Tax revenue prediction method and device based on hybrid model

Abstract

The present invention provides a tax revenue prediction method and device based on a hybrid model. The method comprises: testing a training data sequence by using a test data sequence of a support vector regression model, so as to acquire a prediction value of the support vector regression model; testing the training data sequence by using a test data sequence of an autoregression moving average model, so as to acquire a prediction value of the autoregression moving average model; testing the training data sequence by using a test data sequence of an artificial neural network model, so as to acquire a prediction value of the artificial neural network model; and inputting the prediction value of the support vector regression model, the prediction value of the autoregression moving average model and the prediction value of the artificial neural network model into a hybrid model, so as to calculate a prediction value of tax revenue. According to the present invention, the tax revenue prediction method and device based on the hybrid model have the following advantages that: the advantages of various models can be combined well, model parameters can be adaptively adjusted, and prediction accuracy is high.

Description

technical field [0001] The invention relates to the field of tax revenue prediction, in particular to a tax revenue prediction method and device based on a mixed model. Background technique [0002] At present, most of the statistical forecasting tools used by taxation agencies in my country are foreign software, such as EViews, SPSSmodeler and SAS, etc. These software are expensive, and the user experience is not in line with China's national conditions. The built-in algorithm model is more suitable for the system of Western developed countries, so , all parts of our country need a set of forecasting software and algorithm models suitable for each. [0003] my country's current tax revenue forecasting models include regression, time series and artificial neural networks. The establishment of these models either focuses on tax revenue and related economic factors, or explores the regular characteristics of tax revenue itself. Various models have their own scope of applicatio...

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is to provide a method that can combine the advantages of various models in the prior art, the model parameters do not have the ability of self-adaptive adjustment, and the prediction accuracy is not high. The advantages of various models are well combined, the model parameters have the ability of adaptive adjustment, and the wireless Selfie system and method with high prediction accuracy

Images