Document Type : Original Article
Authors
1
Department of Industrial Engineering, No.C., Islamic Azad University, Noor, Iran, Email: safarastegarmit@gmail.com
2
Corresponding author, Assistant Professor, Department of Industrial Engineering, QaS.C., Islamic Azad University, Qaemshahr, Iran, Email: ma.sadeghpour@iau.ac.ir
3
Assistant Professor, Department of Industrial Engineering, QaS.C., Islamic Azad University, Qaemshahr, Iran. Email: kourosh.nemati@iau.ac.ir
4
Assistant Professor, Department of Industrial Engineering, QaS.C., Islamic Azad University, Qaemshahr, Iran. Email: fa.harsej@iau.ac.ir
10.22091/jemsc.2026.15396.1354
Abstract
In the present research, a demand model for product development customization with a Marketing 5.0 approach is presented. In this regard, deep learning algorithms such as Long Short-Term Memory (LSTM) networks, Recurrent Neural Networks (RNN), and Deep Neural Networks (DNN) were used. Four features firm size, firm revenue, economic growth, and firm electricity consumption cost were considered as factors influencing demand. The results of implementing the deep learning algorithms showed that the Long Short-Term Memory neural network, with 95%, the Recurrent Neural Network with 94%, and the Deep Neural Network with 93% had the highest accuracy in demand forecasting. Furthermore, the firm's electricity cost had the most significant impact on the presented model, followed by firm revenue. The third rank belongs to firm size, and economic growth holds the final rank in terms of electricity demand in the industrial and business sectors.
Keywords
Main Subjects
)
Send comment about this article