Advances in Artificial Intelligence and Machine Learning for Intelligent Decision-Making Systems

Abstract

Intelligent decision-making systems, which augment or automate human judgment through data-driven models, have become central to domains ranging from healthcare diagnosis and financial risk assessment to industrial control, supply chain management, and autonomous systems. Recent advances in artificial intelligence (AI) and machine learning (ML) — including deep learning, reinforcement learning, and increasingly large foundation models — have substantially expanded the scope, accuracy, and autonomy of such systems, while simultaneously raising new demands for transparency, robustness, and effective human-AI collaboration. This paper presents a comprehensive review of advances in AI and ML for intelligent decision-making systems, covering the conceptual foundations and architecture of decision support systems, the principal machine learning paradigms underpinning modern decision-making — supervised and predictive modeling, reinforcement learning, multi-criteria and hybrid decision models, and large AI model-driven decision-making — and the role of explainable AI (XAI) in fostering trust and accountability. The review surveys representative application domains, including healthcare, finance, industrial automation, supply chain and logistics, and autonomous systems, and critically examines open challenges related to data quality and bias, interpretability, uncertainty quantification, human-AI collaboration, and ethical and regulatory considerations. The paper concludes by identifying promising future research directions, including trustworthy and human-centered decision-making, integration of large language and foundation models into decision pipelines, and real-time, low-latency interpretable decision support. This review is intended to serve as a consolidated reference for researchers and practitioners designing robust, transparent, and effective AI-driven decision-making systems.