Scholarlink

Stock market forecasting for real estate companies is a complex challenge due to the influence of economic, financial, and political factors. This study presents a relative analysis of AI and profound deep learning models for predicting stock prices in the real estate sector. Models like Recurrent Neural Networks (RNN), Gated Recurrent Units (GRU), Long Short-Term Memory (LSTM), Linear Regression, Auto-Regressive Integrated Moving Average with Exogenous inputs (ARIMAX), Fast Fourier Transform (FFT), Random Forest, and TimesNet were evaluated. The strengths and weaknesses of each model are assessed to determine their effectiveness in this forecasting task. By analyzing performance metrics such as mean squared error, root mean squared error, and mean absolute percentage error, this study aims to provide valuable insights for investors and analysts to make informed decisions based on the predictive capabilities of these models.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Comparative Analysis of Machine Learning and Deep Learning Models for Real Estate Stock Price Forecasting Prediction

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Prudhvi Krishna Thandra

摘要

Stock market forecasting for real estate companies is a complex challenge due to the influence of economic, financial, and political factors. This study presents a relative analysis of AI and profound deep learning models for predicting stock prices in the real estate sector. Models like Recurrent Neural Networks (RNN), Gated Recurrent Units (GRU), Long Short-Term Memory (LSTM), Linear Regression, Auto-Regressive Integrated Moving Average with Exogenous inputs (ARIMAX), Fast Fourier Transform (FFT), Random Forest, and TimesNet were evaluated. The strengths and weaknesses of each model are assessed to determine their effectiveness in this forecasting task. By analyzing performance metrics such as mean squared error, root mean squared error, and mean absolute percentage error, this study aims to provide valuable insights for investors and analysts to make informed decisions based on the predictive capabilities of these models.