Showing papers in "Electronic Commerce Research in 2021"

20 years of Electronic Commerce Research

Abstract: 2021 marks the 20th anniversary of the founding of Electronic Commerce Research (ECR) The journal has changed substantially over its life, reflecting the wider changes in the tools and commercial focus of electronic commerce ECR’s early focus was telecommunications and electronic commerce After reorganization and new editorship in 2014, that focus expanded to embrace emerging tools, business models, and applications in electronic commerce, with an emphasis on the innovations and the vibrant growth of electronic commerce in Asia Over this time, ECR’s impact and volume of publications have grown rapidly, and ECR is considered one of the premier journals in its discipline This invited research summarizes the evolution of ECR’s research focus over its history

Impact of content characteristics and emotion on behavioral engagement in social media: literature review and research agenda

Abstract: We present a review of N = 45 studies, which deals with the effect of characteristics of social media content (e.g., topic or length) on behavioral engagement. In addition, we reviewed the possibility of a mediating effect of emotional responses in this context (e.g., arousing content has been shown to increase engagement behavior). We find a diverse body of research, particularly for the varying content characteristics that affect engagement, yet without any conclusive results. We therefore also highlight potential confounding effects causing such diverging results for the relationship between content characteristics and content engagement. We find no study that evaluates the mediating effect of emotional responses in the content—engagement relationship and therefore call for further investigations. In addition, future research should apply an extended communication model adapted for the social media context to guarantee rigorous research.

The relationship between smartphone use and subjective well-being in rural China

Abstract: Due to the popularization of the Internet in rural China, mobile Internet use has become an essential part of rural residents’ lives and work. No studies, however, have investigated the potential effect of smartphone use on quality of life among rural residents in China. This study thus applies ordinary least squared, conditional quantile and instrumental variable techniques to survey data for 493 rural Chinese households to assess the impact of smartphone use (SU) on their subjective well-being (SWB). The results reveal an association between SU and increases in both life satisfaction and happiness that remains even after we adjust for possible endogeneity. The analysis also indicates that SU intensity is associated with lower levels of both SWB measures, especially when it exceeds 3 h per day. Quantile estimates further indicate that in both participation and intensity, SU has a much greater impact on SWB at the median level of the SWB distribution. Our multiple mediation results show that the positive SU–SWB linkage is partially mediated by both farm income and off-farm income. This may suggest that the local government should invest in Internet infrastructure to promote agricultural activities and develop specific rural services to boost farm income via better access to information of agricultural production and market networks. Mobile information and communication technologies can also provide more opportunities for rural entrepreneurship and innovation, in particular by motivating young farmers to actively engage in rural e-business ventures which can raise off-farm income.

Four generational cohorts and hedonic m-shopping: association between personality traits and purchase intention

Abstract: In retailing, it is recognized that prominent differences exist between generational cohorts. As such, analysis of varying patterns of personality traits and their effects between generations is essential for understanding consumer behaviors. This research focuses on the association between the Big Five personality traits and m-shopping intentions of hedonic products among four generational cohorts: baby boomers and Generations X, Y, and Z. Generational cohort theory, the Big Five Personality Model, and resistance to innovations theory are integrated in a theoretical framework. The research was conducted by online survey of 1241 Internet users aged 14–72. Different patterns of effects of personality traits between generations were found. For baby boomers and Generation X, a positive association between openness to experience and m-shopping intention was found. Moreover, in these generations, personality traits were more powerful in predicting m-shopping intention, compared to younger generations. Among Generation Y, extraversion was positively correlated with m-shopping intention. Among Generation Z, a negative correlation between agreeableness and m-shopping intention was found. Based on our findings, we propose a generational approach to marketing strategy and suggest specific practical implications.

