Filters








161 Hits in 9.2 sec

Predicting China's SME Credit Risk in Supply Chain Finance Based on Machine Learning Methods

You Zhu, Chi Xie, Gang-Jin Wang, Xin-Guo Yan
2016 Entropy  
We propose a new integrated ensemble machine learning (ML) method, i.e., RS-RAB (Random Subspace-Real AdaBoost), for predicting the credit risk of China's small and medium-sized enterprise (SME) in supply  ...  The experimental results show that RS-RAB possesses an outstanding prediction performance and is very suitable for forecasting the credit risk of China's SME in SCF by comparison with the other three ML  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/e18050195 fatcat:ctoq7x5vwvakvck5yv4auja2qq

Credit Evaluation of SMEs Based on GBDT-CNN-LR Hybrid Integrated Model

Lei Zhang, Qiankun Song, Yingjie Wang
2022 Wireless Communications and Mobile Computing  
Based on previous studies, this paper proposes a two-layer feature extraction method based on Gradient Boosting Decision Tree (GBDT) and Convolutional Neural Network (CNN).  ...  Under the background of the increasing demand for credit evaluation and risk prediction, the establishment of an effective credit evaluation model for small- and medium-sized enterprises has become a research  ...  Ma [21] put forward a hybrid integrated method RS-Boosting based on boosting and random subspace sampling to predict corporate credit risk and verified the effectiveness and feasibility of the method  ... 
doi:10.1155/2022/5251228 fatcat:vxt3kydhjzfm5cerwbbxrbueay

Ensemble based Hybrid Machine Learning Approach for Sentiment Classification- A Review

Rabi Narayan, Manan Roy, Sujata Dash
2016 International Journal of Computer Applications  
But, recently it has been observed from the findings that ensemble based learning algorithm achieves better understanding and acceptance of the solution in terms of diversity and accuracy.  ...  In this paper, an extensive study of ensemble based machine learning techniques in the domain of sentiment classification has been done to enhance the efficiency, by adopting multiple learning algorithms  ...  Gang Wang and Jian Ma [27] also integrated random subspace and boosting to predict credit risk problem. They called it as RS-boosting which was evaluated on two corporate credit datasets.  ... 
doi:10.5120/ijca2016910813 fatcat:pw7zwvvd2nak5bfck6nhryvwda

Ten-year evolution on credit risk research: a systematic literature review approach and discussion

Fernanda Medeiros Assef, Maria Teresinha Arns Steiner
2020 Ingeniería e Investigación  
In this work, a systematic literature review is proposed which considers both "Credit Risk" and "Credit risk" as search parameters to answer two main research questions: are machine learning techniques  ...  Given its importance in financial risk management, credit risk analysis, since its introduction in 1950, has been a major influence both in academic research and in practical situations.  ...  Acknowledgments This study was partially funded by PUCPR and by the Coordination for the Improvement of Education Personnel -Brazil (CAPES, represented by thefirst author) and by the National Council for  ... 
doi:10.15446/ing.investig.v40n2.78649 doaj:49fab6209b7f4390938e44fa1c83b518 fatcat:tm5glc2tz5hddmlfqaznc5na4q

Multimodel Integrated Enterprise Credit Evaluation Method Based on Attention Mechanism

Lei Zhang, Qiankun Song, Heng Liu
2022 Computational Intelligence and Neuroscience  
Based on the previous researches, this paper first screens out features by correlation coefficient method and gradient boosting decision tree (GBDT).  ...  Due to the difficulty of credit risk assessment, the current financing and loan difficulties of small- and medium-sized enterprises (SMEs) are particularly prominent, which hinders the operation and development  ...  Acknowledgments is work was partially supported by Group Building Scientific Innovation Project for Universities in Chongqing (CXQT21021) and Science and Technology Research Project of Chongqing Education  ... 
doi:10.1155/2022/8612759 pmid:35237312 pmcid:PMC8885257 fatcat:vwzo5f4lxrdi5j4lu7oqjasorm

Forecasting SMEs' credit risk in supply chain finance with an enhanced hybrid ensemble machine learning approach

You Zhu, Li Zhou, Chi Xie, Gang-Jin Wang, Truong V. Nguyen
2019 International Journal of Production Economics  
Thus, forecasting SMEs' credit risk in SCF has become one of the most critical issues in financing decision-making.  ...  SMEs' credit risk.  ...  For instance, RS-Boosting integrates boosting and random subspace (RS), and it is used to forecast corporate credit risk .  ... 
doi:10.1016/j.ijpe.2019.01.032 fatcat:kymujd32yba6pkuo6nrodyf5fe

Machine Learning Applied to Banking Supervision a Literature Review

Pedro Guerra, Mauro Castelli
2021 Risks  
Credit risk assessment and stress testing are highlighted topics as well as other risk perspectives, with some references to ML application surveys.  ...  One limitation of this study is the paucity of contributions using supervisory data, which justifies the need for additional investigation in this field.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/risks9070136 fatcat:gqjub6czvjao3fbqwf34otgwre

COMBINING B&B-BASED HYBRID FEATURE SELECTION AND THE IMBALANCE-ORIENTED MULTIPLE-CLASSIFIER ENSEMBLE FOR IMBALANCED CREDIT RISK ASSESSMENT

