Scholarlink

With the growing digitization, project management is experiencing AI-driven forecasting and classification analysis with the aid of different intelligent algorithms to enhance its decision-making capability and efficiency. This study investigates how machine learning algorithms like the Long Short-Term Memory (LSTM) can analyze project progress data and assist in strategic decision-making. Using real-world project data from the energy sector, this study assesses LSTM models’ ability to provide relevant insights for project managers. The results indicate that training on multiple projects improves forecasting accuracy, reducing the Root Mean Squared Error (RMSE) by 37% when training on two projects instead of one. Aside from some limitations, the study presents how the machine learning model can be useful as a decision support tool for project managers in different complex projects. The results also offer valuable perspectives on the use of intelligent algorithms to enhance resource allocation, planning, and better project management.

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

Investigating the Applicability of Long Short-Term Memory (LSTM) Algorithm in Project Decision-Making: A Case Study in ML-Driven Forecasting

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Mirza Muntasir Nishat,
  • Magnus Olai Aarvold,
  • Wilhelm Jan Hartvig,
  • Nils O. E. Olsson

摘要

With the growing digitization, project management is experiencing AI-driven forecasting and classification analysis with the aid of different intelligent algorithms to enhance its decision-making capability and efficiency. This study investigates how machine learning algorithms like the Long Short-Term Memory (LSTM) can analyze project progress data and assist in strategic decision-making. Using real-world project data from the energy sector, this study assesses LSTM models’ ability to provide relevant insights for project managers. The results indicate that training on multiple projects improves forecasting accuracy, reducing the Root Mean Squared Error (RMSE) by 37% when training on two projects instead of one. Aside from some limitations, the study presents how the machine learning model can be useful as a decision support tool for project managers in different complex projects. The results also offer valuable perspectives on the use of intelligent algorithms to enhance resource allocation, planning, and better project management.