Cash flow prediction: MLP and LSTM compared to ARIMA and Prophet

Abstract: Cash flow prediction is important. It can help increase returns and improve the allocation of capital in healthy, mature firms as well as prevent fast-growing firms, or firms in distress, from running out of cash. In this paper, we predict accounts receivable cash flows employing methods applicable to companies with many customers and many transactions such as e-commerce companies, retailers, airlines and public transportation firms with sales in multiple regions and countries. We first discuss “classic” forecasting techniques such as ARIMA and Facebook's™ Prophet before moving on to neural networks with multi-layered perceptrons and, finally, long short-term memory networks, that are particularly useful for time series forecasting but were until now not used for cash flows. Our evaluation demonstrates this range of methods to be of increasing sophistication, flexibility and accuracy. We also introduce a new performance measure, interest opportunity cost, that incorporates interest rates and the cost of capital to optimize the models in a financially meaningful, money-saving, way.

Smartphone-based information acquisition and wheat farm performance: insights from a doubly robust IPWRA estimator

Abstract: This study examines the impact of smartphone-based information acquisition on crop yields, net returns, return on investment (ROI), and production costs, using survey data collected from 558 wheat farmers in rural China. We employ a double-robust inverse probability weighted regression adjustment estimator to address the potential selection bias issue. The results reveal that information acquisition via smartphones significantly increases wheat yields, net returns, and ROI by 7%, 31%, and 39%, respectively, and it has a negative but insignificant impact on production costs. These results largely echo the results estimated from propensity score matching and endogenous switching regression models. In general, our findings suggest that policy interventions targeting to boost farm economic performance should consider distributing agricultural production and marketing information via smartphones.

Study on early warning of E-commerce enterprise financial risk based on deep learning algorithm

Abstract: With the development trend of economic progress, the capital business of e-commerce enterprises has become complicated. The financial risk of listed companies is a problem that needs to be paid attention to. The financial risk of e-commerce companies is a complex and gradual process, and its unique reasons may be many. E-commerce companies are facing financial risks or difficulties, and bankruptcy and liquidation are also increasing. Financial risk has seriously affected e-commerce companies and society. As a result, the early warning methods of financial risks have been constantly improved. With the arrival of the new economic era in the era of knowledge economy, the early warning of financial risks in e-commerce companies has become a hot issue in the financial management of e-commerce companies. Based on the deep learning algorithm, this paper studies from the perspective of establishing the financial early warning model based on deep learning and constructing the financial risk early warning mechanism of e-commerce companies, and analyzes and forecasts the financial risks of listed companies. Through the construction of financial security early warning system, crisis signals can be diagnosed as soon as possible, and crisis signals can be prevented and solved timely and effectively.

When does online review matter to consumers? The effect of product quality information cues

Abstract: Word of Mouth (WOM) is powerful, and online reviews are often the most accessible WOM information source in electronic commerce. Maintaining favorable online reputation has been the top priority for businesses, and investments in improving online review valence have been increasing. Extensive studies explored how online reviews might influence sales, however, the results have been inconsistent. This study explores whether and how consumers might incorporate online reviews into decision making based on signaling theory and examines when online review valence influences sales and when it might not. In a signaling perspective, online reviews might serve as a product quality signal, and subsequently, consumers might incorporate less the online review information into decision making if other product information cues such as expert ratings or brands help to verify the product quality. The findings from 633,029 consumer decisions on a hotel-booking website indicate that product quality information cues moderate the effect of online reviews on purchase likelihood. Also, product quality information cues were highly endogenous in estimating the effect of online reviews on sales. Online reviews are not likely to be a significant influencer on sales if the seller signal product quality with convincing information cues.

