مقاله انگلیسی رایگان در مورد تکنیک های یادگیری ماشین در پیش بینی ریسک اعتباری SME در تامین مالی زنجیره تامین – اسپرینگر ۲۰۲۲

springer

 

مشخصات مقاله
ترجمه عنوان مقاله پیش بینی ریسک اعتباری شرکت های کوچک و متوسط در تامین مالی زنجیره تامین با یک استراتژی نمونه گیری بر اساس تکنیک های یادگیری ماشین
عنوان انگلیسی مقاله Forecasting SMEs’ credit risk in supply chain finance with a sampling strategy based on machine learning techniques
انتشار مقاله سال ۲۰۲۲
تعداد صفحات مقاله انگلیسی  ۳۳ صفحه
هزینه دانلود مقاله انگلیسی رایگان میباشد.
پایگاه داده نشریه اسپرینگر
نوع نگارش مقاله
مقاله پژوهشی (Research article)
مقاله بیس این مقاله بیس میباشد
نمایه (index) scopus – master journals – JCR
نوع مقاله ISI
فرمت مقاله انگلیسی  PDF
ایمپکت فاکتور(IF)
۴٫۵۴۹ در سال ۲۰۲۰
شاخص H_index ۱۱۱ در سال ۲۰۲۲
شاخص SJR ۱٫۱۶۵ در سال ۲۰۲۰
شناسه ISSN ۱۵۷۲-۹۳۳۸
شاخص Quartile (چارک) Q1 در سال ۲۰۲۰
فرضیه ندارد
مدل مفهومی دارد
پرسشنامه ندارد
متغیر دارد
رفرنس دارد
رشته های مرتبط مهندسی صنایع – مدیریت
گرایش های مرتبط لجستیک و زنجیره تامین – مهندسی مالی و ریسک – مدیریت کسب و کار
نوع ارائه مقاله
ژورنال
مجله / کنفرانس سالنامه تحقیق در عملیات – Annals of Operations Research
دانشگاه The School of Economics and Management, University of Science and Technology Beijing, China
کلمات کلیدی پیش بینی ریسک اعتباری – تامین مالی زنجیره تامین – انتخاب متغیر کلیدی – استراتژی نمونه گیری نامتعادل – تحلیل وابستگی جزئی
کلمات کلیدی انگلیسی Credit risk forecasting – Supply chain finance – Key variable selection – Imbalanced sampling strategy – Partial dependency analysis
شناسه دیجیتال – doi
https://doi.org/10.1007/s10479-022-04518-5
کد محصول e16634
وضعیت ترجمه مقاله  ترجمه آماده این مقاله موجود نمیباشد. میتوانید از طریق دکمه پایین سفارش دهید.
دانلود رایگان مقاله دانلود رایگان مقاله انگلیسی
سفارش ترجمه این مقاله سفارش ترجمه این مقاله

 

فهرست مطالب مقاله:

Abstract

۱ Introduction

۲ Related works

۳ Methodology

۴ Dataset information and predictors

۵ Results

۶ Discussions

۷ Conclusions

Appendix A: The pseudocode of SVM-based classifier

Appendix B: The pseudocode of ANN-based classifier

Appendix C: The pseudocode of C4.5 DT

Appendix D: The pseudocode of RF

Appedix E: The pseudocode of bagging

Appendix F: The pseudocode of GB

Appendix G: Variables and definition

References

 

بخشی از متن مقاله:

Abstract

     Exploring the value of multi-source information fusion to predict small and medium-sized enterprises’ (SMEs) credit risk in supply chain finance (SCF) is a popular yet challenging task, as two issues of key variable selection and imbalanced class must be addressed simultaneously. To this end, we develop new forecast models adopting an imbalance sampling strategy based on machine learning techniques and apply these new models to predict credit risk of SMEs in China, using financial information, operation information, innovation information, and negative events as predictors. The empirical results show that the financial-based information, such as TOC, NIR, is most useful in predicting SMEs’ credit risk in SCF, and multi-source information fusion is meaningful in better predicting the credit risk. In addition, based on the preferred CSL-RF model, which extends cost-sensitive learning to a random forest, we also present the varying mechanisms of key predictors for SMEs’ credit risk by using partial dependency analysis. The strategic insights obtained may be helpful for market participants, such as SMEs’ managers, investors, and market regulators.

Introduction

     The development of small and medium-sized enterprises (SMEs) has attracted attention from scholars and practitioners over the globe. However, because of the tightening of credit criteria for corporate loans, SMEs are facing significant challenges, mainly including capital constraints, high operational costs, and ambiguous information (Yan & He, 2020). As a major component of the economy in China, SMEs contribute almost 90% of the number of enterprises, 80% of urban employment, 70% of GDP, 60% of technological innovation, and 50% of tax revenue (see https://www.ndrc.gov.cn/ for more detail). SMEs in China also face problems mainly including high financial distress, high financing costs, high operational risks, tightening financing channels, high fraud risks, and asymmetric financing information (Weng et al., 2016; Zhu et al., 2019).

     As a popular financing channel, supply chain finance (SCF) defined by Hofmann (2005) as the inter-firms optimization of financing and the integration of financing processes with customers, suppliers, and service providers to increase the value of all participating firms, has attracted attention from both practitioners and scholars alike. The Chinese government has developed some new financial policies to ease the financing pressure on SMEs, e.g., Promoting SME Development Plan (2016–۲۰۲۰), which seek to “promote more supply chains to join the financing service platform of SMEs”. Similar initiatives are underway in other countries and regions, such as the United States, United Kingdom, Japan, Canada, South Korea, Europe, and Mexico. SCF is also being used to promote the development of SMEs. For example, the Office of the United States Trade Representative (USTR) is implementing a series of initiatives to address the financing problems of SMEs, including SCF.

Results and analyses

     To our best knowledge, this is the first study to consider the value of multi-source information fusion to predict the SMEs’ credit risk in SCF, and presents some managerial implications. We predict the credit risk of SMEs in SCF with an imbalance sampling strategy on machine learning techniques. Considering the value of multi-source information fusion in the big data era, we construct a broader knowledge base, including financial information, operation information, innovation information, and negative events, to predict the credit risk of SMEs in China, and develop new models to simultaneously solve for key predictor selection and imbalance classes. We then adopt six evaluation criteria to compare the prediction performances of the six machine learning techniques—SVM, NN, DT, RF, bagging, and GB—based on the data of VA and VS, respectively. We compare the results of new models via a re-sampling strategy for baseline models on VA and VS; the results indicate that the proposed CSL-RF model is optimal in terms of accuracy and robustness. The empirical results indicate that the financial-based information is the main source to predict SEMs’ credit risk in SCF, and the multi-source information fusion is meaningful. In addition, based on the preferred CSL-RF model, we also present the varying mechanisms of key predictors for SMEs’ credit risk by using partial dependency analysis. Finally, we generate strategic insights for market participants, such as regulators, investors, and managers.

ارسال دیدگاه

نشانی ایمیل شما منتشر نخواهد شد.