International Journal of Electronic Business (16 papers in press)
Predicting P2P Lenders Decisions: The Prospect Theory Approach
by Yong Lu, Zhexiang Sheng, Kaidong Zhang, Qiang Duan
Abstract: This study investigates the importance predictors for lenders decisions on peer-to-peer lending based on prospect theory. We apply two machine learning algorithms (decision trees and random forest) to identifying the important measures. We found that borrowers default history is the most important variable, followed by the default ratio of the borrowers other type of friend and borrowers credit score as lender. These results prove that lenders play safety rule in the highly risky P2P lending business. Maximum entropy algorithm verifies these results and proves the robustness of our model.
Keywords: Prospect Theory; Machine Learning; P2P Lending.
Factors Influencing Trust in Social Commerce: The Case of Qatar
by Hamad Al Kubaisi, Emad Abu-Shanab
Abstract: The global spread of social media platforms, along with the technology acceptance, has contributed significantly in accelerating the birth of social commerce, which is one of the most prominent advancements of e-commerce. To keep up with the trend, online vendors or social vendors need to improve customers' trust towards social commerce to enhance customer engagement and to leverage the potential power of social networking. This research aims at studying the factors influencing trust in Social commerce in the context of Qatar. The proposed research model adopted seven different factors that are assumed to influence trust in social commerce in Qatar. These factors include Platform Involvement (PI), Information Quality (IQ), Perceived Privacy Protection (PPP), Trust Disposition (TD), Informational Support (IS), Social Commerce Constructs (SCCs), and Reputation of Online Vendors (REP). A sample of 320 valid responses was collected using a snowball sampling technique. Different statistical methods were performed, including multiple regression for hypotheses testing. Four variables out of seven were found statistically significant in predicting the trust in social commerce, namely, the Reputation of online vendors, Information Quality, Platform Involvement, and Social Commerce Constructs. Based on the research findings, research and managerial implications, limitations, and future work were presented and discussed.
Keywords: Social Commerce; Trust; Qatar; Platform Involvement; Information Quality; Reputation of Online Vendors; Social Commerce Constructs; Trust Disposition; Informational Support; Perceived Privacy Protection.
ANTECEDENT AND CONSEQUENCES OF CONSUMERS SATISFACTION IN ONLINE GROCERY SHOPPING
by Adinda Citra Kusuma, Mukhamad Najib, Irman Hermadi
Abstract: The rapid development of the Internet and changes in consumption patterns in Indonesia encourage consumers to shop for various products online including shopping for daily necessities such as groceries. This study aims to analyze the effect of online grocery shopping experience factors on satisfaction and the effect of consumer satisfaction on trust and loyalty. Data collection was carried out utilizing online survey of 169 respondents who had shopped online for groceries. The data were analyzed using the Structural Equation Model (SEM) Method using SmartPLS software. The analysis shows that the online shopping experience has a significant and positive influence on consumer satisfaction except variable customization and ease of return. Furthermore, consumer satisfaction has a significant and positive effect on trust and loyalty. The experience of consumers in shopping online can be used as a reference to increase satisfaction so that consumers become trustworthy and loyal.
Keywords: Consumer Satisfaction; Trust; Loyalty; Online Shopping Experience; Online Grocery Shopping.
Significant Factors Affecting M-Banking Adoption
Case Study: Higher Education Institutions in Tehran
by Masoud Ramezaninia, Farhad Panahifar, Nima Hassanzadeh Sarhangi
Abstract: The present work aims at presenting a model for examining predictors of M-banking adoption by the use of the Technology Acceptance Model and Unified Theory of Acceptance and Use of Technology model. Prior Experience added as an independent variable for the first time, while in the antecedent researches it (Experience) was used as a moderator. Also, perceived security was used as a new predictor in our model. We empirically investigated six variables affecting mobile commerce adoption in Iran, including Perceived ease of use, Perceived usefulness, Prior Experience, Perceived Usefulness, Perceived security, and Social Influence. The research data were gathered from 385 subjects in Iran and analyzed using SEM with Smart PLS. The results revealed that Prior Experience and Perceived Usefulness are the main variables affecting M-banking adoption. Merely, perceived ease of utilize was the exception that statistically showed insignificant influence on adoption of M-banking in the present work.
Keywords: Unified Theory of Acceptance and Use of Technology model (UTAUT); Iran; Technology Acceptance Model (TAM); M-banking; Mobile commerce.