Towards effective discovery of natural communities in complex networks and implications in e-commerce

Abstract: Automated community detection is an important problem in the study of complex networks. The idea of community detection is closely related to the concept of data clustering in pattern recognition. Data clustering refers to the task of grouping similar objects and segregating dissimilar objects. The community detection problem can be thought of as finding groups of densely interconnected nodes with few connections to nodes outside the group. A node similarity measure is proposed here that finds the similarity between two nodes by considering both neighbors and non-neighbors of these two nodes. Subsequently, a method is introduced for identifying communities in complex networks using this node similarity measure and the notion of data clustering. The significant characteristic of the proposed method is that it does not need any prior knowledge about the actual communities of a network. Extensive experiments on several real world and artificial networks with known ground-truth communities are reported. The proposed method is compared with various state of the art community detection algorithms by using several criteria, viz. normalized mutual information, f-measure etc. Moreover, it has been successfully applied in improving the effectiveness of a recommender system which is rapidly becoming a crucial tool in e-commerce applications. The empirical results suggest that the proposed technique has the potential to improve the performance of a recommender system and hence it may be useful for other e-commerce applications.

Optimal pricing decision of composite service offered by network providers in E-commerce environment

Abstract: With the increasing demand of consumers for diversified network services, more and more network service providers are competing fiercely in providing network composite services in order to meet the market demand. Network composition service is the most basic service. According to certain rules, it synthesizes new services and then realizes new functions. At present, the pricing of service composition by network service providers in the market is not scientific, meanwhile random and temporary pricing is still relatively common. In order to scientifically guide network service providers to price composite service scientifically and effectively, improve the profit of service providers, and meet the maximum service demand of consumers. Based on the theory of market demand price, this paper applies the pricing model in supply chain management to the pricing link of composite service network. From the perspective of network service providers, a two-objective competitive pricing model is constructed, and the simulation example analysis and sensitivity test are carried out. The simulation results show that the composite service provided by network service providers satisfy the general market demand price theory. In order to help service providers make scientific decisions on price adjustment of network services, this paper also makes sensitivity analysis of market demand on price changes. The research shows that the composite service provided by network service providers satisfy the general market demand price theory, while adjusting the price can only meet the general market demand price change theory if the original price is less than half of the original price.

A choice of selling format in the online marketplace with cross-sales supply chain: Platform selling or traditional reselling?

Abstract: In the online retail market, how to work with upstream suppliers is a key issue for downstream online retailers (e-retailers). Online retailers can choose between functioning either as the “two-sided platforms” (e.g., Taobao.com or eBay.com) allowing suppliers to sell directly to customers by paying a revenue-sharing fee, or as the “resellers” (e.g., Wal-mart.com or JingDong.com) that purchase products from suppliers, and then resell them to customers. Given the rapid growth of e-commerce over past few years, this choice, which is the focus of this article, has become an important practice-based decision. We develop a game-theoretic model for a cross-sales supply chain in which two suppliers deal with two common online retailers. As Stackelberg leaders, online retailers can operate either as a two-sided platform (serving both suppliers and customers) or as a reseller (ordering from suppliers and selling competing products on its own platform). Each supplier adopts either an exclusive-sales strategy, selling products through an exclusive e-retailer, or a cross-sales strategy, selling products through two e-retailers. We analyze the optimal decisions for both e-retailers and suppliers in competing supply chains and describe the system equilibrium for the online marketplace.

A novel trust recommendation model for mobile social network based on user motivation

Abstract: Traditional collaborative filtering recommendation algorithm has the problems of sparse data and limited user preference information. To deal with data sparseness problem and the unreliability phenomenon on the traditional social network recommendation. This paper presents a novel algorithm based on trust relationship reconstruction and social network delivery. This paper introduces the method of eliminating falsehood and storing truth to avoid the unreliable phenomenon and improves the accuracy of falsehood according to the user similarity formula based on the scale of contact established by users. In this paper, the problem of attack caused by the misbehaving nodes is investigated when the recommended information is disseminated in the existing trust model. In addition, a recommendation-based trust model is proposed that includes a defensive plan. This scheme employs the clustering techniques on the basis of interaction count, information Compatibility and node intimacy, in a certain period of time dynamically filter dishonest recommendation related attacks. The model has been verified in different portable and detached topologies. The network knots undergo modifications regarding their neighbors as well as frequent routes. The experimental analysis indicates correctness and robustness of the reliance system in an active MANET setting. Compared with the most advanced recommender system, the proposed recommendation algorithm in accuracy and coverage measurements show a significant improvement.

