Leveraging the Synergy of AI and Optimization Models for Enhanced Problem Solving and Decision-Making
摘要截稿:
全文截稿: 2025-07-31
影响因子: 3.424
期刊难度:
CCF分类: 无
中科院JCR分区:
• 大类 : 工程技术 - 2区
• 小类 : 计算机:跨学科应用 - 2区
• 小类 : 工程:工业 - 2区
• 小类 : 运筹学与管理科学 - 2区
Overview
In recent years, both Artificial Intelligence (AI) and Optimization Models have emerged as powerful tools for problem-solving and decision-making across various domains. AI techniques, such as machine learning and natural language processing, have demonstrated their ability to extract patterns and insights from vast amounts of data. Lam et al. (2022), for example, introduced a cutting-edge exact algorithm for Multi Agent Path Finding, a set of combinatorial optimization problems rooted in AI and automated planning. They tackled scenarios where both space and time are discretized by applying the branch-and-cut-and price framework from mathematical optimization. They call for further research in this class of problem.On the other hand, Optimization Models offer systematic approaches to finding the best solutions to complex problems. Recent research indicates a growing necessity to incorporate more resilient analytical models that combine AI and optimization techniques (Doumpos et al., 2023; Gambella et al., 2021). For instance, studies have developed a feature-enhanced genetic programming method for the automatic design of high-quality dispatching rules for customer order scheduling in an offline learning strategy (Shi et al., 2021). As this research area is in its nascent phase, several various avenues and opportunities remain to enhance our comprehension of possibilities across diverse angles, encompassing problem categories, application domains, themes, and methodologies. This Special Issue aims to explore and advance the research on the combination of AI and Optimization Models to harness the complementary strengths of both methodologies and highlight the importance of their integration for achieving superior results in diverse applications
Guest editors:
Davood Golmohammadi, Ph.D. [Managing Guest Editor]Associate Professor of Management Science and Information SystemsCollege of ManagementUniversity of Massachusetts Bostondavood.golmohammadi@umb.edu
Prof. Diego A. de. J. Pacheco, PhD [Guest Editor]Aarhus Business School, DKAarhus Universitydiego@btech.au.dk
Kenneth J Klassen, MBA, PhD, PMP [Guest Editor]Professor of Operations ManagementGoodman School of Business, Brock Universitykklassen@brocku.ca
Mostafa Zandieh, PhD [Guest Editor]ProfessorDepartment of Industrial Management and Information TechnologyShahid Beheshti University, G.C., Tehran, Iranm_zandieh@sbu.ac.ir
Special issue information:
Contributions:
This Special Issue will enhance understanding in this important and emerging area of study as follows:
a. Comprehensive Problem Solving: The integration of AI and Optimization Models enables a more comprehensive approach to problem-solving, leveraging AI's ability to process large datasets and recognize complex patterns, while optimization techniques ensure the identification of optimal or near-optimal solutions.
b. Real-Time Decision-Making: By combining AI's capacity to analyze real-time data with optimization's ability to generate efficient solutions, organizations can make well-informed and timely decisions, particularly in dynamic and rapidly changing environments.
c. Enhanced Resource Utilization: Integrating AI and Optimization Models can lead to improved resource allocation and utilization, optimizing processes and minimizing costs across various domains like logistics, supply chain management, and energy consumption.
d. Multi-Dimensional Problem Domains: Complex real-world problems often involve multiple objectives and constraints. The combination of AI and Optimization Models provides a powerful approach to tackle multi-dimensional problem domains, offering a more nuanced understanding of trade-offs and balancing conflicting goals.
Importance of AI and Optimization Model IntegrationThe synergistic combination of AI and Optimization Models presents several compelling reasons for its significance:
a. Data-Driven Decision-Making: AI (including Analytics) is adept at extracting insights from data, but it often lacks the capability to make strategic decisions. When combined with Optimization Models, AI's data-driven insights can be translated into actionable decisions, enhancing the overall decision-making process.
b. Handling Uncertainty: Real-world problems frequently involve uncertainty and dynamic environments. AI's adaptive nature can assist in analyzing changing data patterns, while Optimization Models can create robust plans that adapt to uncertainties, resulting in more resilient systems.
c. Efficient Exploration of Solution Space: Optimization Models excel in searching vast solution spaces, but they can be limited by the complexity of the problem. AI, especially in the form of evolutionary algorithms or reinforcement learning, can assist in exploring diverse solution spaces efficiently, finding novel and unconventional solutions.
d. Personalization and Customization: AI can help identify individual preferences and behavior patterns, enabling Optimization Models to tailor solutions to specific user needs. This personalization can significantly enhance user experiences and outcomes in recommendation systems, personalized medicine, and marketing campaigns.
4. Applications
Articles that discuss the use of Analytics and Big Data to enhance problem solving are included under the broader umbrella of AI and Optimization. The integration of AI and Optimization Models has wide-ranging applications, including but not limited to:
a. Healthcare: Personalized treatment plans, drug discovery, scheduling (patient, doctor, nurse, OR, etc.), patient prioritization and resource allocation in healthcare can be optimized by integrating AI with optimization techniques, leading to improved patient outcomes and cost efficiency.
b. Transportation and Logistics: Optimizing routes, delivery schedules, and resource allocation in transportation and logistics can be significantly improved by incorporating AI techniques in the optimization process.
c. Finance and Investment: Combining AI's predictive capabilities with optimization techniques can lead to more accurate portfolio optimization, risk management, and trading strategies.
d. Manufacturing and Supply Chain: Optimizing production processes, inventory management, and supply chain logistics can be enhanced by leveraging AI to analyze demand patterns and predict disruptions.
Conclusion:
In conclusion, the integration of AI and Optimization Models represents a formidable alliance in problem-solving and decision-making across numerous sectors. By harnessing AI's data-driven insights and Optimization Models' ability to identify optimal solutions, organizations can achieve greater efficiency, make informed decisions in real-time, and navigate complex problem spaces with confidence. The potential applications of this combined approach are vast and can lead to transformative advancements in a wide range of fields