Development of distributed LSTM framework to forecast transportation lead time

Utkarsh Mittal and Dilbagh Panchal

International Journal of Industrial and Systems Engineering, 2025, vol. 49, issue 4, 520-544

Abstract: This study aimed to develop an AI-based system to evaluate delivery complexities and reduce system vulnerabilities more accurately. The approach of the study is empirical where dataset from different systems is used to develop ML and DL models to forecast more accurately transportation time and improve profitability. Various models, e.g., linear regression, deep learning, and distributed long short-term memory (DLSTM) networks are used. It is found that the DLSTM regression model shows superior performance in forecasting the delivery times compared to the other models, achieving an accuracy of around 90%, as the model has the ability to handle complex and nonlinear relationships among variables. The findings underscore the potential of machine learning (ML) and deep learning (DL) in improving predictability and profitability aimed increasing digitalisation in global transportation.

Keywords: machine learning; deep learning; delivery time forecasting; profitability optimisation; fuzzy C means clustering; supply chain risk management. (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.inderscience.com/link.php?id=146067 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ids:ijisen:v:49:y:2025:i:4:p:520-544

Access Statistics for this article

More articles in International Journal of Industrial and Systems Engineering from Inderscience Enterprises Ltd
Bibliographic data for series maintained by Sarah Parker ().