Measuring the consumer engagement related to social media: the case of franchising

Abstract: The appearance of social media has fostered consumers chatting with each other, comparing and recommending products and services In the case of franchising, social media take on a yet greater importance due to brands having to achieve the expansion of their chains selecting new franchisees The aim of this paper is, on the one hand, to analyze the activity of franchise chains in social media -Facebook and Twitter- and, on the other hand, to measure the engagement which social media users show with franchise brands or chains Quantitative data from Spanish franchisors (N = 53 and N = 46) was collected by means of the Fanpage Karma and Twitonomy tools The PRGS model and statistical tests were used for the analysis of the data The results show that the activity of the chains in social media is different according to the sector in which the chain is operating Conclusions are also drawn regarding the characteristics of franchising chains

The effects of China’s cross-border e-commerce on its exports: a comparative analysis of goods and services trade

Abstract: This study examines the effects of China’s cross-border e-commerce (CBEC) on its goods and services exports to ‘Belt and Road’ (B&R) countries for the period 2000–2018 using a gravity model. We find that CBEC has a greater positive impact on trade in services than on trade in goods, especially after the implementation of the B&R initiative. Furthermore, as the level of CBEC rises, distance tends to have a lower (higher) impact on services (goods) trade, whereas the impact on services (goods) trade increased (decreased) annually. Hence, promoting the sustainable development of CBEC can lead to increased export volumes.

Assessing hotel decision-making of disabled guests: satisfaction correlation study between online comments’ credibility and perceived risk

Abstract: Online comments have become an important tool for disabled guests because of lower physical movement requirements. In order to illustrate and evaluate disabled guests’ decision-making characteristics, this paper has used two steps for studying: (1) Data mining technology to collect e-comments from C-trip ( www.ctrip.com ) of 97 hotels in the cities of Beijing, Shanghai, Hangzhou and Guangzhou. Over 260,000 words were collected and analyzed by using ROSTcm software for this research. (2) Examined the relationship between the credibility and the perceived risk of disabled guests for their behavioral intentions. The result of this study has showed that: (1) Disabled guests pay more attention to the hotel barrier-free facilities, hotel barrier-free facilities, hotel personalized service, location accessibility, and the attitude and atmosphere of the hotel. (2) Disabled guests show positive attitude towards the hotel, and a neutral attitude accounting for 25.86% which indicates that the hotel industry still has much improving room especially with regards to disabled accessible guestrooms and accessibility. (3) Electronic Word-of-Mouth (eWOM) source credibility has a great influence on the overall perceived risk of the review of disabled guests because they are more likely for seeking internet comments for their lodging decision-making than other common guests. eWOM rational management can reduce the overall potential risk for disabled guests. (4) Hotels can enhance disabled guests’ decision-making by advanced eWOM management. The study illustrated that disabled guests who used eWOM could be better managed and reduce potential risks when making decisions. As a result, this study also found that with better management of eWOM, it could help to meet the potential market for the disabled guests and at the meanwhile attract more customers because of higher social reputation.

Game theoretic analysis of logistics service coordination in a live-streaming e-commerce system

Abstract: This study explores the coordination issues in the logistics service supply chain, which stem from the rapid development of live-streaming e-commerce (LSE). It also investigates the influences of a cost-sharing mechanism on the key decisions for live-streaming e-commerce logistics service supply chains (LSE-LSSC) with regard to the level of effort of logistics services. The motivation of the research is derived from the growing efficiency demands for logistics services in the LSE field. We consider an LSE-LSSC, which consists of one e-commerce shipper, one logistics service integrator, and one logistics service provider. On the basis of the game theoretic method, the performance of the logistics service supply chain is assessed and compared with four models among the participating entities of the LSE-LSSC. Some interesting results and key managerial insights are obtained in the modeling study. More importantly, the influences of cost-sharing on the key decisions of each player are discussed in detail, and the coordination contract of the level of effort of the logistics service is estimated.

