Development and performance evaluation of neural network classifiers for Indian internet shoppers

The rapid growth of usage of internet has paved the way towards the use of online shopping. Consumers’ behavior is one of the significant aspects that is considered by the service providers for the improvement of various services. Consumers are generally satisfied if their needs are fulfilled. In this paper an in depth investigation is made on the behavior of Indian consumers towards online shopping. Factor analysis is carried out to extract significant factors that affect online shopping of Indian consumers and these consumers are clustered based on their behavior, towards online shopping using hierarchical clustering. Employing the results of clustering in training of multilayer perceptron (MLP), functional link artificial neural network (FLANN) and radial basis function (RBF) networks efficient classifier models are developed. The performance of these classifiers are evaluated and compared with those obtained by conventional statistical based discriminant analysis. The simulation study demonstrates that the RBF network provides best classification performance of internet shoppers compared to those given by the FLANN, MLP and discriminant analysis based methods. The simulation study on the impact of different combination of inputs demonstrates that demographic input has least effect on classification performance. On the other hand the combination of psychological and cultural inputs play the most significant role in classification followed by psychological and then cultural inputs alone.     

The moderating effects of psychological reactance and product involvement on online shopping recommendation mechanisms based on a causal map

The use of the Internet in the daily activities of individuals and firms has become entrenched, and online shopping has become commonplace. However, debates about how online shopping recommendation mechanisms (OREMs) should be designed have not been completely resolved. The challenge with traditional online shopping recommendation mechanisms (TR-OREMs) is that they focus too much on quantitative factors. Thus, they ignore causal interrelationships with qualitative factors that are believed to significantly impact quantitative factors. Considering only quantitative factors and ignoring qualitative ones likely distorts the final recommendation results. Another problem with TR-OREMs is that they ignore the perceived psychological reactance of consumers against the recommended products. Such consumer reactance may be reduced when the causal interrelationships among all the quantitative and qualitative factors are analyzed and incorporated properly into the OREM. To overcome these problems, we propose a causal map – online shopping recommendation mechanisms (CM-OREMs) based on a causal map. We analyzed possible causal relationships among quantitative and qualitative factors and incorporated them in the recommendation process to reduce consumer reactance against the recommendation results. Furthermore, an elaboration likelihood model (ELM) was used to build hypotheses about how the online shopping behavior of consumers is affected by OREMs based on the proposed causal map. Specifically, the performance of the proposed OREM was empirically analyzed by gathering experiment data from qualified respondents who were asked to refer to the proposed OREM before making purchasing decisions via mobile phones. Statistical results showed that the proposed OREMs could enhance consumer decision satisfaction, decision confidence, and attitude toward the recommended products. It could also positively affect consumer purchasing intentions. The OREM had a greater effect on the high-reactance group of participants than on the low-reactance group as well as on a high-involvement product versus a low-involvement product.     

A feedback control approach to maintain consumer information load in online shopping environments

The heterogeneity of e-commerce users requires online shopping environments to advance from a simple framework to one that is adaptive. This need results from the negative consequences of user frustration due to information load. We used a feedback control theory based approach to address the online consumer information overload issue in an adaptive manner. To demonstrate the efficacy of this feedback control approach, a design science method evaluated the feedback controller. The main effect was that the dynamic adaptivity did not have to rely on summarizing data for inference to the individual. The proposed feedback control design is therefore a robust and viable option for organizations to incorporate into their online shopping environments to accommodate user variation of information load for e-commerce adaptivity.     

Factors affecting female user information adoption: an empirical investigation on fashion shopping guide websites

With the prosperity of online shopping platforms, similar or even the same products tend to have a large variety of sources to be purchased from. More and more consumers seek the product information from online review websites before making a purchase, as they are willing to provide reviews or share their purchase experience. These behaviors turn the online review websites into vertical and community-based sales channels. Based on the Information Adoption Model, this study conducted an empirical investigation to analyze female users’ information adoption process when using fashion shopping guide website. The results show that information quality and source credibility have significant impact on information usefulness, which in turn contributes to information adoption. In addition, users with different levels of purchasing motivation demonstrate different dependence on information quality and source credibility.     

Will you spend more money and time on internet shopping when the product and situation are right?

