Analysis of Credit Customer Delinquency Based on BP Neural Network Model
DOI: 10.23977/ferm.2024.070323 | Downloads: 10 | Views: 468
Author(s)
Xinyu Wu 1, Jielin Shang 1
Affiliation(s)
1 PLA Dalian Naval Academy, Dalian, China
Corresponding Author
Xinyu WuABSTRACT
With the advancement of the economic market in the new century, the issues of credit evaluation and risk prediction have received increasing attention. The advent of the big data era has led to the widespread development and application of neural networks. As an excellent classification tool, artificial neural networks do not require fixed premises or assumptions about inputs and outputs before modeling. They possess self-learning and self-adaptation capabilities, exhibit strong nonlinear mapping abilities, and have fault tolerance mechanisms, making them a powerful tool for solving credit issues. This paper utilizes R software to clean, process, and analyze credit customer data provided by a German credit database. A BP neural network model is established and evaluated based on criteria such as accuracy and AUC value. The model demonstrates good fitting effects and is used to predict the corresponding data set.
KEYWORDS
BP neural network; credit; delinquency; predictionCITE THIS PAPER
Xinyu Wu, Jielin Shang, Analysis of Credit Customer Delinquency Based on BP Neural Network Model. Financial Engineering and Risk Management (2024) Vol. 7: 181-186. DOI: http://dx.doi.org/10.23977/ferm.2024.070323.
REFERENCES
[1] William Caballero,Ramo´n Giraldo and Jorge Mateu. A universal kriging approach for spatial functional data [J]. Stochastic Environmental Research and Risk Assessment 2013 (7):1553–1563.
[2] Antonio Cuevas, Manuel Febrero and Ricardo Fraiman, On the use of the bootstrap for estimating functions with functional data [J]. Computational Statistics and Dat a Analysis 2006(51):1063–1074.
[3] Giraldo R, Delicado P, Mateu J. Continuous time-varying kriging for spatial prediction of functional data: An environmental application [J]. Journal of Agricultural, Biological, and Environmental Statistics 2010(1):66–82.
[4] Giraldo R, Delicado P and Mateu J. Ordinary kriging for function- valued spatial data. Environmental and Ecological Statistics 2011(3): 411–426.
[5] gnaccolo R, Mateu J and Giraldo R. Kriging with external drift for functional data for air quality monitoring [J]. Stochastic Environmental Re- search and Risk Assessment 2014(28): 1171–1186.
[6] Lina Schelin, Sara Sjöstedt-de Luna. Kriging Prediction Intervals Based on Semiparametric Bootstrap [J] Mathematical Geosciences 2010(42): 985–1000.
[7] Maria Franco-Villoria, Rosaria Ignaccolo. Bootstrap based uncertainty bands for prediction in functional kriging [J]. Spatial Statistics, 2017(8):130-148
[8] Cressie N. Statistics for Spatial Data [M]. Revised Edition Wiley, New York,1993.
[9] AM Computation Vehicle with GCV/AIC/REML Smoothness Estimation. R package version 1.8.6[EB/OL]. http://CRAN.R-project.org/package=mgcv
[10] Brunsdon C, Fotheringham S, and Charlton M. "Geographically Weighted Re-gression-Modelling Spatial Non-Stationarity," [J]. The Statistician, 1998(47): 431–443.
Downloads: | 29512 |
---|---|
Visits: | 601973 |
Sponsors, Associates, and Links
-
Information Systems and Economics
-
Accounting, Auditing and Finance
-
Industrial Engineering and Innovation Management
-
Tourism Management and Technology Economy
-
Journal of Computational and Financial Econometrics
-
Accounting and Corporate Management
-
Social Security and Administration Management
-
Population, Resources & Environmental Economics
-
Statistics & Quantitative Economics
-
Agricultural & Forestry Economics and Management
-
Social Medicine and Health Management
-
Land Resource Management
-
Information, Library and Archival Science
-
Journal of Human Resource Development
-
Manufacturing and Service Operations Management
-
Operational Research and Cybernetics