Gotta buy em all? Online shopping cart abandonment among new and existing customers
by Theresa Maria Rausch, Benedikt Martin Brand
Abstract: For online retailers, sales conversions and shopping cart abandonment rates are essential measures of their success and determine their long-term performance as well as survival within the e-market. Thus, extant behavioral literature determined factors triggering online shopping cart abandonment, whereas another stream of literature explored customers online purchase behavior with real-world clickstream data. Thereby, existing research drew on different customer segmentations such as mobile versus desktop shoppers or ordinary users versus community members to identify needs of heterogeneous customer subgroups. Nevertheless, prior research still lacks a holistic understanding of online shopping cart abandonment with unbiased user generated behavior apart from prior behavioral investigations. This study hence fills a research gap by determining factors resulting in online shopping cart abandonment based on clickstream data (11,586 observations) from a leading German online retailer. Since particularly new and existing customers need to be addressed differently to be attracted, the study identifies drivers of cart abandonment separately for both segments. Like preceding research, the study uses a logit model to identify these drivers and thus, considers online shopping cart abandonment as a binary classification problem. The findings indicate that mobile shoppers exhibit a higher likelihood of abandoning their shopping cart. This relation even intensifies for new customers. For existing customers, the odds of completing the purchase decreases with every additional item in the customers shopping cart and in contrast, new customers are rather likely to abandon the shopping cart with an increasing number of shopping cart page impressions.
Keywords: online shopping cart abandonment; purchase behavior; clickstream data; customer segmentation; e-commerce; user generated behavior.
Determining the factors affecting the acceptance of social commerce in service-oriented businesses using the fuzzy Delphi method
by Nasibeh Pouti, Mohammad Taghi Taghavifard, Mohammad Reza Taghva, Mohammad Fathian
Abstract: Social commerce has emerged as a new paradigm in business and commerce for nearly a decade. The first attempt to apply this paradigm is to identify the factors affecting its acceptance studied in several research works. To achieve the purpose of the study, we conducted a systematic review of research related to the adoption and use of social media in business in the period 2010 to 2019. Based on the three stages of searching, screening and retrieving, and completing the databases, we identified 224 related studies. The confirmed factor relations in the studies were identified. By integrating synonymous factors, 228 factors were identified as influencing factors on social commerce acceptance from the users' point of view. Then, we attempted to identify the most important influential factors based on three screening stages. Finally, the experts examined the remaining factors using the fuzzy Delphi method.
Keywords: Social Commerce; Service-Based Businesses; Intention to Accept; Fuzzy Delphi.
Analysing online reviews of restaurants in Malaysia: a novel approach to descriptive and predictive analytic
by Kok Wei Khong, Shasha Teng, Mohammad Mohsin Butt, Babajide AbuBakr Muritala
Abstract: This paper aims to develop a model of restaurant products and services quality based on consumer sentiments shared on social networks. We applied term frequency-inverse document frequency (TF-IDF) weighted algorithm to generate empirical entities. These entities were incorporated into hypothetically defined constructs which reflect their thematic and sentimental nature, to test our predictive model using variance-based structural equation modelling. The results suggest that consumers have a positive attitude toward Malaysian restaurants regarding price, hospitality, location, waiting time, food variety, and restaurant atmosphere. Restaurant managers are advised to prioritise their restaurant attributes and manage key attributes to sustain and attract customers. By understanding the relative importance of restaurant reviews, restaurant managers are able to create and maintain competitive advantages in the restaurant industry, ultimately achieving customer loyalty and positive brand image.
Keywords: online reviews; text mining; unstructured data; clustering; Bayesian structural equation modelling; SEM.
The impact of payment methods and payment-related marketing communications on e-commerce retailer trust - an empirical consumer analysis of Indonesian e-commerce start-ups
by Farrah Almira Lakeman, Nadine Walter, Thomas Cleff
Abstract: The purpose of this paper is to investigate preferences of online payment methods of consumers using e-commerce websites of start-up companies in Indonesia. A quantitative online survey was used and 215 valid responses from e-commerce consumers in Indonesia were generated. The study confirms the positive impact of trust on the online purchase decision. It also reveals that convenience of online payment methods positively influences the level of trust in e-commerce start-ups. This was confirmed for access and transaction convenience. Payment-related marketing communication also proves to generate trust - information dissemination about payment methods throughout the customer journey (before the check-out) and the usage of assurance seals are particularly important.
