by an increase in the number of purchases and user activity. There was also a data security issue in the application, which put users at risk of data loss. An experiment was conducted to change the default value of user settings, which led to an increase of the positive metrics for using the data reservation functionality. The problem of polling users is also considered, which is an important component in the process of improving the ergonomics of an application. The method of remote user polling was used, which allowed to receive quick feedback from users and quickly respond to requests from users. The result of the work is the confirmation of the hypothesis of changes in the user interface in the cycles of the iterative development model, the positive dynamics of application metrics, as well as the satisfaction of users with the changes.

Influence of Brand Image, Price, and Product Quality on Shopee User Purchase Decision (Shopee User Study in Jabodetabek)

The purpose of this research are: to determine the positive and significant effect of brand image on purchasing decisions of Shopee users, to determine the positive and significant effect of price on purchasing decisions of Shopee users, to determine the positive and significant effect of product quality on purchasing decisions of Shopee users. The object of research is 100 Shopee users who have or have used the Shopee Application for shopping. The method used in this research is descriptive and quantitative methods. The data analysis technique in this study was used to analyze the data using the regression model parameters. Descriptive test results show; Significant influence of brand image on purchasing decisions of Shopee users, significant effect of price on purchasing decisions of Shopee users, significant influence of product quality on purchasing decisions of Shopee users.

Aided Product Modeling Design Based on Virtual Reality Technology

With the development of science and technology and the complexity of design objects, the requirements for product modeling design are getting higher and higher. How to design products in a targeted manner to meet the needs of consumers has become a key issue for enterprises. In order to improve the efficiency of product design, this article has carried out a research on the design of a new refrigerator product that a company plans to launch based on virtual reality technology. First, based on the conventional new product launch process, virtual reality technology is incorporated in the two links of market research and prototype testing. The virtual research client was tested after research and development. The average score was 9.32 for stability, 9 for ease of operation, and 8.86 for experience comfort. After optimizing the comfort level, a virtual survey was randomly launched on the home appliance shopping website. Analyze the general situation of 1258 users, the factors that affect refrigerator buying behavior, and the acceptable price of refrigerators. Among the 1,258 users who participated in the virtual survey, the male to female ratio was 0.9:1, and the age was mainly between 25 and 35. The number of people with high school education was the largest, accounting for 39.6%, 46% of users believe that price is the primary factor they consider when buying a refrigerator, and the generally accepted range is around 3,000 yuan. After obtaining sufficient demand and market information, develop new products, build a virtual design database, perform scene modeling, texture mapping, and achieve interactive effects. Of the 739 users who participated in the virtual experience, only 526 of them thought it was more comfortable during the experience. Therefore, it is necessary to improve the comfort during the experience. Only 59 people are very satisfied with the appearance of the refrigerator, and the appearance of the new refrigerator should be adjusted in time to meet market demand. The user's purchase intention ratio for the three refrigerators A, B and C is 1:3:1.6, and production can be arranged according to this ratio. The total cost of virtual design is 154,800 yuan less than traditional design, and the total time is 23 days less. This shows that product modeling design based on virtual reality technology can save costs and improve efficiency, and it is worth promoting.

Enhancing Bring Your Own Device Security in Education

The acceptance and use of personal devices at educational institutions is on the rise, resulting in the education sector’s adoption of Bring Your Own Device (BYOD). The institutions benefit from cost reduction in buying and managing IT devices as users purchase and bring their own devices. Users benefit by accessing learning materials and collaboration anytime, anywhere while on the move via institutional network. However, literature on BYOD indicates that various challenges are faced with usage of BYOD such as loss/stolen devices, malware, lack of policy, user negligence among others. This paper examined the literature in order to identify BYOD challenges, solutions, and guidelines that would inform secure BYOD usage in education.

Incorporating Price into Recommendation with Graph Convolutional Networks

In this work, we aim at developing an effective method to predict user purchase intention with the focus on the price factor in recommender systems. The main difficulties are two-fold: 1) the preference and sensitivity of a user on item price are unknown, which are only implicitly reflected in the items that the user has purchased, and 2) how the item price affects a users intention depends largely on the product category, that is, the perception and affordability of a user on item price could vary significantly across categories. Towards the first difficulty, we propose to model the transitive relationship between user-to-item and item-to-price, taking the inspiration from the recently developed Graph Convolution Networks (GCN). The key idea is to propagate the influence of price on users with items as the bridge, so as to make the learned user representations be price-aware. For the second difficulty, we further integrate item categories into the propagation progress and model the possible pairwise interactions for predicting user-item interactions. We conduct extensive experiments on two real-world datasets, demonstrating the effectiveness of our GCN-based method in learning the price-aware preference of users.

