基于粗糙集BP神经网络的房产税基批量评估研究——以广州市为例

Research on Batch Assessment of Property Tax Base Based on Rough Set Theory and BP Neural Network--Take Guangzhou City as an Example

自2021年发布《中华人民共和国国民经济和社会发展第十四个五年规划和2035年远景目标纲要》以来,提出推进房产税立法,健全地方税体系,从法律层面保证房产税实施。房产税基批量评估作为一项繁难的系统工程,基础数据复杂多样,又需兼顾公平性与效率性。借助大数据和计算机智能能够很好地解决此问题,且评估结果科学准确。本文基于粗糙集理论与BP神经网络构建房产税基批量评估模型,识别并剔除7个对房产税基影响不大的冗余属性,筛选出20个显著特征变量,并通过广州市9 000套二手普通居民住宅交易样本数据进行验证,结果表明,RS-BPANN模型在房产税基批量评估中可以实现低成本、高效率、评估结果科学准确的要求,为研究我国房产税基批量评估提供了一定的思路。

Since the release of the Outline of the 14th Five-Year Plan and 2035 Vision for National Economic and Social Development of the People's Republic of China in 2021,it has proposed to promote the property tax legislation,improve the local tax system,and ensure the implementation of the property tax from the legal level.As a complicated system engineering,the bulk evaluation of property tax base has complex and diverse basic data,and it needs to take into account both fairness and efficiency.This problem can be well solved with the help of big data and computer intelligence,and the evaluation results are scientific and accurate.Based on rough set theory and BP neural network,this research builds a batch evaluation model of property tax base,identifies and eliminates 7 redundant attributes that have little impact on the property tax base,screens out 20 significant characteristic variables,and verifies them through the sample data of 90o0 second-hand ordinary residents'housing transactions in Guangzhou.The results show that,RS-BPANN model can achieve low cost,high efficiency and scientific and accurate evaluation results in the batch evaluation of property tax base,which provides a certain idea for studying the batch evaluation of property tax base.