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.

The purpose of this study was to examine racial/ethnic differences in AFS use and their contributing factors using a decomposition analysis.

The 2018 National Financial Capability Study dataset was used to analyze the four major types of AFS—title loans, payday loans, pawnshops, and rent-to-own (RTO) stores—as proxies for AFS use. The study conducted both logistic regression analysis and decomposition analysis to examine the contributing factors.

The results of the logistic regression analysis demonstrated significant disparities in the use of alternative financial services (AFS) among racial and ethnic groups. Specifically, it was found that Blacks were more likely to utilize title and payday loans, pawnshops, and rent-to-own (RTO) stores compared to Whites. In contrast, Hispanics and Asians/individuals of other ethnicities were less likely to use title loans, but Hispanics were more likely to opt for payday loans over Whites. Furthermore, objective financial literacy exhibited a negative association with the likelihood of using these four types of AFS, whereas subjective financial literacy consistently showed a positive association. When examining the decomposition analyses, it became evident that both objective and subjective financial literacy played significant roles in explaining the racial and ethnic disparities in AFS usage. However, the patterns varied in three specific pairwise comparisons.

This study revealed the relative contributions of each factor to the racial/ethnic disparities through decomposition analysis. Our Fairlie decomposition approach addressed non-linearities within the decomposition framework, particularly in estimating the probabilities of AFS utilization, given its binary outcomes. This extension builds upon the Oaxaca decomposition. The study offers valuable insights into the variations in AFS use among different racial and ethnic groups.

We examine the relationship between macroeconomic news and fund price jumps, using high-frequency 5-min intraday data for Exchange Traded Funds (ETFs) and Listed Open-end Funds (LOFs) from 2019 to 2020.

We utilize the non-parametric jump test known as the LM method to detect fund price jumps. In addition, we perform Logistic regression to analyze the relationship between macroeconomic news and fund price jumps. Moreover, we use multiple linear regression to explore the relationship between fund price jumps and subsequent returns.

The probability of price jumps increases by 22.56% when macroeconomic news is released. Moreover, the returns associated with news-driven price jumps display a reversal pattern, and there is an asymmetric relationship in subsequent returns following macroeconomic shocks. Specifically, funds tend to exhibit lower returns after news-driven price jumps compared to those that are not influenced by news events.

In today's digital age, investors have unprecedented access to a wealth of information through the Internet and various communication platforms. News and market data can be instantly accessed and disseminated, allowing for swift dissemination of information to investors worldwide. However, despite this enhanced accessibility, investors continue to exhibit overreactions or underreactions to new information.

Macroeconomic news release provide crucial insights into the overall health and performance of the economy. By monitoring and analyzing these indicators, investors can gain valuable information that can guide their investment decisions. Furthermore, by fostering a transparent and reliable information disclosure systems, governments can play a critical role in ensuring the stability and transparency of the funds market.

The paper utilizes 5-min high-frequency data from funds and incorporates a comprehensive macroeconomic news information database. These methodological choices enhance the precision and reliability of the analysis, allowing for a more nuanced understanding of the relationship between macroeconomic news releases and fund price jumps.

This paper aims to identify the determining factors for the financial performance (FP) of social enterprises in an emerging country, in this case Brazil.

This paper identifies the determinants of the FP of social enterprises in Brazil using the resource-based view as a theoretical lenses and the quantitative method (n = 601) of logistic regression, analyzing the importance of nine variables related to SEs.

The findings refer to practical contributions (which show how SEs should focus and allocate their resources to maximize FP) and theoretical contributions linked to entrepreneurship literature (by differentiating the results of this work from the literature on commercial entrepreneurship in terms of resources), social entrepreneurship literature (by presenting the resources that determine their FP), business literature, entrepreneurial finance and entrepreneurship in emerging economies.

This work represents a novelty from a methodological point of view, filling the gap regarding the lack of studies that apply a quantitative methodology to a large sample and analyze several different variables when most studies analyze only one factor related to the performance of an organization. It also fills the gap in entrepreneurship studies that use some theoretical lenses. This work is also a pioneer in analyzing the variables involved, such as market orientation, technologies and impact measurement in social entrepreneurship. As this work uses data from a secondary sample, there is the limitation of not choosing the analyzed variables. Even though there were many variables in the sample, it was impossible to consider some variables, referring to various aspects of resources and performance. For this same reason, the social performance of SEs, which is of fundamental importance within the objectives of any organization of this type, was not analyzed and may be a suggestion for future work.

