2728. AI-Enhanced Full-Objective MCDM: A Data-Driven Approach for Sustainable Decision-Making
Invited abstract in session TA-30: Production and Transportation, stream Advanced Lot Sizing and Inventory Strategies .
Tuesday, 8:30-10:00Room: Maurice Keyworth 1.05
Authors (first author is the speaker)
| 1. | Sarfaraz Hashemkhani Zolfani
|
| School of Engineering, Universidad Catolica del Norte |
Abstract
As decision-making becomes increasingly complex in modern society, the need for objective, data-driven approaches in Multi-Criteria Decision-Making (MCDM) is more critical than ever. Traditional weighting methods often rely on subjective judgment, which can introduce bias and inconsistencies. This study explores the advancement of full-objective MCDM methods, such as ITARA, CRITIC, and MEREC, and their integration with Artificial Intelligence (AI) and Machine Learning (ML) to enhance decision-making processes.
By leveraging AI, full-objective methods can be automated, adaptive, and scalable, allowing real-time analysis of large datasets. Machine learning techniques, such as clustering, deep learning, and reinforcement learning, can refine weight assignment, identify patterns, and optimize decision outcomes. Additionally, AI-powered Intelligent Decision Support Systems (IDSS) can enhance transparency and interpretability, making MCDM more accessible for policymakers and industry leaders.
A key focus of this study is the role of AI-driven MCDM in sustainable development. By improving resource allocation, climate resilience planning, and green infrastructure development, these models can support evidence-based policies for urban sustainability, energy efficiency, and environmental conservation.
Keywords
- OR in Sustainability
- Artificial Intelligence
- Decision Support Systems
Status: accepted
Back to the list of papers