Investment Bank Risk Prediction Model Based on Dynamic Parameter Neural Network
Download as PDF
For traditional neural network algorithm to predict the risk in the investment banking applications exhibit, predictive accuracy is not high. In this paper, a dynamic parameter optimization of investment banking based on neural network, is the first risk prediction model under the dynamic consolidation and deletion rules, and adaptive dynamic adjustment of parameters to obtain the most appropriate neural network model, then in order to accelerate convergence and prevent oscillation, the introduction of a momentum factor, last modified error function, to ensure the network training error as small as possible, so the network has a smaller case weights. The simulation results showed that the bank's risk prediction model based on neural network optimized dynamic parameters proposed, compared to standard neural network algorithm, has higher prediction accuracy.
Investment banking, Risk prediction, Momentum factor