This study aims to find the key drivers of green innovation in family firms by examining firm characteristics and geographical factors. It seeks to develop a conceptual framework that explains how internal resources and external environments influence environmental innovation practices in these businesses.

Using machine learning (ML) methods, this study develops a predictive model for green innovation in family firms, drawing on data from 3,289 family businesses across 27 EU Member States and 12 additional countries. The study integrates the Resource-Based View (RBV) and Location Theory to analyze the impact of firm-level resources and geographical contexts on green innovation outcomes.

The results show that both firm-specific resources, such as size, digital capabilities, years of operation and geographical factors, like country location, significantly influence the likelihood of family firms engaging in environmental innovation. Larger, technologically advanced firms are more likely to adopt sustainable practices, and geographic location is crucial due to different regulatory environments and market conditions.

The findings reinforce the RBV by showing the importance of firm-specific resources in driving green innovation and extend Location Theory by emphasizing the role of geographic factors. The study enriches the theoretical understanding of family businesses by showing how noneconomic goals, such as socioemotional wealth and legacy preservation, influence environmental innovation strategies.

Family firms can leverage these findings to enhance their green innovation efforts by investing in technology, fostering sustainability and recognizing the impact of geographic factors. Aligning innovation strategies with both economic and noneconomic goals can help family businesses improve market positioning, comply with regulations and maintain a strong family legacy.

This research contributes a new perspective by integrating the RBV and Location Theory to explore green innovation in family firms, highlighting the interplay between internal resources and external environments. It also shows the effectiveness of machine learning methods in predicting environmental innovation, providing deeper insights than traditional statistical techniques.

The aim of this research is to elucidate the correlation between open innovation, digital strategies and networking in enhancing agricultural enterprises within the new perspective of Agrifood 5.0. As such, it contributes to making businesses more competitive, especially in the Italian agricultural sector, where small and medium-sized enterprises are highly fragmented. Numerous studies have asserted that the competitiveness of actors operating within a specific territory is closely linked to local identity and image enhancement. Agricultural organizations are undergoing a profound transformation, with technological assets emerging as catalysts for new synergies. Advanced technologies such as robotics, the Internet of Things (IoT) and automation (AI) are emerging as differentiating elements capable of further advancing the agricultural sector, transitioning it from Agrifood 4.0 to Agrifood 5.0. The empirical analysis of the research shows a positive correlation between a collaborative attitude and a propensity for innovation. Indeed, the data demonstrated that digital strategies and open innovation positively influence competitiveness in agricultural SMEs.

The methodology employed in this study is mixed, incorporating both qualitative and quantitative approaches. The quantitative aspect involves analysis of the dataset from the Italian Statistical Institute (ISTAT) through logistic regression, while the qualitative component entails analysis of semi-structured interviews conducted with a sample of 174 agricultural cooperatives in southern Italian regions (Campania). This approach allows for a comprehensive understanding of the research topic, capturing both numerical trends and nuanced insights from interviews.

After analyzing the data from the 7th General Census of Agriculture conducted by ISTAT, a clear understanding of the sector has emerged, revealing several potential research avenues. It is evident that innovation in the agricultural sector is often driven by the largest and best-capitalized production entities, primarily located in Italy. Conversely, smaller agricultural entities can benefit from networking as new technological assets act as catalysts for new synergies, innovation and competitiveness.

Enhancing the relational contribution within the network and humanizing a fragmented sector are crucial elements for promoting open innovation. Network structuring facilitates the transmission of managerial knowledge, contributing to an overall increase in the intellectual and relational capital of the agricultural sector. These factors, combined with open innovation, enhance the competitiveness of individual firms and elevate the brand of the entire sector, creating a conducive environment for transitioning toward Agrifood 5.0. This transition is characterized by increased interconnection, continuous innovation and overall prosperity. Specific studies on this topic are lacking in Italy, particularly in the southern regions. Therefore, this contribution focuses on investigating the Campania region.

The novelty of this study lies in its investigation of the relationship between agricultural enterprises and innovation in the context of enterprises networking strategies (i.e. associationism and/or cooperation), promoting competitiveness. The limitations of this study are related to the dimension of the sample selected and its relationship with other productive sectors.

