Customer Churn in Retail E-Commerce Business: Spatial and Machine Learning Approach

This study is a comprehensive and modern approach to predict customer churn in the example of an e-commerce retail store operating in Brazil. Our approach consists of three stages in which we combine and use three different datasets: numerical data on orders, textual after-purchase reviews and socio-geo-demographic data from the census. At the pre-processing stage, we find topics from text reviews using Latent Dirichlet Allocation, Dirichlet Multinomial Mixture and Gibbs sampling. In the spatial analysis, we apply DBSCAN to get rural/urban locations and analyse neighbourhoods of customers located with zip codes. At the modelling stage, we apply machine learning extreme gradient boosting and logistic regression. The quality of models is verified with area-under-curve and lift metrics. Explainable artificial intelligence represented with a permutation-based variable importance and a partial dependence profile help to discover the determinants of churn. We show that customers’ propensity to churn depends on: (i) payment value for the first order, number of items bought and shipping cost; (ii) categories of the products bought; (iii) demographic environment of the customer; and (iv) customer location. At the same time, customers’ propensity to churn is not influenced by: (i) population density in the customer’s area and division into rural and urban areas; (ii) quantitative review of the first purchase; and (iii) qualitative review summarised as a topic.

Decision-Making Strategy for Digital Transformation: A Two-Year Analytical Study and Follow-Up Concerning Innovative Improvements in University e-Services

Universities worldwide strive to provide the best student services possible, particularly those that support student achievements and career goals. Therefore, academic advising continues to be a significant part of the student experience, one which universities need to fully understand in terms of its objectives, application processes, and required skill. As a result of significant technological improvements since the turn of the millennium, including expanding internet applications and digital transformations, universities have established computer information systems that support academic advising and course registration services. This study examined the effects of modifications to the electronic academic advising and course registration systems at King Abdulaziz University in 2018, and then again in 2020, following a university-wide system failure in 2018 resulting from a demand overload. In 2018, a preliminary statistical analysis and student feedback survey were conducted by the authors to measure student satisfaction with the online portal On-Demand University Services (ODUS Plus). In addition to recommendations suggested by the 2018 analysis such as balancing the load distribution of the university’s network, organizational (i.e., non-technical) solutions, rules, and regulations were adjusted such as progressive course registration that prioritized those expected to graduate first. The survey and analysis were repeated by the authors in 2020 to assess improvements in student satisfaction. As a result of the changes, the investigation revealed improved student satisfaction with the performance of ODUS Plus and network access. Overall, students were significantly more satisfied in 2020 than in 2018. This research shows that some technical challenges can be resolved using re-engineered processes and organizational solutions.

Antecedents of Online Impulse Buying: An Analysis of Gender and Centennials’ and Millennials’ Perspectives

Impulse buying continues to be a relevant topic for retail management, yet few studies have examined the role of online impulse buying. This study analyzes the effect of impulse buying tendency on online impulse buying behavior through the mediation of normative evaluation and the urge to buy impulsively on the Internet. As a secondary objective, we aim to identify whether gender and generation influence the model. The research was conducted in Mexico with millennials and centennials who had previously bought products on the Internet. We used quantitative, explanatory, non-experimental, cross-sectional research. We applied an electronic survey, and, for the statistical technique, we used PLS. According to the results, impulse buying tendency both directly and indirectly influences online impulse buying behavior through the mediating roles of normative evaluation and the urge to buy impulsively on the Internet. Moreover, we found that gender does not have an effect on the model. Regarding generation, two significant differences were found between centennials and millennials.

Investigating the Impact of Situational Influences and Social Support on Social Commerce during the COVID-19 Pandemic

Without question, 2020 was an unprecedented period for all businesses and consumers in the world, especially for social commerce businesses. Growing online shopping during the pandemic has proliferated the appetite of social commerce websites. Drawing on the situational influences’ theory and social support theory, the purpose of this study was to investigate the impact of situational influences during the COVID-19 pandemic on online purchase intention across the big five personality traits. The data were collected via online survey. The sample consisted of 349 social commerce website users in the UK. The model was tested using Partial Least Squares-Structured Equation Modelling (PLS-SEM). The results showed the different cohorts of buying intention on social commerce websites. Social support does not impact online purchase intention, while other situational factors do. Moreover, the model varied across the big five personality traits. The study substantially contributes to social commerce by investigating the social support and situational influences across different types of personality traits on online purchase intention during the pandemic.

