Prediction Model of Deep Sensor Based on BP Neural Network
CHEN Tong
ZHOU Xiaohui
Abstract：As is known to all,local financial revenue is an important part of the country. The scientific and rational prediction of local financial revenue can effectively overcome the randomness and blindness of the scale of budget. In the wave of big data. It is very important to be good at using data to predict and analyze financial revenue and transform a lot of trivial data into useful decision information. At present,most of the financial income combination forecasting models are all three layers of neural network structure. Aiming at the characteristics of fiscal revenue forecasting,combined with current fiscal revenue combination forecasting method and deep learning idea,a deep sensor prediction model based on BP neural network is proposed. It is a four layer neural network struc?ture,by using the data of Xi'an's fiscal revenue as the test sample,the model is proved to be of high precision,fast convergence and high accuracy with the promotion and practicality by comparing with the conventional BP neural network.
Keywords：data miningfiscal revenue forecastdeep learningDMLP
Publication Date：2019-01-01
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：5( 2978-2981,3009 )