Search results

Product returns are a major challenge for e-businesses as they involve huge logistical and operational costs. Therefore, it becomes crucial to predict returns in advance. This study aims to evaluate different genres of classifiers for product return chance prediction, and further optimizes the best performing model.

An e-commerce data set having categorical type attributes has been used for this study. Feature selection based on chi-square provides a selective features-set which is used as inputs for model building. Predictive models are attempted using individual classifiers, ensemble models and deep neural networks. For performance evaluation, 75:25 train/test split and 10-fold cross-validation strategies are used. To improve the predictability of the best performing classifier, hyperparameter tuning is performed using different optimization methods such as, random search, grid search, Bayesian approach and evolutionary models (genetic algorithm, differential evolution and particle swarm optimization).

A comparison of F1-scores revealed that the Bayesian approach outperformed all other optimization approaches in terms of accuracy. The predictability of the Bayesian-optimized model is further compared with that of other classifiers using experimental analysis. The Bayesian-optimized XGBoost model possessed superior performance, with accuracies of 77.80% and 70.35% for holdout and 10-fold cross-validation methods, respectively.

Given the anonymized data, the effects of individual attributes on outcomes could not be investigated in detail. The Bayesian-optimized predictive model may be used in decision support systems, enabling real-time prediction of returns and the implementation of preventive measures.

There are very few reported studies on predicting the chance of order return in e-businesses. To the best of the authors’ knowledge, this study is the first to compare different optimization methods and classifiers, demonstrating the superiority of the Bayesian-optimized XGBoost classification model for returns prediction.

This study aims to investigate the connection between the circular economy and sustainable operations management to identify the challenges and opportunities in platform organizations. The study looks at how the stated circular economy strategies (Reduce, Reuse, Repair, Refurbish, Repurpose and Recycle) are integrated across different industries, emphasizing how they align with the e-business model. The research evaluates their contribution to achieving Sustainable Development Goal 12, which focuses on responsible consumption and production.

A literature review has analyzed CE frameworks, business models and the role of sustainable operations management practices. This study utilized secondary data analysis of platform organizations and insights from case studies to identify patterns, strategies and outcomes. The study also involved practical examinations within organizations, specifically focusing on innovative start-ups.

The analysis uses the 6R framework (Reduce, Reuse, Repair, Refurbish, Repurpose and Recycle) to uncover valuable insights into organizational practices and highlight the role of platform organizations in promoting and achieving circular economy objectives. The research findings focus on the central importance of data regulation and governance while showcasing sustainable business practices through platform organizations.

This research is significant as it connects circular economy with platform organizations’ business models, emphasizing data regulation, resource efficiency, waste reduction and aligning business practices with Sustainable Development Goal 12.

This paper aims to analyze the factors that affect the attitudes of Armenian small and medium enterprises (SMEs) regarding digitalization, examining whether they view it as a tool to foster innovation and business growth, while also assessing the extent to which digitalization mitigated the negative impacts of the COVID-19 crisis.

The empirical approach is based on data collected from 452 Armenian SMEs, which were further analyzed using SPSS Statistics 23.0 software. Scales for assessing the COVID-19 impact, innovation and digitalization were constructed and validated. To test five hypotheses, binomial logistic regression was conducted to appraise the importance of digitalization for Armenian SMEs, including the ability to mitigate the consequences of the recent COVID-19 pandemic.

The results of the analysis showed that the economic sector plays a significant role in forming the expectations of firms on the positive impact of digitalization, while the company size does not affect them. This paper found that the provision of online services before the pandemic did not help Armenian SMEs to be less affected by the crisis. Furthermore, the perception of whether digitalization facilitated innovative processes, products and services did not depend on the degree of being affected by COVID-19. Finally, the findings indicate that the more agile companies which had the ability to convert their business model into an e-business model were less affected by the crisis.

This paper contributes to the literature by studying the effect of digitalization on SMEs, as well as how SMEs in small developing countries like Armenia mitigated the negative effects of the COVID-19 pandemic. The current work is unique as, to the best of the authors’ knowledge, there are no prior empirical studies focusing on impact of digitalization and innovation induced by exogenous shocks in an under-researched country like Armenia.

This paper aims to analyse the unified theory of acceptance and use of technology (UTAUT) and UTAUT2 constructs used in research on information and communication technology (ICT) adoption and use among micro, small and medium enterprises (MSMEs) in non-organisation for economic co-operation and development (OECD) countries. It also investigates the areas of ICT adoption along the value chain in studies using these constructs.

Systematic literature review (SLR) was conducted, where 910 studies were retrieved manually in five academic databases. Forty-eight studies were finalised after four filtration levels.

Majority of the studies were published within the past six years, and 85.42% were studies in the form of journal papers. UTAUT constructs more researched compared to UTAUT2 constructs. More than half of the studies investigated ICT application in value chain boundaries, while 16 studies were organisation-wide studies.

With developments in MSMEs’ technology, the UTAUT2 model must be expanded to internal company operations including finance and infrastructure maintenance. To boost competitiveness and productivity, non-OECD authorities should focus on the cost and user-centric characteristics of MSMEs’ technology adoption.

Although SLRs on UTAUT and UTAUT2 constructs have been attempted previously, this study contributes to the body of knowledge by focusing analysis on the application of those constructs on MSMEs in non-OECD countries and also by situating ICT adoption along the value chain of enterprises.

India has witnessed a significant surge in internet users in recent years, creating an ideal environment for E-entrepreneurship. With the rise of E-commerce and the growth of the digital economy, there is tremendous potential for online businesses in developing nations. Our study outlines the behavioral, cognitive, and environmental aspects shaping students' E-entrepreneurial intentions (EEI).