SE-stacking: Improving user purchase behavior prediction by information fusion and ensemble learning.

Online shopping behavior has the characteristics of rich granularity dimension and data sparsity and presents a challenging task in e-commerce. Previous studies on user behavior prediction did not seriously discuss feature selection and ensemble design, which are important to improving the performance of machine learning algorithms. In this paper, we proposed an SE-stacking model based on information fusion and ensemble learning for user purchase behavior prediction. After successfully using the ensemble feature selection method to screen purchase-related factors, we used the stacking algorithm for user purchase behavior prediction. In our efforts to avoid the deviation of the prediction results, we optimized the model by selecting ten different types of models as base learners and modifying the relevant parameters specifically for them. Experiments conducted on a publicly available dataset show that the SE-stacking model can achieve a 98.40% F1 score, approximately 0.09% higher than the optimal base models. The SE-stacking model not only has a good application in the prediction of user purchase behavior but also has practical value when combined with the actual e-commerce scene. At the same time, this model has important significance in academic research and the development of this field.

Monetizing Edge Service in Mobile Internet Ecosystem

In mobile Internet ecosystem, mobile users (MUs) purchase wireless data services from Internet service provider (ISP) to access to Internet and acquire the interested content services (e.g., online game) from Content Provider (CP). The popularity of intelligent functions (e.g., AI and 3D modeling) increases the computation-intensity of the content services, leading to a growing computation pressure for the MUs&#x2019; resource-limited devices. To this end, <i>edge computing service</i> is emerging as a promising approach to alleviate the MUs&#x2019; computation pressure while keeping their quality-of-service, via offloading some computation tasks of MUs to edge (computing) servers deployed at the local network edge. Thus, edge service provider (ESP), who deploys the edge servers and offers the edge computing service, becomes an upcoming new stakeholder in the ecosystem. In this work, we study the economic interactions of MUs, ISP, CP, and ESP in the new ecosystem with edge computing service, where MUs can acquire the computation-intensive content services (offered by CP) and offload some computation tasks, together with the necessary raw input data, to edge servers (deployed by ESP) through ISP. We first study the MU&#x0027;s Joint Content Acquisition and Task Offloading (J-CATO) problem, which aims to maximize his long-term payoff. We derive the <i>off-line</i> solution with crucial insights, based on which we design an <i>online</i> strategy with provable performance. Then, we study the ESP&#x0027;s edge service monetization problem. We propose a pricing policy that can achieve a <i>constant fraction</i> of the ex post optimal revenue with an extra <i>constant loss</i> for the ESP. Numerical results show that the edge computing service can stimulate the MUs&#x2019; content acquisition and improve the payoffs of MUs, ISP, and CP.

Loot boxes are gambling-like elements in video games with harmful potential: Results from a large-scale population survey

Loot boxes are a growing feature in the business models of video game production. They can be obtained through in-game purchases ranging from $0.5 to over $100 and contain chance-based virtual items that may offer an advantage in a video game making them gambling-like products.This study seeks to fill the current research gap with the analysis of a representative survey among 46,136 Internet users. Within this sample 1508 are Pay2Win users and more specifically, 586 of those Pay2Win users (38.9%) purchase loot boxes. Loot box users are an average age of 36.7 years and are predominantly male (55.3%). A high number (45.9%) meet the criteria for problem gambling measured by the PGSI. A significant negative age-effect exists, and a lower level of education has strong positive impacts on loot box participation. Loot box participation and purchasing frequency are positively associated with gambling problems and we argue that loot box purchasers are at risk of experiencing gambling problems.

S-commerce: Influence of Facebook likes on purchases and recommendations on a linked e-commerce site

Social networking site (SNS) driven e-commerce, the latest social commerce (s-commerce) phenomenon, gains prominence with the introduction of the call-to-action feature. The call-to-action feature on any sponsored post or advertisement on SNS redirects the user to a linked e-commerce website that offers the product. Information cues available on the SNS are expected to influence user decision making on the linked e-commerce site. Set in the context of Facebook driven e-commerce, this study explores how likes on Facebook influence user's purchase and recommendation decisions on a linked e-commerce website. Using controlled experiments we find that a higher volume of likes on Facebook leads to a higher likelihood of purchasing and recommending a product on the linked e-commerce site. This effect is found to be mediated by the user's initial product attitude formed on Facebook. An additional analysis examining the strength of the influence reveals that the mere presence of likes is not sufficient to impact the user's decision making. In fact, a low volume of likes elicits user behavior similar to absence of likes. The influence is effective only if the number of likes is substantially high. The findings of the study add to the s-commerce literature by establishing the inter-site influence of Facebook likes on user's purchase and post-purchase decisions and providing empirical evidence of the efficacy of SNS-driven e-commerce.

