دورية أكاديمية
أعرض في EDS

Optimizing hyper-parameters of neural networks with swarm intelligence: A novel framework for credit scoring.

التفاصيل البيبلوغرافية
العنوان: Optimizing hyper-parameters of neural networks with swarm intelligence: A novel framework for credit scoring.
المؤلفون: Runchi Zhang, Zhiyi Qiu
المصدر: PLoS ONE, Vol 15, Iss 6, p e0234254 (2020)
بيانات النشر: Public Library of Science (PLoS), 2020.
سنة النشر: 2020
المجموعة: LCC:Medicine
LCC:Science
مصطلحات موضوعية: Medicine, Science
الوصف: Neural networks are widely used in automatic credit scoring systems with high accuracy and outstanding efficiency. However, in the absence of prior knowledge, it is difficult to determine the set of hyper-parameters, which makes its application limited in practice. This paper presents a novel framework of credit-scoring model based on neural networks trained by the optimal swarm intelligence (SI) algorithm. This framework incorporates three procedures. Step 1, pre-processing, including imputation, normalization, and re-ordering of the samples. Step 2, training, where SI algorithms optimize hyper-parameters of back-propagation artificial neural networks (BP-ANN) with the area under curve (AUC) as the evaluation function. Step 3, test, applying the optimized model in Step 2 to predict new samples. The results show that the framework proposed in this paper searches the hyper-parameter space efficiently and finds the optimal set of hyper parameters with appropriate time complexity, which enhances the fitting and generalization ability of BP-ANN. Compared with existing credit-scoring models, the model in this paper predicts with a higher accuracy. Additionally, the model enjoys a greater robustness, for the difference of performance between training and testing phases.
نوع الوثيقة: article
وصف الملف: electronic resource
اللغة: English
تدمد: 1932-6203
Relation: https://doaj.org/toc/1932-6203
DOI: 10.1371/journal.pone.0234254
URL الوصول: https://doaj.org/article/385b8964ea84475db0708015d2f45e9f
رقم الأكسشن: edsdoj.385b8964ea84475db0708015d2f45e9f
قاعدة البيانات: Directory of Open Access Journals
الوصف
تدمد:19326203
DOI:10.1371/journal.pone.0234254