As many businesses faced economic disruption due to the Covid-19 pandemic and sought financial relief, existing bank relationships became critical to getting a loan. This study examines factors associated with the development of personal relationships of rural small businesses with community bank representatives.

We applied a mixed-method approach. We employed descriptive statistics, principal factor analysis and logistic regression for data analysis. We distributed an online survey to rural small businesses in five states in the United States. Key informant interviews with community bank representatives supplemented the survey results.

A business owner’s trust in a banker was positively associated with the establishment of a business–bank relationship. However, an analysis of individual trust’s components revealed that the nature of trust is complex, and a failure of one or more components may lead to decreased trustworthiness in a banker. Small businesses that preferred personal communication with a bank were more inclined to relationship banking.

Due to the relatively small sample size and cross-sectional data, our results may not be conclusive but should be viewed as preliminary and as suggestions for future research. Bankers should be aware of the importance of trust for small business owners and of the actions that lead to increased trustworthiness.

The study extends the existing knowledge on the business–bank relationship by focusing mainly on social (instead of economic) factors associated with the establishment of the business–bank relationship in times of crisis and high uncertainty.

Despite the growing use of Fourth Industrial Revolution (4IR) technologies in construction, the reasons behind adopting social media in this context and its real benefits for sustainable construction and productivity remain unclear. This study aims to examine how construction professionals perceive the impact of social media on sustainable construction and productivity in the industry.

This research used a mixed-methods research approach (qualitative and quantitative), resulting in the formulation of a well-structured questionnaire which was distributed to construction professionals. Ordinal regression and multinomial logistic regression were carried out to assess the impact of social media use on sustainable construction and productivity enhancement, as well as the extent of social media utilization in construction projects.

Through exploratory factor analysis, five distinct clusters of social media consequences were identified, namely: information and knowledge sharing, community engagement and morale, environmental and resource management, disruptive and stressful effects and communication and collaboration. Furthermore, the extent of social media usage is closely related to three key factors: community engagement and morale, environmental and resource management and communication and collaboration.

This study represents one of the pioneering research efforts in Nigeria to investigate the implications of social media usage in the construction industry. Thus, future studies can build upon this research to further contribute to the multifaceted dimensions of social media’s impact on the construction industry.

Small farmers in India are collectivized and legalized as Farmer Producer Companies (FPCs) to progress in agri-food value chains as small agribusiness enterprises. FPCs are dependent on timely information for their sustainability and profitability. Mobile apps are a cost-effective form of information and communication technology. Hence, the purpose of this study is to explore the major determinants of mobile apps adoption by FPCs.

Quantitative and qualitative data are collected by administering a semi-structured questionnaire and conducting in-depth interviews with board members of 115 FPCs, with a total membership of 30,405 farmers operating in 14 districts of the state of Kerala, India. The logit model is used for quantitative analysis, while dialog mapping is used for qualitative analysis, based on an integrated technology acceptance model and technology organization environment framework.

Logistic regression results evidence that amongst FPC characteristics, while company size and age are significantly impacting apps adoption, there is no significant association between board size, education level, multiple commodities business or export intention of companies on apps adoption. Digital literacy and technical hands-on training for FPC board members are quintessential to facilitate mobile apps adoption.

The findings are pertinent to policymakers to earmark funds for technical handholding and digital upskilling of FPCs. The need for developing comprehensive, location-centric, farmer-friendly apps by agritech companies is evidenced.

To the best of the authors’ knowledge, this is a pioneering work in the domain of mobile apps adoption from a farmers’ agribusiness enterprise perspective in an emerging market economy using a mixed-methods approach.

Advanced big data analysis and machine learning methods are concurrently used to unleash the value of the data generated by government hotline and help devise intelligent applications including automated process management, standard construction and more accurate dispatched orders to build high-quality government service platforms as more widely data-driven methods are in the process.

In this study, based on the influence of the record specifications of texts related to work orders generated by the government hotline, machine learning tools are implemented and compared to optimize classify dispatching tasks by performing exploratory studies on the hotline work order text, including linguistics analysis of text feature processing, new word discovery, text clustering and text classification.

The complexity of the content of the work order is reduced by applying more standardized writing specifications based on combining text grammar numerical features. So, order dispatch success prediction accuracy rate reaches 89.6 per cent after running the LSTM model.

The proposed method can help improve the current dispatching processes run by the government hotline, better guide staff to standardize the writing format of work orders, improve the accuracy of order dispatching and provide innovative support to the current mechanism.