Different from past online shopping research which focuses on exploring the cognitive and attitudinal aspects of online consumption behaviors, this study focuses on examining how online shopping motivation and product type affect the searching and spending behavior in an online website. In particular, the interactive effect between online shopping motivation and product type are explored in the study. A 2 × 2 between-subjects factorial experiment with two shopping motivations (i.e., goal-oriented and experiential) and two product types (i.e., hedonic and utilitarian product) was conducted. In addition to the main effects of online shopping motivation and product type, the results show that there is an interactive effect between online shopping motivation and product type on budget control. Participants conducted the loosest budget control when purchasing hedonic products in a goal-oriented online shopping trip because the shopping motivation provides a good justification for online shoppers to purchase hedonic goods without guilt or regret.     

Personality traits and effectiveness of presentation of product information in e-business systems

Consumer interaction with product information is one of the critical components in business-to-consumer (B2C) e-commerce environments. Online consumers' characteristics can be expected to play an important role when designing how product information is presented in such e-commerce environments. We suggest that online consumers' personality traits impact effectiveness of the presentation of product information on e-commerce sites and the extent to which the various e-commerce environments are effective. In this article, we propose and empirically validate relationships among online consumers' personality traits, product information presentation richness and on-line consumer behaviour in e-commerce environments. Results show that effectiveness of product information presentation varies by online consumers' psychological types, and that rich product information presentation significantly influences the online buying behaviour of intuitive types, and feeling types, rather than sensing and thinking types. Discussion of the results and their implications for theory and practice as well as limitations and future research directions are presented.     

Using an Eye-Tracking Approach to Explore Gender Differences in Visual Attention and Shopping Attitudes in an Online Shopping Environment

Growth in online marketing has been unprecedented, and mainstream shopping is shifting from traditional stores to online shopping channels. However, many aspects of online consumer behavior remain unaddressed. In particular, the effects of gender differences in visual attention on shopping attitudes are a great challenge in online retailers’ attempts to understand consumers’ cognitive processing and strategies. This study was designed to investigate the effects of gender on visual attention to online shopping information and its influence on attitudes about the products displayed. Using an eye-tracking approach, the results identified significant gender differences in visual attention to online shopping information and shopping attitudes about the products presented. Female participants attended visually to most of the online shopping information areas to a greater degree than did males, and their attitudes about products were influenced to some degree by visual attention to the consumer opinion areas. Although males’ visual attention was lower than females’, their shopping attitudes were influenced extensively by visual attention to product information and consumer opinion areas.     

Business information extraction from semi-structured webpages

To protect online consumers, as OECD Guidelines recommend, Internet shopping malls should provide information about their business on their webpages. In Korea, The Consumer Protection Law in Electronic Commerce, forced Internet shopping malls to provide their business information, so that consumers could easily identify them. Since most Korean Internet shopping malls provide consumers with business information in a semi-structured format on their homepages, a software agent can easily identify them.

To investigate automatically the provision of the business information with the Internet shopping malls, this article proposes the methods of gathering URLs of Internet shopping malls, of monitoring alterations of webpages, and of extracting business information. Business information extraction in our research is based on synonyms and indicator words of the attributes. We used inductive learning to raise the efficiency of information extraction. With experiments, we showed the potentialities of our agent system. The average extraction accuracy of our agent system was 89.3%.     

Examining the impact of rich media on consumer willingness to pay in online stores

This research examines the impact of rich media on purchase intentions and willingness to pay in online stores. Via an online experiment, we tested the effects of two rich media presentation formats: product videos and virtual product experience, and compared them with static displays. The results confirm that the rich media displays enhanced the feeling of informedness about the examined products and increased excitement regarding the shopping experience. Virtual product experience had a direct positive effect on consumer purchase intentions, suggesting that virtual product experience-focused tools have the potential to outperform passive videos. Moreover, consumers showed higher willingness to pay values for experience products than for search products when interaction was possible.     

The role of sunk costs in online consumer decision-making

Sunk costs, which can cause inconsistencies between consumer behavior and economic theory, have been widely studied in different research areas and among various consumer groups. Nevertheless, the authors found that to date there has been no empirical research examining how sunk costs affect consumer behavior with regard to online shopping in different product types. Therefore, this study used the following 2 × 2 × 2 experimental design to study the effects of sunk costs on consumers’ online shopping decisions. The results show that (1) sunk costs have significant effects on consumer online shopping behavior. However, due to the different product characteristics, the impacts were weaker effective when consumers bought search goods than when they purchased experience goods; (2) the sunk costs (Membership fee vs. Deposit) of an initial choice and a new choice had interaction effects on consumer intention to purchase a new product; and (3) the sunk costs and service quality of an initial choice and new choice would affect the level of regret felt with regard to the consumer’s initial choice. In addition, some recommendations on market positioning and service quality design are made, which practitioners can refer to when formulating marketing strategies.     

