Listed company performance comprehensive evaluation method

Abstract

The invention discloses a listed company performance comprehensive evaluation method. The listed company performance comprehensive evaluation method comprises steps such as model establishment, model resolution, model selection, condition density prediction, randomness evaluation, and the like. The effects of the listed company performance comprehensive evaluation method are that a neural network quantile regression model of the listed company performance comprehensive evaluation is established, the priorities in the two aspects of the neural network model and the quantile regression model are combined, a variation rule of the performance level of the listed company can be depicted exactly, and powerful functions are presented. As a standard gradient optimization algorithm of the neural network quantile regression model for the performance comprehensive evaluation of the listed company is given, the calculation speed of the model is improved under the prediction of not affecting the model estimation accuracy. As an AIC standard selected by the neural network quantile regression model of the listed company performance comprehensive evaluation is established, a suitable model structure can be selected, and the model is prevented from being too complex and falling in an over-fitting awkward situation efficiently.

Description

technical field [0001] The invention belongs to the technical field of application of nonlinear quantile regression theory and method in comprehensive evaluation, and in particular relates to a performance comprehensive evaluation method of listed companies. Background technique [0002] Comprehensive performance evaluation of listed companies is an important part of corporate governance. The accuracy of the evaluation results and the scientificity of identifying key influencing factors are directly related to the effectiveness of corporate governance. The comprehensive performance evaluation of listed companies is based on certain scientific methods to accurately predict the performance level of listed companies: sorting, classification, and has the characteristics of nonlinearity, conditionality, and uncertainty. [0003] The comprehensive performance evaluation of listed companies has its own complexity, which mainly includes two aspects. First, the evaluation index syst...

AI Technical Summary

Problems solved by technology

[0004] However, existing methods (whether parametric or non-parametric) often obtain a deterministic evaluation result, and there is a high risk of misjudgment in ordering or classifying the evaluation results

Images