|Table of Contents|

Economic Benefit Risk Prediction Based on Feature Selection and Deep Learning Model(PDF)

南京师范大学学报（工程技术版）[ISSN:1006-6977/CN:61-1281/TN]

Issue:
2024年04期
Page:
87-92
Research Field:
计算机科学与技术
Publishing date:

Info

Title:
Economic Benefit Risk Prediction Based on Feature Selection and Deep Learning Model
Author(s):
Liu Haihong1; 2; Yu Ming3; Liu Jing4; Wu Ruihui1; 2
(1.School of Economics and Management,Guangzhou Nanyang Polytechnic College,Guangzhou 510900,China)
(2.School of Management,Universiti Malaysia of Kelantan,Kota Bharu,Kelantan 16250,Malaysia)
(3.School of Economics and Management,Shihezi University,Shihezi 832000,China)
(4.School of Computer Science and Technology,Kashi University,Kashi 840000,China)
Keywords:
financial risk prediction; deep learning; feature selection; multi-verse optimization; bidirectional gated recurrent units
PACS:
TP391
DOI:
10.3969/j.issn.1672-1292.2024.04.009
Abstract:
The combination of big data,cloud computing and artificial intelligence technologies has significantly enhanced the capability of enterprise financial data processing. In order to improve the accuracy and reliability of financial risk prediction for small and medium-sized enterprises(SMEs),an financial risk prediction framework based on multi-verse optimization(MVO)algorithm and bidirectional gated recurrent units(BiGRU). Initially,complex financial data are subjected to feature normalization,followed by the selection of the optimal feature subset using the MVO algorithm. Subsequently,the evaluation of economic benefit risk for SMEs is accomplished using the BiGRU deep learning model. The sequential model-based algorithm configuration(SMAC)is employed to perform parameter tuning for the BiGRU model,optimizing its parameter configuration to enhance model performance and generalization ability. The SMAC algorithm automatically searches for the best combination of parameters in the parameter space,thereby identifying the optimal model configuration. Experimental results demonstrate that the proposed hybrid model exhibits higher accuracy and predictive capability in the task of predicting financial risk for SMEs,outperforming similar state-of-the-art methods,thereby confirming the potential and importance of feature selection and deep learning models in economic benefit risk analysis.

References:

[1]PENG X,HUANG H. Fuzzy decision making method based on CoCoSo with critic for financial risk evaluation[J]. Technological and Economic Development of Economy,2020,26(4):695-724.
[2]杨德杰,章宁,袁戟,等. 基于堆栈降噪自编码网络的个人信用风险评估方法[J]. 计算机科学,2019,46(10):7-13.
[3]李庆涛,林培光,王基厚,等. 基于板块效应的深度学习股价走势预测方法[J]. 南京师范大学学报(工程技术版),2022,22(1):30-38.
[4]王立凯,曲维光,魏庭新,等. 基于深度学习的中文零代词识别[J]. 南京师范大学学报(工程技术版),2021,21(4):19-26.
[5]LI X,WANG J,YANG C. Risk prediction in financial management of listed companies based on optimized BP neural network under digital economy[J]. Neural Computing and Applications,2023,35(3):2045-2058.
[6]苏云鹏,杨宝臣,周方召. 我国市场债券收益的可预测性及其经济价值研究[J]. 管理科学学报,2019,22(4):27-52.
[7]KUMAR D,SARANGI P K,VERMA R. A systematic review of stock market prediction using machine learning and statistical techniques[J]. Materials Today:Proceedings,2022,49(1):3187-3191.
[8]YANG S. A novel study on deep learning framework to predict and analyze the financial time series information[J]. Future Generation Computer Systems,2021,125(1):812-819.
[9]ZHANG Y A,YAN B B,AASMA M. A novel deep learning framework:Prediction and analysis of financial time series using CEEMD and LSTM[J]. Expert Systems with Applications,2020,159(1):113609.
[10]METAWA N,PUSTOKHINA I V,PUSTOKHIN D A,et al. Computational intelligence-based financial crisis prediction model using feature subset selection with optimal deep belief network[J]. Big Data,2021,9(2):100-115.
[11]刘建伟,赵会丹,罗雄麟,等. 深度学习批归一化及其相关算法研究进展[J]. 自动化学报,2020,46(6):30-38.
[12]ABUALIGAH L. Multi-verse optimizer algorithm:A comprehensive survey of its results,variants,and applications[J]. Neural Computing and Applications,2020,32(16):12381-12401.
[13]牛红丽,赵亚枝. 利用Bagging算法和GRU模型预测股票价格指数[J]. 计算机工程与应用,2022,58(12):132-138.
[14]方娜,余俊杰,李俊晓,等. 基于CNN-BIGRU-ATTENTION的短期电力负荷预测[J]. 计算机仿真,2022,39(2):40-44.
[15]WU J,CHEN S P,LIU X Y. Efficient hyperparameter optimization through model-based reinforcement learning[J]. Neurocomputing,2020,409(1):381-393.
[16]ALAM T M,SHAUKAT K,HAMEED I A,et al. An investigation of credit card default prediction in the imbalanced datasets[J]. IEEE Access,2020,8(1):201173-201198.
[17]DASTILE X,CELIK T. Making deep learning-based predictions for credit scoring explainable[J]. IEEE Access,2021,9(1):50426-50440.

Memo

Memo:
-
Last Update: 2024-12-15