Risk rating method for optimizing Hopfield neural network based on firefly algorithm

Abstract

The invention discloses a risk rating method for optimizing a Hopfield neural network based on a firefly algorithm, and the method comprises the following steps: firstly, determining a performance period and a risk level, extracting a modeling sample customer, and obtaining customer data as a modeling index system, the customer data comprising the risk level and credit data affecting repayment performance; preprocessing the credit data, and randomly segmenting a training set and a test set; constructing a Hopfield neural network topological structure according to the data features of the modeling sample, determining the parameters of the network, and initializing the weight and threshold of the Hopfield neural network; and constructing a mapping relation between the weight and the threshold of the Hopfield neural network and a firefly algorithm, obtaining an optimal weight and an optimal threshold through the firefly algorithm, and training the Hopfield neural network by using the training set. According to the method, the optimal weight and threshold of the Hopfield neural network are determined by using the firefly algorithm, the convergence speed of the neural network is accelerated, the accuracy of the prediction model is improved, and the requirement of real-time evaluation of Internet financial credit can be met.

Description

technical field [0001] The invention relates to the technical field of risk control in the Internet financial industry, in particular to a risk rating method based on a firefly algorithm to optimize a Hopfield neural network. Background technique [0002] With the development of Internet finance and the continuous expansion of consumer credit business, the importance of risk assessment for loan applicants is increasing. The algorithms used for risk assessment in the prior art are mainly logistic regression, decision tree, support vector machine and Bayesian network, etc., but these algorithms can only process static information data of customers, such as personal characteristics, occupational information, family information, Educational level and so on will not change in the short term, and cannot reflect personal income fluctuations and credit fluctuations, and cannot realize dynamic evaluation of customers' credit. [0003] The neural network model with associative memory...

AI Technical Summary

Problems solved by technology

[0005] The traditional Hopfield neural network is based on the gradient descent method. The random selection of the initial parameters makes it easy to fall into the problem of local optimum, and the learning speed and performance of the network are not good.

At present, the genetic algorithm and particle swarm optimization algorithm are mainly used to optimize the initial value of the Hopfield neural network, but the genetic algorithm has complex operations such as encoding, decoding, crossover, and mutation, and the population size requirement is large and the training time is long; In the later stage of the optimization process, it is easy to fall into the local extremum region, and there are problems such as slow convergence speed.

Images