What Makes GO-JEK Go in Indonesia? The Influences of Social Media Marketing Activities on Purchase Intention

This research examines the relationship between social media marketing activities and purchase intention mediated by trust and brand image to confirm the constructs with practical applicability, specifically in a growing online ride-hailing service company. This study employs a quantitative approach with a causal research design to test the proposed hypotheses to identify interrelationships between each pair of constructs. Data collection was performed through a survey of 350 respondents via an online questionnaire as the primary data source distributed to social media users in Indonesia who had experienced using GO-JEK services. In addition, EFA, CFA, SEM, and bootstrapping methods were run to analyze these research data. Social media marketing, trust, and brand image affect consumers’ purchase intention significantly. Among the five dimensions of social media marketing, the findings show that two dimensions—namely, entertainment and word of mouth, bring the most significant direct effect on purchase intention. Trust and brand image mediate the relationship between social media marketing and purchase intention. This study suggests practical directions for organizations. First, it reveals the social media dimensions that directly encourage purchase intention among consumers. Second, it explains that trust and brand image can amplify each variable’s influence on the purchase intention among consumers. GO-JEK is an example of the online ride-hailing industry that causes the generalizability issue in different business contexts. Based on our findings, there are some practical directions for GO-JEK. First, it reveals the social media marketing dimensions that directly encourage purchase intention among consumers to use GO-JEK. Second, it explains that trust and brand image can amplify the influence of each variable on consumers’ purchase intention. Very few studies investigated social media marketing’s role in a GO-JEK business model in the Indonesian context. This research delivers in-depth insights into the significant factors that affect Indonesian consumers to decide which product they intend to buy through the influence of social media activities.

A Cluster Analysis Concerning the Behavior of Enterprises with E-Commerce Activity in the Context of the COVID-19 Pandemic

The planning of activities of e-commerce enterprises and their behavior has been influenced by the emergence of the COVID-19 pandemic. The behavior of e-commerce enterprises has been highlighted at the level of EU countries through an analysis elaborated on four variables: the value of e-commerce sales, cloud computing services, enterprises that have provided training to develop/upgrade the ICT skills of their personnel, e-commerce, customer relationship management (CRM) and secure transactions. Using the hierarchical clustering method, analysis was carried out on these variables to identify certain economic and behavioral patterns of e-commerce activity from 2018 and 2020. The study of the relationships involved in the e-commerce activity of these enterprises is reflected in models of the economic behavior of 31 European states in relation to the targeted variables. The results show that the impacts of the COVID-19 pandemic are strongly manifested in the direction of the evolution of each indicator but differ from one country to another. The trends depend on the level of development and the particularities of each country’s economy in adapting to the repercussions reported in relation to the level of impact of the COVID-19 pandemic. This is highlighted by the significant regrouping of countries in 2020 compared with 2018 in relation to the average values of the indicators. The results show that, in 2020, the most significant percentages of the value of e-commerce sales were recorded in Belgium, Ireland and Czechia, as in 2018. In e-commerce, customer relationship management and secure transactions, Denmark and Sweden were superior in 2020 to the countries mentioned above, which were dominant in 2018. For the other two indicators, Finland and Norway were the top countries included in the analysis in both years. The conclusion supports the continuous model of e-commerce enterprise behavior in order to meet the requirements of online customers.

Cross-Border E-Commerce Development and Challenges in China: A Systematic Literature Review

This paper reviews the primary scientific articles applicable to the logistics industry, and specifically those relating to cross-border e-commerce in China. The authors focused on reviewing the articles about the current status of cross-border e-commerce in China and the factors affecting its development, with the aim of highlighting literature gaps. The authors used a systematic literature review (SLR) to identify, gather, and analyze 60 primary papers selected from international peer-reviewed journals and international conference proceedings between 2001 and 2020. Chinese cross-border e-commerce has experienced a trend of steady progress, although several challenges remain. These challenges include, but are not limited to, low custom clearance efficiency, complex monitoring and supervision, tax rebate settlement challenges, payment risks, insufficient talent within the Chinese industry, and the lack of scientific management guidelines. The significant contributions of this paper include critical highlights of the current gaps and future research themes.

