Scholarlink

This study utilizes machine learning algorithms for population forecasting, crucial for national planning. Employing time series analysis on historical population data, we used algorithms including Facebook's Prophet, LSTM, state space model, Holt–Winters, and SARIMA for their proficiency in handling time series data. Our results show high accuracy, with Prophet achieving a mean absolute percentage error of 0.48% and LSTM a root mean squared error of 300020.64. This approach enables precise, region-specific population predictions, beneficial for urban planning and environmental management, marking a significant advancement in using machine learning for reliable population forecasts and strategic national decision-making.

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

Machine Learning Modeling for Population Forecasting

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • F. M. Tanmoy,
  • Zobaida Hossain,
  • Orin Tasfia,
  • Md. Abrar Hamim,
  • Md. Sadekur Rahman,
  • Md. Tarek Habib

摘要

This study utilizes machine learning algorithms for population forecasting, crucial for national planning. Employing time series analysis on historical population data, we used algorithms including Facebook's Prophet, LSTM, state space model, Holt–Winters, and SARIMA for their proficiency in handling time series data. Our results show high accuracy, with Prophet achieving a mean absolute percentage error of 0.48% and LSTM a root mean squared error of 300020.64. This approach enables precise, region-specific population predictions, beneficial for urban planning and environmental management, marking a significant advancement in using machine learning for reliable population forecasts and strategic national decision-making.