QGA-BP神经网络在农业信贷风险评估中的应用

Application of QGA-BP Neural Network in Risk Assessment of Agricultural Credit

为了提高风险评估的准确度和效率,有效降低农业信贷风险,提出一种基于优化反向传播(Back-Propagation,BP)神经网络的风险评估方法。首先,该方法利用量子遗传算法(Quantum GeneticAlgorithm,QGA)调整和确定BP神经网络的初始权重和阈值,实现了BP神经网络模型参数设置优化。然后,将QGA-BP神经网络模型应用于农业信贷风险评估中,并基于案例分析法进行验证。最后,通过对比QGA-BP神经网络与GA-BP神经网络的性能验证所提方法的有效性。结果表明:QGA-BP神经网络可以加快神经网络的收敛速度,改善BP神经网络容易陷入局部最小值的缺点。QGA-BP神经网络模型在农业供应链金融信用风险预测中表现良好,其预测精度和预测速度都有所提高。

In order to improve the accuracy and efficiency of risk assessment and effectively reduce the risk of agricultural credit,a risk assessment method based on optimized Back-Propagation(BP)neural network was proposed.Firstly,this method uses Quantum Genetic Algorithm(QGA)to adjust and determine the initial weights and thresholds of BP neural network,and realizes the optimization of BP neural network model parameter setting.Then,the QGA-BP neural network model is applied to the risk assessment of agricultural credit,and verified by case analysis.Finally,the effectiveness of the proposed method is verified by comparing the performance of QGA-BP neural network and GA-BP neural network.The experimental results show that QGA-BP neural network can accelerate the convergence speed of neural network and improve the disadvantage that BP neural network is easy to fall into local minimum.QGA-BP neural network model performs well in the prediction of financial credit risk in agricultural supply chain,and its prediction accuracy and speed are improved.