How do reputation, structure design and FinTech ecosystem affect the net cash inflow of P2P lending platforms? Evidence from China

Abstract: Based on daily data of 749 active online P2P lending platforms in Chinese market, this study explores the key factors affecting the net cash inflow rate of the platform which is vital for its operation and survival from the perspective of reputation, structure design and FinTech ecosystem. Internal governance issues of P2P lending platforms are further discussed according to the model results. A positive U-shaped relationship has been found between the platform duration and its net cash inflow rate which proves the role of reputation in the long-term development of P2P lending platforms. In addition, we demonstrate that both capital and operational structure design of the platform (e.g. shareholders background, credit assignment, trusteeship and guarantee) have a significant impact on the platform’s net cash inflow rate. The cash flow level of the platform has also been affected by the regional FinTech ecosystem. Platforms in a medium-developing ecosystem may have the highest net cash inflow rate, while a backward ecosystem will lower the cash flows of the platforms located in this area on average. Some suggestions on cash flow management and internal governance of P2P lending platforms for both platform founders and governments are put forward in the end of the study.

Ranking objectives of advertisements on Facebook by a fuzzy TOPSIS method

Abstract: Social networking sites (SNSs) have become a vital medium for companies to place advertisements and setting an objective of advertisements on SNSs is an important issue of planning a business’s market strategy. The purpose of this work is to develop a fuzzy technique for order preference by similarity to an ideal solution (TOPSIS) method for evaluating and selecting objectives of advertisements on Facebook. In the proposed model, the fuzzy weighted ratings are defuzzified by a centroid method to generate distances of each alternative to the positive and negative ideal solutions. A fuzzy weighted normalized distances index is proposed to rank alternatives, and the centroid method is used for defuzzification. Formulas for the defuzzification of fuzzy weighted ratings and the fuzzy weighted normalized distances index are developed. A numerical example of evaluating objectives of advertisements on Facebook is used to demonstrate the feasibility of the proposed method. Example result reveals that the proposed fuzzy weighted normalized distances index is as effective as the crisp closeness coefficient in ranking objectives under the proposed fuzzy TOPSIS method. An experiment demonstrates that the rankings of objectives may be more likely to change as the gap between two linguistic weights that are assigned to fuzzy weighted normalized distances index increases.

The influence of community engagement on seller opportunistic behaviors in e-commerce platform

Abstract: Firms using e-commerce as platforms need to develop effective mechanisms to govern seller opportunism. This paper attempts to explore the effect of seller community engagement, as an informal mechanism of network governance, on seller opportunistic behaviors. In particular, we identify two types of the seller community established by the e-commerce platforms, which offers infrastructures supporting tightly and loosely coupled relationships among members, respectively. We find that engaging in both types of communities reduces seller opportunistic behaviors. We also show that the intensity of competition positively moderates the relationship between engagement in the communities with tight infrastructure and sellers’ opportunistic behaviors, while deterrence perception exerts a negative moderating effect on the relationship. In contrast, the intensity of competition negatively moderates the relationship between engagement in communities with loose infrastructure and opportunistic behaviors. The findings provide theoretical and managerial implications for opportunism governance in electronic markets.

Economical user-generated content (UGC) marketing for online stores based on a fine-grained joint model of the consumer purchase decision process

