基于BP神经网络的“三公”经费支出研究  

Research on the Expenditure of“Three Public”Funds Based on BP Neural Network

作　　者：李紫文 LI Zi-wen(Business School,University of Shanghai for Science and Technology,Shanghai 200093,China)

机构地区：[1]上海理工大学管理学院,上海200093

出　　处：《科技和产业》2021年第9期154-159,共6页Science Technology and Industry

摘　　要：以国家税务总局系统2011—2018年的“三公”经费数据为研究样本,对其近几年“三公”经费的实际支出和预决算差距进行分析。针对“三公”经费预决算差距情况,利用BP神经网络,将历年“三公”经费支出数据作为神经网络的输入,将下一年的实际支出作为神经网络的输出,通过神经网络的学习和训练,建立一个“三公”经费支出预测模型,提高“三公”经费预算准确度,为下一年“三公”经费的预算提供一定参考。Taking the data of“three public”funds from 2011 to 2018 in the State Taxation Bureau system as the research sample,analyzes the actual expenditure of“three public”funds and the gap between the budget and final accounts of the funds in recent years.In view of the gap between the budget and final accounts of“three public”funds,BP neural network is used to take the data of“three public”funds over the years as the input of neural network,and the actual expenditure of next year as the output of neural network.Through the learning and training of the neural network,a forecast model of the expenditure of the“three public”funds is established,which improves the accuracy of the budget of the“three public”funds,and provides some reference for the budget in the next year.

关 键 词：国税系统 “三公”经费 BP神经网络 预算支出预测 

分 类 号：F812.45[经济管理—财政学]