Design and Application of a Prediction Model for User Purchase Intention Based on Big Data Analysis

Design and Application of a Prediction Model for User Purchase Intention Based on Big Data Analysis

Success factors of brand community management in social media

The rise of social media has significantly altered both consumer behaviour and the possibilities of companies to engage in brand community management. Alongside the operation of conventional brand communities, companies nowadays have the chance to manage communities on social media platforms. While the social media literature has considerably increased in recent years, there is a lack of studies focusing on success factors in terms of a broad range of specific content categories that community managers offer to generate the desired user engagement. Based on the uses and gratifications theory, the study deduces a model that supposes relationships between different content categories and user engagement as well as its effect on users' brand trust and purchase intention. This model was largely supported by the structural equation model with data gathered from 247 users active in Facebook brand communities. The study finds entertaining, vivid, informative and credible content to have a positive influence on user engagement. In addition, the study confirms the influence of user engagement on brand trust and purchase intention, while brand trust mediates the relationship between user engagement and purchase intention.

Reviewer Credibility and Sentiment Analysis Based User Profile Modelling for Online Product Recommendation

Deciphering user purchase preferences, their likes and dislikes is a very tricky task even for humans, making its automation a very complex job. This research work augments heuristic-driven user interest profiling with reviewer credibility analysis and fine-grained feature sentiment analysis to devise a robust recommendation methodology. The proposed credibility, interest and sentiment enhanced recommendation (CISER) model has five modules namely candidate feature extraction, reviewer credibility analysis, user interest mining, candidate feature sentiment assignment and recommendation module. Review corpus is given as an input to the CISER model. Candidate feature extraction module uses context and sentiment confidence to extract features of importance. To make our model robust to fake and unworthy reviews and reviewers, reviewer credibility analysis proffers an approach of associating expertise, trust and influence scores with reviewers to weigh their opinion according to their credibility. The user interest mining module uses aesthetics of review writing as heuristics for interest-pattern mining. The candidate feature sentiment assignment module scores candidate features present in review based on their fastText sentiment polarity. Finally, the recommendation module uses credibility weighted sentiment scoring of user preferred features for purchase recommendations. The proposed recommendation methodology harnesses not only numeric ratings, but also sentiment expressions associated with features, customer preference profile and reviewer credibility for quantitative analysis of various alternative products. The mean average precision (MAP@1) for CISER is 93% and MAP@3 is 49%, which is better than current state-of-the-art systems.

A Novel Many-Objective Recommendation Algorithm for Multistakeholders

Most traditional recommender systems focus specifically on increasing consumer satisfaction by providing a list of relevant content to consumers. However, the perspectives of other multisided marketplace stakeholders are also equally important, i.e., the exposure for suppliers or providers and profit for the platform. The suppliers want their products to be presented to users, and the objective of the platform is to maximize their profit. Nevertheless, because consumers' preferences and the objectives of providers as well as the platform may conflict with each other, it degrades the utility of the recommendation methods by only considering users' views. Therefore, in this work, we use a many-objective optimization method to maintain a tradeoff among five objectives for three stakeholders and obtain multiple Pareto front solutions in a single run. We first combine customer lifetime value and user purchase preference to create a new similarity model (Sim_RFMP) to increase the recommendation accuracy of the recommendation list. Furthermore, we propose a many-objective model (NBHXMAOEA) for multistakeholder recommendation. In NBHXMAOEA, we present a novel N-block heuristic crossover operator (NBHX) that recombines blocks of chromosomes based on heuristics. Through extensive experiments, the results demonstrate that our proposed NBHXMAOEA achieves superior performance in terms of average accuracy, diversity, novelty, provider coverage, and platform profit to its competing methods.

Technology acceptance theories and factors influencing artificial Intelligence-based intelligent products

The rapid growth of artificial intelligence (AI) technology has prompted the development of AI-based intelligent products. Accordingly, various technology acceptance theories have been used to explain acceptance of these products. This comparative study determines which models best explain consumer acceptance of AI-based intelligent products and which factors have the greatest impact in terms of purchase intention. We assessed the utility of the Technology Acceptance Model (TAM), the Theory of Planned Behavior (TPB), the Unified Theory of Acceptance and Use of Technology (UTAUT), and the Value-based Adoption Model (VAM) using data collected from a survey sample of 378 respondents, modeling user acceptance in terms of behavioral intention to use AI-based intelligent products. In addition, we employed decomposition analysis to compare each factor included in these models in terms of influence on purchase intention. We found that the VAM performed best in modeling user acceptance. Among the various factors, enjoyment was found to influence user purchase intention the most, followed by subjective norms. The findings of this study confirm that acceptance of highly innovative products with minimal practical value, such as AI-based intelligent products, is more influenced by interest in technology than in utilitarian aspects.

