Resilience, an increasingly prominent concept in both academic research and industrial practices, refers to the adaptability and ability of supply chains to manage and recover from disruptions. As organizations face growing challenges from global uncertainties, natural disasters, and market volatility, resilience has become a critical priority. Artificial Intelligence (AI) is increasingly recognized as a powerful enabler of supply chain resilience by improving the ability to anticipate, detect, and respond to disruptions using data-driven insights. In addition to AI, technologies such as Cyber-Physical Systems and Digital Twins enhance real-time visibility and scenario planning, contributing to more adaptive and integrated supply chains. This study aims to identify the key factors influencing supply chain resilience and develop a predictive model based on a dataset comprising KPIs, strategic insights, and resilience metrics needed for our study. A comparative analysis of machine learning, deep learning, and ensemble-based hybrid models is conducted to determine the most accurate and robust predictive approach. The findings support the development of a framework that enables organizations to strengthen their resilience through data-driven strategies and technology adoption.