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.

Aiming at the inefficiency of solving the Sobol index using the traditional mathematical analytical method, a Sobol global sensitivity analysis method is proposed.

In this paper, a support vector regression (SVR) surrogate model is constructed to solve the Sobol index. The optimal combination of SVR hyperparameters is obtained by using the improved beluga whale optimization (IBWO). Meanwhile, in order to solve the problem that Sobol sequences will form correlation regions in high-dimensional space leading to the uneven distribution of sampling points, a scrambled strategy is introduced in the Sobol sensitivity analysis using IBWO-SVR. Thus, the IBWO-SVR-SS sensitivity analysis model is established.

The results of two test functions show that the method further improves the accuracy of the sensitivity analysis. Finally, the first-order Sobol index and second-order Sobol index are solved by the IBWO-SVR-SS method using the metro bogie frame as an engineering example. Through the analysis results, the key design parameters of the frame and the design parameter combinations with more obvious coupling relationships are identified, providing a strong reference for the subsequent analysis and structural optimization.

Sobol sensitivity analysis using the surrogate model method can effectively improve the efficiency of the solution. In addition, IBWO is used for the optimization of the SVR hyperparameters to improve the accuracy and efficiency of the optimization, and finally, the correction of the Sobol sequence through the introduction of the disruption strategy also further improves the accuracy of the sensitivity analysis of Sobol.

The serious wear problem of heavy-haul freight vehicle wheels affects the safety and economy of vehicle operation. This paper aims to study wheel wear evolution law and the influence of line parameters on wheel wear of heavy-haul freight, and provide the basis for operation and line maintenance.

The wheel wear test data of heavy-haul freight vehicles were analyzed. Then a heavy-haul freight vehicle dynamic model was established. The line parameters influencing wheel wear in heavy-haul freight vehicles were also analyzed by the Jendel wear model, and the effects of rail cant, rail gauge, rail profile and line ramp on wheel wear were analyzed.

A rail cant of 1:40 results in less wheel wear; an increase in the rail gauge can reduce wheel wear; and when matched with the CHN60 rail, the wear depth is relatively small. A decrease of 9.21% in wheel wear depth when matched with the CHN60 rail profile. The ramp of the heavy-haul line is necessary to consider for calculating wheel wear. When the ramp is considered, the wear depth increases by 8.47%. The larger the ramp, the greater the braking force and therefore, the greater of the wheel wear.

This paper first summarizes the wear characteristics of wheels in heavy-haul freight vehicles and then systematically analyzes the effect of line parameters on wheel wear. In particular, this study researched the effects of rail cant, rail gauge, rail profile and line ramp on wheel wear.

The peer review history for this article is available at: https://publons.com/publon/10.1108/ILT-02-2024-0038/

This article intends to explore how organizational learning affects innovation in public library services, and the role of public librarians in innovation in library services.

This study collected 375 valid questionnaires from 19 public libraries in Shanghai and Zhejiang based on organizational learning, organizational innovation and employee psychological empowerment theory. Additionally, SPSS and HLM are used to analyze the relationship among the three processes of organizational learning: knowledge acquisition, knowledge sharing and knowledge application, and public library service innovation.

Results show that organizational learning has a significant positive effect on the service innovation of public libraries. Knowledge acquisition and knowledge application in the process of organizational learning have a significant positive influence on the service innovation of public libraries, but the impact of knowledge sharing on service innovation is weak. Employee psychological empowerment has a negative regulating influence on knowledge sharing–public library service innovation, but no significant influence on knowledge application–public library service innovation and knowledge acquisition–public library service innovation.

This research explores the effectiveness of the theory of organizational learning in the field of public libraries and also confirms the role of librarians in the work of public libraries. Together, they promote the innovation of public libraries.

Drawing from social capital theory and resource dependence theory, this paper aims to test the relationship between top management team (TMT) government social capital and firm’s innovation performance via firm’s network prestige, and the moderating effect of TMT academic social capital.

The authors collected data from the China Stock Market and Accounting Research Database as well as A-share listed firms’ annual reports, and finally generated a sample of 922 firms and 2,464 firm-years from 2008 to 2014. UCINET 6.0 was used to analyze the data.

