A Comprehensive Review of Artificial Intelligence, Machine Learning, and Generative Models for Intelligent Decision-Making Across Modern Computational Domains

Abstract

Machine Learning (ML) and Artificial Intelligence (AI) have found their way into the perennial categories of valuable tools used to make intelligent decisions in data-intensive and complex spaces. The ongoing accelerated research and development in the supervised learning field, deep learning, generative algorithms, and signal processing applications have facilitated effective solutions to financial, medical, intelligent transportation system, Internet of Things (IoT), and cyber-physical infrastructures. Rule-based and statistical methods prove often to be not scalable or generalizable in regard to heterogeneous, in large dimensional, and dynamically changing data. This in turn is leading to the adoption of data-driven and learning-based solutions that can be used to aid in prediction, automation and adaptive intelligence. The current review paper provides a synthesis of the most recent research advances in the field of AI-based decision-support systems and dwells upon the algorithmic core, specific areas of application, and trends. The article summarizes the findings of papers dealing with financial anomaly detection, learning analytics, radiomics-aided medical imaging, IoT-powered intelligent systems and generative artificial intelligence as well as cutting-edge signal processing systems. The most critical challenges associated with the interpretability, data quality, scalability, security, and ethical governance are under consideration. The review ends with an overview of the future research directions to explainable, multimodal, and responsible AI systems that will be able to work properly in the real-world settings.

DOI: https://doi-ds.org/doilink/01.2026-18381397