Abstract: User-generated content (UGC) is influential in reducing customer perceived risk and determining online store sales. E-sellers spend huge costs and efforts to improve UGC for it serves as a convenient and persuasive alternative for marketing and advertising purposes. Considering that consumers may set lower and/or upper limits (i.e., psychological thresholds) in which the good is expected to be, and purchase decisions are considered as a multi-stage decision process, yet models in previous research cannot uncover this decision-making process. Therefore, exploring the impact of UGC at each decision-making stage and detecting the psychological thresholds on various aspects of UGC (i.e., the fine-grained effects of UGC) contribute to optimizing the UGC with the best cost to boost sales. To this end, a fine-grained joint two-stage decision model, zero-inflated negative binomial regression (ZINB-P) model is proposed to support economical UGC marketing. Specifically, we compile a factors system composed of various types of aggregate-level statistics of UGC, which can impact risk perception. Afterward, change point analysis is used to find multi-level consumer psychological thresholds on UGC factors and consumers’ risk perception model is constructed to measure purchasing probabilities in the first decision-making stage. On the basis of consumers’ risk perception model, the ZINB-P model is built to fully capture the fine-grained effects of UGC factors on each stage of the consumer purchase decision. It integrates two stages of consumer decision: the consumer risk perception and non-compensatory choice in the first stage, and the second compensatory stage. A genetic algorithm is constructed to jointly estimate the parameters in ZINB-P model. Finally, an experiment on a kind of fresh produce from Taobao.com evidences the precision of our model. We demonstrate how our model can provide with economical UGC marketing strategies using a decision support table, in which some scenarios are identified. E-sellers can use this table to find the scenarios they are located in and identify the critical UGC factors that impede the sales in each scenario, and thus economical UGC marketing strategies can be obtained by improving these critical UGC factors.

Modeling users’ acceptance of mobile social commerce: the case of ‘Instagram checkout’

Abstract: Mobile Social Commerce (MSC) is the present and the future of e-commerce; and a growing topic of research interest. However, despite its numerous current abilities and its prosperous future prospects there has been slightly investigated so far. In order to fill this research gap, this empirical study aims to model and examine the factors that impact individuals’ behavioral intention on adopting MSC. In specific, it focuses on a comparatively new service of Instagram, the checkout option; and investigates m-users’ behavioral intention towards this operation in a country where this service is not available yet. The study presents a holistic acceptance conceptual model in the context of MSC that combines the UTAUT scheme, the innovation characteristics of the DOI theory (i.e., compatibility and innovativeness), along with the basic social interaction variables (i.e., closeness and familiarity) and the major ICT inhibitors (i.e. risk and anxiety); with the aim to increase the understanding on the topic. As far as it is concerned, ‘Instagram checkout’ has never explored before. The results demonstrate that compatibility and performance expectancy exert the strongest positive effect on behavioral intention. Social influence and familiarity also influence positively m-users’ decisions to adopt ‘Instagram checkout’, whereas anxiety exerts a negative impact.

Prediction on transaction amounts of China’s CBEC with improved GM (1, 1) models based on the principle of new information priority

Abstract: Benefited by e-commerce activities and information technology development, cross-border e-commerce (CBEC) has experienced rapid growth and attracted much research attention. This study takes China’s CBEC as a typical research object and intends to forecast its future development trend based on an exploration of its dynamic changing rules as a whole. The data set of transaction amounts of China’s CBEC from 2008 to 2018 was used in the modeling processes of improved grey models (GM) (1,1) proposed in this study, after which forecast results on the development of China’s CBEC from 2019 to 2020 were achieved. The experimental results reveal that, introducing the principle of new information priority to the improvement of grey models indeed works when forecasting a newly-emerging and vulnerable system like CBEC. Finally, it is predicted that China’s CBEC promises to continue to grow in the near future.

The value of offline channel subsidy in bricks and clicks: an O2O supply chain coordination perspective

Abstract: This paper aims to explore a rarely studied mutual promotional effects, operational strategies and cross-channel subsidy policies in a two-stage/two-player online-to-offline (O2O) supply chain. The centralized, decentralized and coordination decision models are developed, analyzed and compared for O2O mode without offline subsidy, O2O mode with offline subsidy and the pure online/offline channel mode. The revenue sharing contract (RSC) and two-part tariff contract (TTC) with Nash bargaining game are incorporated into the coordination models as the coordinating mechanisms. The numerical and sensitivity analyses based on an industry representative product (a popular smart phone product) are conducted and the corresponding results are compared to derive managerial insights and practice implications. The key findings show that a coordination strategy with offline subsidy can create the highest value to a two-player O2O supply chain and its members. As far as whether RSC or TTC coordinating mechanism should be undertaken, it depends on the risk-taking attitude and the relative power of both players in the supply chain. With a focus on the O2O supply chain strategy exploration, this study amends the literature shortage problem and broaden the much-needed knowledgebase in the O2O supply chain coordination studies.