Keywords: payment methods; e-commerce; convenience; availability; trust; communication; assurance seals; online retailer; start-up; Indonesia.
Preliminary insight into electronic commerce adoption in a developing country: evidence from Ghana
by Frederick Pobee
Abstract: Despite the barriers that have slowed electronic commerce adoption in developing countries, evidence suggests a recent surge in its adoption. This research explores the factors that influence the adoption of electronic commerce among Ghanaians. This research integrates the protection motivation theory (PMT) and the theory of planned behaviour (TPB) to propose a conceptual model. Data was collected from 920 Ghanaian university students to validate the conceptual model. Structural equation modelling (SEM) was employed to evaluate the suggested hypotheses. The findings indicate that self-efficacy, response-efficacy, attitude, subjective norms, perceived behavioural control significantly affect the behavioural intention to adopt e-commerce. Whereas perceived vulnerability, perceived severity, and response costs have insignificant effect on the behavioural intention. As a practical implication, e-vendors and website business designers should build online shopping websites that are easy to navigate, requiring less mental and physical stress from consumers.
Keywords: e-commerce; self-efficacy; subjective norm; adoption; behavioural intention; perceived vulnerability; response cost.
Promoting trust through linguistic features of provider profiles in the sharing economy
by Maarten Ter Huurne, Jonas Moons, Amber Ronteltap, Rense Corten, Vincent Buskens
Abstract: Trust between providers and consumers in the sharing economy are crucial to complete transactions successfully. From a consumer's perspective, a provider's profile is an important source of information for judging trustworthiness, because it contains multiple trust cues. However, the effect of a provider's self-description on perceived trustworthiness is still poorly understood. We examine how the linguistic features of a provider's self-description predict perceived trustworthiness. To determine the perceived trustworthiness of 259 profiles, real consumers on a Dutch sharing platform rated these profiles for trustworthiness. The results show that profiles were perceived as more trustworthy if they contained more words, more words related to cooking, and more words related to positive emotions. Also, a profile's perceived trustworthiness score correlated positively with the provider's actual sales performance. These findings indicate that a provider's self-description is a relevant signal to consumers, even though it seems easy to fake.
Keywords: sharing economy; trust; perceived trustworthiness; linguistic inquiry and word count; LIWC; linguistic features; C2C.
Special Issue on: Knowledge Management and Data Representation in Network Sciences
Distracted driver recognition system using deep forest
by Moolchand Sharma, Ananya Bansal, Utkarsh Agrawal, Pramod Goyal
Abstract: The World Health Organization (WHO) reported around 1.25 million yearly deaths due to road traffic accidents, and the number has been continuously increasing over the last few years. We need to develop an accurate system for detecting distracted drivers and warn them against it. Distracted driving is an ongoing problem that seems only to be getting worse with the dependence on technology. We have used a novel approach, i.e., deep forest, which is a recently researched algorithm, developed as an alternative to deep learning models based on neural networks. We aim to implement deep forests for classification and to compare the results with other techniques. Experimental results shows that the system outperforms well, and achieving an accuracy of 96.75 with DeepForest. The success of the models will, hopefully, one day, aid combat the ongoing and increasing issue of distracted drivers on the roads.
Keywords: convolution neural network; deep forest; decision trees; ensemble-based; non-differentiable; deep learning.
Special Issue on: Intelligent Security using Blockchain for Internet of Things
Security Framework for IoT and Deep Belief Network based Healthcare System using Blockchain Technology
by Senthil Murugan Nagarajan, Prathik Anandhan, Muthukumaran V, Uma K, Kumaran U
Abstract: Nowadays, the computerization and information systems need a very fast, easier and secure data analysis models. So, Blockchain technology and Deep learning concepts plays an important role for data security and analysis in field of healthcare applications. Blockchain technology has optimal reliability in various sectors like healthcare, security, information management, smart home etc. In this paper, Blockchain technology is used for healthcare system to provide a secure and reliability of data transmission. Furthermore, IoT based wearable devices are used to collect the data from the patients. Moreover, Deep Belief Network (DBN) is proposed to classify the obtained data in order to predict the type of disease or problems for patients. The experimental results shows that the proposed framework and classification model abruptly outperforms when compared with other existing techniques. The efficiency of the proposed framework is analysed based on the performance metrics like throughput and latency. The loss ratio for the proposed model seems obtain very less of 0.0126 when compared with other existing techniques like MLP, SVM, ANN, and CNN. The accuracy obtained for the proposed DBN classifier is above 95% for the increase in the number of patients.