The authors find that the government social capital of TMT is positively related to firms’ innovation performance and firms’ network prestige plays a mediating role in this relationship. In addition, TMT academic social capital can strengthen the links between TMT government social capital and innovation performance through firms’ network prestige.

This paper not only contributes to literatures on the mechanism in the relationship between government social capital and firms’ innovation, but also to literatures on the effectiveness of the heterogeneity of firm’s social capital.

The purpose of this paper is to explore a new approach to solve the problem of positive and negative offset in the calculation process of integral elements, then propose a series of new grey relational degree model for cross sequences.

The definitions of cross sequences and area elements have been proposed at first. Then the concept of difference degree between sequences has been put forward. Based on the definition of difference degree between sequences, various modified grey relational degree models for cross sequences have been proposed to solve the measurement problem of cross sequence correlation relationships.

(1) The new definition of cross sequences; (2) The area element; (3) Various modified grey relational degree models for cross sequences based on the definition of difference degree between sequences.

The grey relational analysis model of cross sequences is a difficult problem in grey relational analysis. The new model proposed in this article can effectively avoid the calculation deviation of grey relational analysis model for cross sequences, and reasonably measure the correlation between cross sequences. The new model was used to analyse the food consumer price index in Shaanxi Province, clarifying the relationship between different types of food consumer price indices, some interesting results that are not completely consistent with general economic theory were obtained.

The new definition of cross sequences, the area element and various modified grey relational degree models for cross sequences were proposed.

The purpose of this study is to discuss how organizations can drive organizational performance through human capital (HC) investment through systematic thinking.

This study analyzes three companies from various industries, adopts systems thinking and uses three leading indicators from the balanced scorecard framework to explore the effects of strategic orientations for HC on innovation ecosystems and organizational performance.

In terms of academic contributions, this study broadly verifies the innovation ecosystem model for organizations and reveals that customer-oriented, internal process-oriented and innovation learning-oriented HC strategies reinforce the pathways in organizational innovation ecosystems, thereby enriching the literature on innovation ecosystems.

In terms of practical contributions, this study provides a novel HC-based perspective on developmental dynamics and details the relationships among each aspect of the innovation ecosystem and HC strategies.

The proposed architecture and strategic frameworks provide a reference for corporations to implement strategic orientations of HC, drive operations in organizational innovation ecosystems and improve organizational performance.

The purpose of this study is to present a bibliometric and network analysis that uses the Scopus and Dimension databases to provide new insights into the progression toward the study of sustainable economic development.

This analysis has been drawn on 665 papers published between 2015 and 2023. Bibliometric analysis characterizes a research topic by identifying leading nations, the most significant authors and expressive publications. Network analysis revealed keyword evolution over time, co-citation patterns and study grouping. Content analysis was used to identify major topic in the discipline, with a focus on their interrelationships. Each publication in the data set is briefly described, along with its methodological approach.

The results of this study show that green finance plays a major role in long-term economic growth, having a significant influence on the preservation of environmental quality, economic efficacy and a more comprehensive economic system. Financial technology also accelerates the transition to a carbon-neutral economy by enhancing the beneficial effects of green finance on aspects of the economic system and environmental conservation.

The investigation is based only on Scopus and Dimensions-indexed journal articles. However, additional studies should incorporate publications from other reputable databases, such as Web of Science, PubMed and Science Direct, for the bibliometric analysis, so that the findings of the model analysis become more reliable and valid with examination of more documents. The visualization of similarity viewer was used for data analysis in the study, there is a scope for using other tools such as Biblioshiney and CitNet Explorer.

To support long-term economic growth, authorities should encourage Fintech companies to actively participate in various green finance initiatives and environmental conservation businesses. Financial managers should facilitate the integration of technology and green finance for financial services. It is important to encourage institutional and individual investors alike to look into more environmentally friendly ways to invest and save money. Policymakers should provide a platform for global awareness and government agencies should enhance their recommendations to state governments to increase the efficacy of green finance.

This study contributes to the literature by investigating the relationship between Fintech and green financing. This study holds significance for financial intermediaries, industrialists, investors and policymakers by providing insights into the integration of Fintech with green finance for sustainable development. These findings affirm the pivotal role of Fintech and green finance in fostering sustainable economic development. The novelty of the topic and the variety of publications in which it has been published demonstrate that sustainable economic development has piqued the interest of a wide range of areas.