Incentive mechanism to prevent moral hazard in online supply chain finance

Abstract: With e-commerce developing rapidly, banks have begun to cooperate with online platform operators to finance small and medium-sized enterprises (SMEs). However, this process engenders its own unique financial risks. This study highlights and investigates the risks in a four-party supply chain that include a third-party logistics provider, a bank, a B2B platform operator, and SMEs. In an asymmetric information setting, the collusion mechanisms in this four-party online supply chain are also explored. Subsequently, a two-part incentive contract is designed that can reduce the moral hazard faced by the banks while addressing the trade-off between the payments to the platform operator for better credit rating information and the payments to the third-party logistics provider for supervising collateral storage. For further confirmation, a numerical analysis is presented. The results indicate that based on a suitable capital coefficient, the two-part incentive contract may prevent moral hazard in online supply chains. Furthermore, when the line of credit is high, the bank must increase the incentives for the B2B platform operator to avoid default risk and decrease the incentives for 3PL.

Scenario based e-commerce recommendation algorithm based on customer interest in Internet of things environment

Abstract: With the development of mobile commerce, situational awareness and Internet of things, the boundaries of e-commerce have been greatly expanded, and it has entered a big data era of business information. However, customers are faced with the problem that information is rich but useful information is hard to get. E-commerce is facing the challenge of how to provide personalized information recommendation services for customers and motivate customers to purchase continuously. Therefore, this paper studies the problem of e-commerce recommendation under the condition of large data, and proposes a scenario-based e-commerce recommendation algorithm based on customer interest. Firstly, according to the characteristics of customer interest such as situational sensitivity and diversity in personalized recommendation, a multi-dimensional customer interest feature vector is established by using distributed cognitive theory to differentiate the sensitive scenarios of customer interest. Then, the collaborative filtering recommendation algorithm is used to realize customer similarity judgment and product recommendation in sensitive scenarios. Experimental results show that the method has good customer interest extraction ability. Compared with other recommendation methods, it has higher recommendation accuracy and can adapt to the high-quality commodity recommendation service in the process of customer continuous purchase under complex circumstances.

Hot topic prediction considering influence and expertise in social media

Abstract: The hot topic detection designed to identify the recent issues and trends employs the analysis of real-time social media activities. The existing schemes suffer from low precision because they focus on keyword occurrence frequency in documents written by the unspecified majority. The existing schemes are incapable of predicting near-future hot topics as they are intended to detect hot topics at a particular time. We propose a new hot topic prediction scheme considering users’ influence and expertise in social media. The proposed scheme detects expected near-future hot topics by extracting a set of candidate keywords from social-media posts using the modified TF-IDF. The hot topic prediction index is calculated for each candidate keyword based on the influence and expertise of users who include it in their posts and hot topic predictions are performed based on the change rate over time. Finally, a comparison between existing and proposed hot topic detection schemes demonstrates the proposed scheme’s superiority.

A distinctive early bird price in reward-based crowdfunding

Abstract: Many crowdfunding platforms allow creators maximum flexibility in terms of the prices and rewards offered in a project to gain sufficient capital. Early bird prices, with the original purpose of attracting more early consumers by providing a discounted price for the same product sold in traditional e-commerce retail, are widely used in crowdfunding worldwide and unexpectedly result in “overpay” behaviour. This research aims to explore whether and how creators can use this “overpay” behaviour through dynamic theory with incomplete information, verifying our point of view through empirical analysis. The results show that providing multiple prices for same product generally increases funding performance because backers will balance the surplus and the success rate of their payment decisions to maximize their expected surplus; however, when projects face the low heterogeneity of backer groups, providing a uniform price may be an optimal pricing decision. These findings have direct implications for launching crowdfunding projects that will be more effective in funding more capital by offering reasonable prices.

