Postdoctoral Work Station of Bank of Jiangsu Co., Ltd, Nanjing, Jiangsu, China.
Postdoctoral Research Station of Nanjing University, Nanjing, Jiangsu, China.
PLoS One. 2020 Jun 5;15(6):e0234254. doi: 10.1371/journal.pone.0234254. eCollection 2020.
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.
神经网络在自动信用评分系统中得到了广泛应用，具有较高的准确性和出色的效率。然而，在缺乏先验知识的情况下，很难确定超参数集，这使得其在实践中的应用受到限制。本文提出了一种基于神经网络的信用评分模型的新框架，该框架由最优群体智能（SI）算法训练。该框架包含三个步骤。第 1 步，预处理，包括样本的插补、归一化和重新排序。第 2 步，训练，其中 SI 算法使用 AUC 作为评估函数优化反向传播人工神经网络（BP-ANN）的超参数。第 3 步，测试，将第 2 步中优化的模型应用于预测新样本。结果表明，本文提出的框架能够有效地搜索超参数空间，并找到具有适当时间复杂度的最优超参数集，从而提高了 BP-ANN 的拟合和泛化能力。与现有的信用评分模型相比，本文提出的模型具有更高的预测精度。此外，该模型具有更高的稳健性，因为训练和测试阶段的性能差异较小。