The impact of age and shopping experiences on the classification of search, experience, and credence goods in online shopping

This study explores how age and consumers’ Web shopping experience influence the search, experience, and credence (SEC) ratings of products and services in online shopping. Using the survey data collected from 549 consumers, we investigated how they perceived the uncertainty of product quality on six search, experience, and credence goods. The ANOVA results show that age and the Web consumers’ shopping experience are significant factors. A generation gap is identified for all but one experience good. Web shopping experience is not a significant factor for search goods but is for experience and credence goods. There is an interaction effect between age and Web shopping experience for one credence good. Implications of these results are discussed.     

How online social ties and product-related risks influence purchase intentions: A Facebook experiment

Drawing on information processing theory and the stimulus–organism–response model, we developed research hypotheses about consumers’ decision-making processes. Specifically, we examined the effects of online tie strength, perceived diagnosticity, and product-related risks on consumers’ purchase intentions. We conducted a field experiment on Facebook to test these hypotheses. We found that the product information and recommendations provided by friends with whom consumers have strong ties are perceived as having a high level of diagnosticity. The latter increases the probability that the consumers will purchase the product in question. Product-related risks moderate the effect of tie strength on perceived diagnosticity. For high-risk products, the information and recommendations provided by strong-tie contacts have a greater effect on purchase intentions than the information and recommendations provided by weak-tie contacts. However, we did not find this effect for low-risk products. We discuss the implications of our findings for both theory and practice.     

A consumption system model integrating quality,satisfaction and behavioral intentions in online shopping

A consumption system has two constitutive dimensions: the structural elements and the transaction process. Little attention has been paid to the effect of the consumption system on customer satisfaction and behavioral intentions during online shopping. This paper develops and tests a consumption system model for online shopping that incorporates both product and e-service elements, and the online and offline stages of the transaction process. Applying the transaction process of online shopping, this paper dichotomizes perceived product quality into online perceived product quality (OnPPQ) and offline perceived product quality (OffPPQ), and proposes four dimensions of e-service quality integral to the transaction process. An integrative model is proposed to link OnPPQ, OffPPQ, e-service quality, satisfaction and behavioral intentions. The research was based on empirical data from over 260 university students with experience purchasing apparel from online shops. Structural equation modelling was used to test the model and the hypotheses. The results show that perceived e-service quality, OnPPQ and OffPPQ significantly affect customer satisfaction. However, only customer satisfaction and OffPPQ have a direct effect on behavioral intention. A consumption system model successfully theorizes the dimensions of perceived product quality and e-service quality. The model considers the simultaneous effects of the two structural elements, product and e-service, as well as the temporal effect of the online shopping transaction process. Different structural elements in separate transaction processes have distinct effects on satisfaction and behavioral intentions. The research and its results are especially valuable for online shopping for physical goods.     

Effects of consumer characteristics on their acceptance of online shopping: Comparisons among different product types

Previous electronic commerce (EC) studies have found that consumer characteristics are important when considering issues related to the acceptance of online shopping. However, most studies have focused on a single product or similar products. The effects of different product types have been relatively neglected. Previous studies have limited the generalizability of their results to a few products at best. To overcome this limitation, the purpose of this study was to explore the effects of different product types. The Internet product and service classification grid proposed by Peterson, Balasubramanian and Bronnenberg (Peterson, R. A., Balasubramanian, S., & Bronnenberg, B. J. (1997). Exploring the implications of the Internet for consumer marketing. Journal of Academy of Marketing Science, 25(4), 329–346) was employed to examine the effects of consumer characteristic differences on online shopping acceptance in the context of different products and services. A survey-based approach was employed to investigate the research questions. Regression analysis demonstrated that the determinants of online shopping acceptance differ among product or service types. Additionally, personal innovativeness of information technology (PIIT), perceived Web security, personal privacy concerns, and product involvement can influence consumer acceptance of online shopping, but their influence varies according to product types.     