Jie SUN, Young-Chan LEE, Hui LI, Qing-Hua HUANG
2015 Technological and Economic Development of Economy  
We conduct main experiments using a 1:3 imbalanced corporate credit risk data set with continuous features and extended experiments using a 1:5 imbalanced data set with continuous features and a 1:3 imbalanced  ...  This paper proposes an integrated method that combines B&B (branch and bound)-based hybrid feature selection (BBHFS) with the imbalanceoriented multiple-classifier ensemble (IOMCE) for imbalanced credit  ...  Acknowledgements This research is partially supported by the National Natural Science Foundation of China  ... 
doi:10.3846/20294913.2014.884024 fatcat:xzjw42zexvbrpk3zgju5boxbxa

Data science in economics: comprehensive review of advanced machine learning and deep learning methods

Saeed Nosratabadi, Amir Mosavi, Puhong Duan, Pedram Ghamisi, Ferdinand Filip, Shahab S. Band, Uwe Reuter, Joao Gama, Amir H. Gandomi
2020 Zenodo  
Application domains include a wide and diverse range of economics research from the stock market, marketing, and e-commerce to corporate banking and cryptocurrency.  ...  The findings reveal that the trends follow the advancement of hybrid models, which, based on the accuracy metric, outperform other learning algorithms.  ...  Acknowledgments: Support of the Alexander von Humboldt Foundation is acknowledged. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.5281/zenodo.4087812 fatcat:4flgeabkxvgjrpbydfby3v6tua

A Novel GSCI-based Ensemble Approach for Credit Scoring

Xiaohong Chen, Siwei Li, Xuanhua Xu, Fanyong Meng, Wenzhi Cao
2020 IEEE Access  
ACKNOWLEDGMENT The authors gratefully acknowledge the financial support provided by the major consulting projects of Chinese Academy of Engineering  ...  The common methods include bagging [43] , boosting [27] and the Random Subspace Method (RSM) [44] .  ...  INTRODUCTION Credit risk is the main risk for financial institutions, and the effectiveness of credit risk management is the critical issue for the survival and development of financial institutions.  ... 
doi:10.1109/access.2020.3043937 fatcat:qlhtlws6c5eupih4fvltemboiu

Deep Learning for Financial Applications : A Survey [article]

Ahmet Murat Ozbayoglu, Mehmet Ugur Gudelek, Omer Berat Sezer
2020 arXiv   pre-print
We not only categorized the works according to their intended subfield in finance but also analyzed them based on their DL models.  ...  Lots of different implementations of DL exist today, and the broad interest is continuing.  ...  [88] surveyed the credit scoring and credit risk assessment studies based on soft computing techniques whereas Marques et. al.  ... 
arXiv:2002.05786v1 fatcat:p4ykvxempzajpo66p2z6xaddp4

Self-organizing learning array and its application to economic and financial problems

Z ZHU, H HE, J STARZYK, C TSENG
2007 Information Sciences  
He applied ANN rule extraction and decision tables based on the PROLOGA software to advanced decision-support systems for credit-risk evaluation.  ...  One of the best-known ensemble algorithms is boosting [12] , which is designed to boost the accuracy of individual learning algorithms.  ...  The authors also acknowledge constructive comments and suggestions provided by the reviewers.  ... 
doi:10.1016/j.ins.2006.08.002 fatcat:gxumosempngp7fufad5ixw3jje

Business Failure Prediction Based on a Cost-Sensitive Extreme Gradient Boosting Machine

Yao Zou, Changchun Gao, Han Gao
2022 IEEE Access  
However, the highly imbalanced class distribution of financial risk data and the inexplainable of most machine learning-based early distress warning models limit their commercial application.  ...  To address the above limitations, we enhance the business failure prediction performance by treeensemble in a boosting manner.  ...  on the predictive performance of ensemble models that ensembled MLP, KNN, and C4.5 DT on credit scoring domain and bankruptcy prediction task. [37] introduced a new conception that named as ''financial  ... 
doi:10.1109/access.2022.3168857 fatcat:vvuxpdyiy5c6bc6efj5r64g36e

Forecasting Financial Distress With Machine Learning – A Review

Denize Lemos Duarte, Flávio Luiz de Moraes Barboza
2020 Future Studies Research Journal: Trends and Strategies  
Purpose – Evaluate the various academic researches with multiple views on credit risk and artificial intelligence (AI) and their evolution.Theoretical framework – The study is divided as follows: Section  ...  Intelligence and Machine Learning is recent and requires attention and investigation, thus, this study contributes to the opening of new views in order to deepen the work on this topic.  ...  In order to improve the accuracy in the prediction of credit risk, it is possible to find some studies that use combinations of techniques and classifiers that integrate multiple methods, including making  ... 
doi:10.24023/futurejournal/2175-5825/2020.v12i3.533 fatcat:2rgbaiudpbdkdo4bjkdahup7qi

Data Science in Economics [article]

Saeed Nosratabadi, Amir Mosavi, Puhong Duan, Pedram Ghamisi
2020 arXiv   pre-print
On the other hand, it is found that based on the RMSE accuracy metric, hybrid models had higher prediction accuracy than other algorithms.  ...  Application domains include stock market, marketing, E-commerce, corporate banking, and cryptocurrency.  ...  Acknowledgments: Conflicts of Interest: The authors declare no conflict of interest.  ... 
arXiv:2003.13422v1 fatcat:genllmgl3bhmrhq4txfvlgbpey
« Previous Showing results 1 — 15 out of 161 results