Keywords: Blockchain Technology; Healthcare System; Internet of Things (IoT); Deep Belief Network (DBN); Security.
RPL enhancement with mobility aware two stage objective function for improving network lifetime in IoT
by Robin Cyriac, Saleem Durai MA
Abstract: The routing protocol for low power and lossy network (RPL) has tremendous scope in IoT, due to the fact that it can be customized as per networks domain requirement by altering Objective Function (OF). Many studies have proven that the careful crafting of OF with different metrics improve the quality of route identified by RPL. As the complexity of OF increases due to different metric combinations, the performance of RPL will start to deteriorate. We divide OF into a two stage process to solve this problem. In the first stage we keep a simple OF that considers ETX and path delay and rank parents as per RPL specification. A fixed number of best ranked parents from the first stage OF are considered for further processing in the second stage OF. Fuzzy based second stage OF considers mobility history, queue availability and remaining energy of the parents to select the preferred route. Second stage OF is run only on limited number of parents which improves performance of RPL. Performance evaluation shows that our Two Stage Objective Function (TS-OF) reduces packet loss by 28% and energy consumption by 34% compared to the state of the art RPL objective function. \r\n
Keywords: IObjective Function; RSSI; Energy consumption; Parent selection mechanism; RPL; IoT
A Markov Decision Process based Secure Consensus Framework for Leveraging Blockchain Technology in IoT Applications
by Nonita Sharma, Monika Mangla, Sachi Nandan Mohanty
Abstract: In this manuscript, we propose a secure consensus framework that implements Markov Decision Process (MDP) for blockchain technology in IoT applications. The proposed framework presents projection for the sojourn time and stationary efficiency measures for any transaction or block. Implementing MDPs provides a group of states and a collection of actions to choose from. MDP also offers instantaneous reward purpose and a probabilistic transition matrix. The proposed framework that suggest implementation of MDP in blockchain technology further escalates the security of the network. The paper demonstrates the architecture of the proposed framework.
Keywords: blockchain; bitcoin; byzantine faults; consensus; distributed ledger; smart contract; markov decision process.
Blockchain-based consensus algorithm for solving security issues in distributed internet of things
by Bhabendu Kumar Mohanta, Kalpana Samal, Debashish Jena, Somula Ramasubbareddy, Marimuthu Karuppiah
Abstract: In the last decade internet of things (IoT) emerged as one of the most promising fields of research. The services provided by the IoT have come as a big relief to human life due to the smartness and real-time monitoring without human intervention. IoT applications are widely used as it provides a high level of comfort, automation of the system, and efficiency. To make successful use of ever-growing IoT applications requires addressing the security, privacy, and trust to protect IoT devices and user privacy from attackers. In this paper, initially different security and privacy challenges are identified in an IoT application. Secondly, analysis regarding blockchain technology is done which gives the idea to solve some of the IoT security challenges. Blockchain-based consensus algorithm PBFT is used to perform secure computation in a smart transportation system. Security analysis shows
that the proposed protocol worked correctly in presence of malicious or faulty nodes.
Keywords: internet of things; IoT; security; privacy; blockchain; consensus algorithms; distributed system; trust management.
Special Issue on: Intelligent Virtual Networks and Applications
Smart resource scheduling by correlating discriminative quality factors to optimise resource utilisation in IAAS of cloud networks
by Bellam Ravindra Babu, Aliseri Govardhan
Abstract: The significant requirement in cloud computing is detecting the deterministic model for performing resource scheduling. Resource scheduling is crucial because of several anomalies presence and high dimensionality values shown during resource scheduling. The number of tasks envisioned in contention at resource broker of IAAS and higher dimensionality of proposed anomalies values for quality resource aspects was out of scope concerning the existing resource scheduling techniques. Therefore, the contemporary resource scheduling techniques were not prominent for optimal resource scheduling. For optimising resource scheduling in terms of earlier mentioned properties like the maximum amount of tasks and maximum dimensionality anomalies projection, an ensemble resource scheduling technique has been derived in this article under batch scheduling classification. Further, the simulation study envisioned that the projected model of this contribution is more significant and robust for delivering optimum resource scheduling when compared to other contemporary models in terms of dimensionality and volume of anomalies.
Keywords: resource scheduling; VM migration; virtual machines; VMs; QoS; cloud computing; resource management.