A Literature Review of Taxes in Cross-Border Supply Chain Modeling: Themes, Tax Types and New Trade-Offs

The e-commerce platforms have facilitated the information flow of cross-border supply chain (CBSC) and attracted a wide range of companies and individuals to participate in cross-border businesses. The tax costs associated with cross-border commodity flow have received unprecedented attention. However, there is a lack of common platforms between international tax planners and CBSC optimizers, and the impact of various tax policies on CBSC operations is still unclear. To fill this gap, this study presents a literature review to elaborate on the interface between taxes and CBSC operations. First, a literature collection approach is constructed, and 71 pertinent publications are identified. Then, a four-dimensional categorization consisting of supply chain themes, research methodologies, tax types, and illustration types was designed to classify and summarize the research content of the selected articles. The results show that (1) there are six main supply chain-related themes, i.e., the supply chain network, the distribution channel structure, product quantity and quality, production outsourcing, the procurement mode, and supply chain emissions, that are significantly affected by taxes. (2) Four types of taxes, including the corporate income tax (CIT), tariffs, environmental taxes and the value-added tax (VAT), have obvious impacts on CBSC operations. (3) Four mainstream methodologies, i.e., mathematical models, empirical models, conceptual models and simulation models, have been applied to explore the tax effects in CBSC modeling. (4) The tax-saving opportunities in CBSC operations mainly come from the following five areas: CIT rate gaps in different regions, special tax regulations such as the tax cross-credit principle and arm’s length principle, regional trade agreements (RTAs), preferential tax policies and export VAT rebate policy. Finally, this research provides a framework to analyze the trade-offs between taxes and traditional CBSC modeling factors. The results can support enterprises in CBSC in dealing with the complex international tax policies.

Sentiment Analysis of Review Data Using Blockchain and LSTM to Improve Regulation for a Sustainable Market

E-commerce has developed greatly in recent years, as such, its regulations have become one of the most important research areas in order to implement a sustainable market. The analysis of a large amount of reviews data generated in the shopping process can be used to facilitate regulation: since the review data is short text and it is easy to extract the features through deep learning methods. Through these features, the sentiment analysis of the review data can be carried out to obtain the users’ emotional tendency for a specific product. Regulators can formulate reasonable regulation strategies based on the analysis results. However, the data has many issues such as poor reliability and easy tampering at present, which greatly affects the outcome and can lead regulators to make some unreasonable regulatory decisions according to these results. Blockchain provides the possibility of solving these problems due to its trustfulness, transparency and unmodifiable features. Based on these, the blockchain can be applied for data storage, and the Long short-term memory (LSTM) network can be employed to mine reviews data for emotional tendencies analysis. In order to improve the accuracy of the results, we designed a method to make LSTM better understand text data such as reviews containing idioms. In order to prove the effectiveness of the proposed method, different experiments were used for verification, with all results showing that the proposed method can achieve a good outcome in the sentiment analysis leading to regulators making better decisions.

Exploring the Moderating Role of Readers’ Perspective in Evaluations of Online Consumer Reviews

Drawing upon the heuristic–systematic model (HSM) and considering the readers’ perspective, this study predicts that readers’ involvement and homophily between the reader and the review author (source) moderate the relationships between the credibility perception of online reviews and its antecedent factors. To test our hypotheses, we performed a user study on the Amazon Mechanical Turk platform. The results show that reader’s involvement moderates source credibility, internal consistency, review objectivity, and review sidedness on review credibility. In addition, homophily between the reader and the source also moderates the relationship between review credibility and its source. Our study contributes to information processing literature, especially in the context of online reviews, and suggests a better classification of the attributes related to online reviews using the HSM. Besides, it helps e-commerce platforms to customize online reviews for each reader to satisfy their information need and help them to make a better purchasing decision.