基于PSO-LSTM的区域二手房价预测方法研究
Research on Regional Second-hand Housing Price Prediction Method Based on PSO-LSTM
周昌堉 1李长云1
作者信息
- 1. 湖南工业大学,湖南 株洲 412007
- 折叠
摘要
探究房价趋势是一个高度复杂且充满非线性特征的研究难题.针对目前二手房价预测精度低的问题,文章提出了基于PSO-LSTM的区域二手房价预测方法.粒子群算法通过对LSTM模型进行优化,找到最优的参数组带入PSO-LSTM模型中,进而得到更符合实际情况的预测结果.文章通过湖南省株洲市天元区的二手房价时间序列数据集对PSO-LSTM模型进行训练,并与LSTM神经网络模型进行了对照分析.实验结果显示,PSO-LSTM模型对于区域二手房价的预测精度更优.
Abstract
Exploring the trend of housing prices is a highly complex and full of nonlinear features research challenge.Aiming at the current problem of low accuracy of second-hand housing price prediction,this paper proposes a regional second-hand housing price prediction method based on PSO-LSTM.The Particle Swarm Optimization optimizes the LSTM model to find the optimal parameter group and incorporate it into the PSO-LSTM model,and then get the prediction results that are more in line with the actual situation.In this paper,the PSO-LSTM model is trained by the time series dataset of second-hand housing price in Tianyuan District,Zhuzhou City,Hunan Province,and the PSO-LSTM model is analyzed against the LSTM neural network model.The experimental results show that the PSO-LSTM model has better prediction accuracy for regional second-hand housing prices.
关键词
区域二手房价预测/时间序列/PSO-LSTM模型/LSTMKey words
regional second-hand housing price prediction/time series/PSO-LSTM model/LSTM引用本文复制引用
出版年
2024
国家科技期刊平台
NSTL
万方数据