Gender differences in consumers’ perception of online consumer reviews

Since the early days of the Internet, gender gap has existed in using the Internet, and it is particularly evident for online shopping. Females perceive higher level of risk for online shopping, and as a result, they tend to hesitate to make purchase online. Online consumer reviews can effectively mitigate such perceived risk by females and thereby attract them to buy online. This study investigates the effect of online consumer reviews on consumer’s purchase intention. In particular, we examine whether there are gender differences in responding to online consumer reviews. The results show that the effect of online consumer reviews on purchase intention is stronger for females than males. The negativity effect, that consumers are influenced by a negative review more than by a positive review, is also found to be more evident for females. These findings have practical implications for online sellers to guide them to effectively use online consumer reviews to engage females in online shopping.     

Assessing the impact of recommender agents on on-line consumer unplanned purchase behavior

Recommendation agents (RAs) have been used by many Internet businesses such as Amazon and Netflix. However, few authors have studied how consumer behavior is affected by those that make suggestions to online consumers based on their recent shopping behavior. Fewer still have examined the role that RAs play in influencing impulse purchasing decisions online. Our study developed a theoretical model to illustrate the impact of RAs on online consumer behavior. The model was tested through an online shopping simulation which used a collaborative filtering based product RA. Particular attention was paid to the effects of an RA on consumer behavior; we found that it increased promotion and product search effectiveness, user satisfaction with the website, and unplanned purchases. Results showed that our model provided insights into the impact of an RA on online consumer behavior and thus provided suggestions for implementing effective systems.     

Search product and experience product online reviews: An eye-tracking study on consumers' review search behavior

This study uses eye-tracking method to investigate consumers' online review search behavior by suggesting that it needs to consider the type of product reviewed. A review-product congruity proposition was testified through a self-report survey and an eye-tracking experiment. The proposition states that consumers of search products expect to seek attribute based reviews, while consumers shopping for experience products tend to seek experience based reviews. Two experiments were conducted in the human factors & ergonomics laboratory of Beihang University, China and all subjects are college students. The results of our first empirical experiment support our hypotheses by showing consumers' more active and positive responses to attribute based reviews when shopping for search products and to experience based reviews when purchasing experience products. The second experiment was conducted with eye tracking method to gain further insights. We found that consumers of search products are attracted and engaged more deeply by attribute based reviews. However, when they browse experience products, the difference of their fixations on experience based reviews and attribute based reviews is not significant, and thus the proposition is partially supported. This study extends our current understanding of consumers' online review search behavior by subsuming product type, which is necessary and helpful, and provides references on the classification and presentation of reviews to facilitate consumers' product judgement and decision making. Moreover, comparison of traditional empirical method and eye-tracking method can help deepen our understanding of complex consumer online shopping behavior.     

基于证据网络的C2C商品购买风险动态评估模型

C2C(consumer to consumer)电子商务市场中的风险认知是消费者网络购物决策的重要依据之一.首先,分析电子商务市场中商家信誉、商品销量和在线商品评论对消费者网购决策的影响;然后,运用信度规则模型推理节点关系,建立基于证据网络的C2C商品购买风险动态评估模型;最后利用从某电子商务网站收集的观测信息,运用多元线性回归分析方法验证购买风险动态评估模型的可行性.借助本模型,可以帮助消费者在网购商品过程中较好地认知商品购买的风险.     

Effects of consumer visit to online community and product channel on local sales of large consumer goods: Evidence from real estate industry

Online intermediaries have become important information sources for consumers’ purchase decision making. However, the economic values of consumer visits to two online intermediaries, namely, online community and product channel, have not been well studied. By collecting a dataset on consumer visits from a large real estate website to match with local offline housing sales data, we empirically explore the respective, relative, and interaction effects of consumer visits to online communities and product channels on sales of large consumer goods. We control for relevant factors, account for potential endogeneity issues, and perform various robustness checks to validate the consistency of our findings. Our results show that consumer visits to online communities have a more significant effect than those to product channels in driving sales. However, the interaction effect of consumer visits to these two online intermediaries on sales is negative. We also find that consumer website-related experience has a significant moderating effect on the relationship between consumer visits to product channels and sales. Our findings provide important theoretical contributions and managerial implications.