Our study incorporated structural equation modeling (SEM), social cognitive theory (SCT), and entrepreneurial event model (EEM) to evaluate the EEI of 460 students from India's top five engineering institutes. The direct and indirect linkages in the model were examined by employing mediation and moderation analysis.

Our findings reveal that behavioral, environmental, and cognitive factors facilitate evaluating feasibility, further igniting students' EEI. The cognitive factors and E-entrepreneurial feasibility (EEF) mediate the relationship between the underlying constructs. Furthermore, financial resource availability (FRA) strengthens, and loss aversion bias(LAB) weakens the linkage between EEF and EEM.

The study's findings may benefit online innovation communities, potential technopreneurs, financial institutions, and policymakers in improving the entrepreneurial ecosystem.

The study integrates psychological and sociological perspectives to understand the key facilitators of EEF and EEI. The study combines SCT and the EEM by appending crucial constructs such as FRA and LAB to broaden the horizons of EEI.

With the advancement of digital transformation, it is important for e-retailers to use artificial intelligence (AI) for customer engagement (CE), as CE enables e-retail brands to succeed. Essentially, AI e-marketing (AIeMktg) is the use of AI technological approaches in e-marketing by blending customer data, and Retail 4.0 is the digitisation of the physical shopping experience. Therefore, in the era of Retail 4.0, this study investigates the factors influencing the use of AIeMktg for transforming CE.

The primary data were collected from 305 e-retailer customers, and the analysis was performed using a quantitative methodology.

The results reveal that AIeMktg has tremendous applications in Retail 4.0 for CE. First, it enables marketers to swiftly and responsibly use data to anticipate and predict customer demands and to provide relevant personalised messages and offers with location-based e-marketing. Second, through a continuous feedback loop, AIeMktg improves offerings by analysing and incorporating insights from a 360-degree view of CE.

The main contribution of this study is to provide theoretical underpinnings of CE, AIeMktg, factors influencing the use of AIeMktg, and customer commitment in the era of Retail 4.0. Subsequently, it builds and validates structural relationships among such theoretical underpinning variables in transforming CE with AIeMktg, which is important for customers to expect a different type of shopping experience across digital channels.

By focusing on the contextual conditions of South African digital entrepreneurs and the affordances of digital technologies, we understand how connective affordances of digital technologies enable a collective approach to digital entrepreneurship.

We do so through an interpretive field study of South African digital entrepreneurs operating in resource-constrained settings.

The findings highlight how entrepreneurs appropriate digital technologies in collectives to achieve connective actions and cooperate and compete simultaneously, giving rise to what we call coopetitive affordance, reflecting a fresh perspective on coopetition in increasingly digital and resource-constrained realities.

This paper extends the connective affordance perspective by illustrating how the concept of coopetitive affordance brings to light how contextual conditions create a humanitarian bond between entrepreneurs and a digital bond created by their appropriation of digital technologies in collectives.

Instant crowdsourcing logistics (ICL) platform is an emerging business model in the field of logistics services. Crowdsourcees’ active participation in platform value co-creation is the key to success for this business model. This study aims to explore the influence of platform governance mechanisms on crowdsourcees’ participation in value co-creation on the platform.

Based on governance theory, this study constructed a model of the influence of platform governance mechanisms on crowdsourcees’ value co-creation intentions and discussed the role of community diversity in this model. The survey data of 319 collected from crowdsourcees on China’s well-known ICL platform were analyzed using a partial least squares structural equation model.

The results showed that platform governance mechanisms have a significant influence on crowdsourcees’ value co-creation intentions. Among them, the impact of the welfare resource support mechanism is the largest, followed by the reputation reward and punishment mechanism, while the price coordination mechanism has the least impact. Community diversity has a significant positive moderating effect on the welfare resource support mechanism and crowdsourcees’ value co-creation intentions, but not between other governance mechanisms and crowdsourcees’ value co-creation intentions.

The results provide references for ICL platform to develop a targeted governance mechanism to enhance the positive role of community diversity and reduce the negative impact.

The purpose of the study is to examine the relevance and application of green communication in management of the risks associated with moral outrage inducing crises. The study aims to identify how green communication mitigates both crisis risks and moral outrage. Additionally, the research discusses ethical and unethical green communication practices in the context of their impact on relationships between organizations and stakeholders during the crisis.

The study is designed as exploratory research. Available English-language journal articles and conference proceedings have been examined to investigate the role of green communications in crisis response contexts. The application of the search criteria and initial filtering yielded a total of 139 publications for further analysis. Following a detailed review and subsequent filtering, the final sample of 66 unique cases has been selected and analyzed in the context of Situational Crisis Communication Theory.

The systematic review and document analysis indicated multitude of significances of green communications in the context of the updated Situational Crisis Communication Theory. Moreover, a novel phenomenon has been identified: greenbleaching is exaggerated or fabricated usage of green communication to mitigate risks in the organizational crises caused by ESG-unrelated factors or events.

This study offers greenbleaching as a novel concept. Moreover, this is the first research that examines unethical green communication in the context of moral outrage inducing crises. Insights for researchers and practitioners regarding sustainability communication, green communication, and crisis communication ethics are also incorporated.

This chapter critically discusses the literature on the subject of circular economy. It defines the circular economy at the outset and advocates its adoption in smart cities. It briefly explains the multiple phases of industrial revolution and the slow and gradual shift from a linear economy which is based on make-use-dispose model to a circular economy which relies on reusing and recycling the products produced in the production cycle. It then critically examines the legal challenges that can be associated with such a system. It draws on the lessons learnt from cities such as Amsterdam which has successfully implemented the system of circular economy. This chapter also delves into the Columbian waste management system to understand the market functioning in the waste management sector which is handled by private enterprises in the country. Moreover, the public–private partnership model in the Chinese city Suzhou is explored, and exciting methods of using this model were found.