摘要
二手房交易市场比重的增大,使得对于二手房房价预测构建模型有重要意义。选取合肥市2019年6月至2020年6月的二手房成交记录作为研究数据。针对BP神经网络模型易陷入局部最优和传统遗传算法的BP神经网络收敛速度过慢的不足,建立双链遗传算法的BP神经网络模型,对研究数据进行仿真训练,并检验了模型的泛化能力。实验结果表明使用模型在精度和收敛速度的双重考量下最优。
The increasing proportion of the second-hand housing market makes it important to build a model for the prediction of second-hand housing prices.This paper selects the transaction records of second-hand houses in Hefei City from June 2019 to June 2020 as the research data.The BP neural network model is easy to fall into the local optimum and the convergence speed of the traditional Genetic Algorithm is too slow.In this paper,the BP neural network model of Double-chain Genetic Algorithm is established,the research data are simulated and trained,and the generalization ability of the model is tested.The experimental results show that the proposed model is optimal under the consideration of both accuracy and convergence speed.
作者
刘海
LIU Hai(School of Economics,Anhui University,Hefei 230601,China)
出处
《价值工程》
2020年第29期3-6,共4页
Value Engineering
关键词
房价预测
BP神经网络
遗传算法
双链遗传算法
house price forecast
BP neural network
Genetic Algorithm
Double-chain Genetic Algorithm