Optimal advertising for a generalized Vidale–Wolfe response model

Abstract: In this research, we formulate budget allocation decisions as an optimal control problem using a generalized Vidale–Wolfe model (GVW) as its advertising dynamics under a finite time horizon. One key element of our modeling work is that the proposed optimal budget allocation model (called GVW-OB) takes into account the roles of two useful indexes of the GVW model representing the advertising elasticity and the word-of-mouth (WoM) effect, respectively, in determining optimal budget. Moreover, we discuss desirable properties and provide a feasible solution to our GVW-OB model. We conduct computational experiments to assess our model’s performance and its identified properties, based on real-world datasets obtained from advertising campaigns by three e-commerce companies on Google AdWords, Facebook Ads and Baidu Ads, respectively. Experimental results show that (1) our GVW-OB strategy outperforms four baselines in terms of both payoff and ROI in either concave or S-shaped settings; (2) linear budget allocation strategies favor concave advertising responses, while nonlinear strategies support S-shaped responses; (3) a larger ad elasticity empowers higher levels of optimal budget and corresponding market share and thus achieves higher payoff and ROI, so does a larger WoM effect; and (4) as the total budget increases, the resulting payoff by the GVW-OB strategy increases monotonically, but the ROI decreases, which is consistent with the law of diminishing marginal utility. From a methodological perspective, our GVW-OB strategy provides a feasible solution for advertisers to make optimal budget allocation over time, which can be easily applied to a variety of advertising media. The identified properties and experimental findings of this research illuminate critical managerial insights for advertisers and media providers.

The impact of perceived risks on internet banking adoption in Iran: a longitudinal survey

Abstract: This paper tried to investigate the trend of changes in severity and the impact of dimensions of perceived risks by customers on their intention to adoption of internet banking (IB) by a longitudinal survey. In order to achieve this goal, based on the perceived risk theory, two surveys were conducted using the same research method in 2009 and 2019 in the Iranian context. The results showed that while the effect of all dimensions of perceived risk in both surveys (except social risk) to adoption of IB were significant, the severity and effect of security and privacy risks increased, time risk decreased and financial and performance risks remained unchanged. Finally, based on the analysis of these results, suggestions were made to modify and optimize banking strategies and policies in order to have a greater impact on reducing these risks.

Determining user needs through abnormality detection and heterogeneous embedding of usage sequence

Abstract: In this study, we propose an advanced method for determining user needs based on abnormality detection and heterogeneous embedding of the usage sequences. We focus on the implied needs at the fine-grained levels based on the usage sequence, whereas previous textual review-based approaches have focused on the explicit needs at the product levels. Moreover, although previous studies regarding a usage sequence have primarily focused on an analysis of the tendency, app prediction, or recommendations, we first attempted to uncover abnormal sequences regarding user needs. Furthermore, in terms of the methodology, we then attempted a heterogeneous embedding approach to calculate the vector representation of each element of the usage sequence including the application, buttons, content, or system keys by utilizing the metapath2vec algorithm, which differs from previous studies that have focused solely on the embedding application usage. Further, to apply the abnormality detection method in determining an abnormal sequence corresponding to the user needs, we calculate the vector representation of the entire usage sequence utilizing RNN-AE based on heterogeneous embedding. After examining and evaluating the extracted abnormal sequences with the help of domain experts from LG Electronics, the experimental results verify that our proposed method can effectively extract a meaningful abnormal sequence corresponding to the implied needs. In addition, we calculated the correlation of the coefficient between the abnormality score and the importance score of the extracted sequences to compare the performance of each sequence model and the abnormality detection method.