"I Think You'll Like It"

Understanding the roles of social factors in online purchase behavior has been a long standing research problem. The recently emerging social e-commerce platforms leverage the stimulated word-of-mouth effect to promote the sales of items, which offers a peek into the complex interplay between the social influence and online purchasing behavior. In this paper, we investigate this problem on a full-scale purchase behavior dataset from one of the leading social e-commerce platforms, Beidian. Specifically, we conduct a comparison study between the social e-commerce and conventional e-commerce that are both integrated in Beidian to examine how social factors affect user's purchase behavior. We reveal that social e-commerce leads to a 3.09~10.37 times higher purchase conversion rate compared with the conventional settings, which indicates users make purchase with significantly fewer item explorations. Then, we propose and validate four primary mechanisms that contribute to the efficient purchase conversion: better matching, social enrichment, social proof and price sensitivity. Moreover, we identify several behavioral indicators that are able to measure the effect of these mechanisms, based on which we design an accurate predictive model (AUC=0.7738) for user's purchase decision. These results combine to shed light on how to understand and model the purchase behavior in social e-commerce.

Self-gratification and self-discrepancy in purchase of digital items

PurposeWhile previous research underscored self-presentation desire as an important motivator of digital item purchase, user needs for digital items may become increasingly inner-focused with the maturation of virtual communities (VCs). The purpose of this paper is to posit that self-discrepancy and self-gratification are key to explaining user purchase of digital items.Design/methodology/approachA survey of 310 users of a social media-based VC well supports the hypotheses.FindingsThe tenet of this study is that individuals purchase digital items in VCs not only for self-presentation purpose per se, but more importantly for reasons of more inner-focused, such as due to their self-discrepancy that motivates them to purchase digital items to enhance self-esteem, and also for self-gratification. Furthermore, self-discrepancy arising from comparing ones’ current self against how they perceive others expect them to ideally be (i.e. self-other discrepancy) increases their self-presentation desire.Originality/valueOverall the findings enrich the current view that individuals purchase digital items mainly to present themselves to others (Kim et al., 2012), thus affording a more complete understanding of this behavior that has both important research and practical implications.

Dynamic Role-based User Service Authority Control and Management on Cloud Computing

The demands for computing resource allocation, user management, and various contents management are increasing with the proliferation of cloud computing. A cloud service system has to provide the system services that are combined or shared based on the web environment, unlike a single application in the past. It has also evolved to appropriately allocate and combine service resources according to the needs and needs of various users to provide a user-dependent web environment. There is an increasing need for software convergence services in the form of software. In response to these needs, a variety of customized services are provided to a user who promises an optional service environment. Those services can be used in combination according to a user's purpose and needs, instead of providing an environment in which a user purchases and uses software locally. In particular, because cloud computing provides the process that a user gain accessing authority to the system which has been granted a service access right for a certain period of time, and including a process of expire the corresponding right is completed, a various authority access control method is designed. In this paper, we define the roles of users who access cloud computing service, and manage user rights according to each role, provide and expire appropriate service resources according to user's privilege and session information. Moreover we analyzed the procedures for constructing an algorithm for service ripple effects according to the procedure of granting service resources to each user and accessing web services and constructing a new role.

Virtual and Augmented Reality as a digital strategy for the commercialization of Michoacan crafts. Case: Mara Ceramics

This work deals with the process of creating 3Dpieces of handicrafts Michoacanas to be shown through the use of Virtual Reality and Augmented as part of the solution to promote a strategy of marketing and promotion of the products of the craft workshop Cerámica Mara, SA de CV . These resources are innovative elements incorporated into an Electronic Commerce site, which allow the user to appreciate during their journey the handmade pieces exhibited in the virtual gallery, with the possibility of selecting the pieces, being able to configure the color and texture, and / or visualize them in their mobile device through the QR codes provided in the site catalog; all with the intention of serving as elements that potentiate the user's purchase intention. The design of the research was based on the qualitative model of case study, under the Scrum development methodology, being a collaborative work between the Academic Bodies of Multimedia and Electronic Commerce of the Technological University of Morelia and the Science, Technology and Management of the Organizations of the Technological Institute of Morelia. The scope obtained so far consists of a functional prototype of the Electronic Commerce Site, which incorporates a journey with 3D models of Virtual Reality and Augmented Reality via QR codes, with the possibility of purchase. It is expected that in later stages data will be obtained that allow studying how to modify the purchase intention, level of sales and market captured in commercialization of Michoacán ceramic crafts, through this proposa

Predictive Analysis of User Purchase Behavior based on Machine Learning

Predictive Analysis of User Purchase Behavior based on Machine Learning