Title: AI-Based Sorting Strategies for Real-Time Logistics and Supply Chain Automation
Authors: Wesam H. Ashour, Samy S. Abu-Naser
Volume: 10
Issue: 7
Pages: 104-112
Publication Date: 2026/07/28
Abstract:
The rapid expansion of digital supply chain ecosystems has created significant challenges in processing, organizing, and prioritizing large-scale real-time logistics data. Traditional sorting algorithms, including Quicksort, Merge Sort, and Heap Sort, remain fundamental computational techniques due to their efficiency and predictable performance; however, they are primarily designed for structured and relatively static datasets. Modern logistics environments generate continuous streams of dynamic data influenced by changing delivery priorities, inventory fluctuations, transportation disruptions, and unpredictable operational conditions. Consequently, conventional sorting approaches often lack the adaptability required for intelligent automation. This paper investigates an Artificial Intelligence (AI)-based adaptive sorting framework designed to enhance real-time logistics and supply chain operations. The proposed approach integrates classical sorting structures with Machine Learning (ML) and Deep Reinforcement Learning (DRL) techniques to dynamically determine sorting priorities based on contextual operational factors. Unlike traditional sorting methods that rely on predefined comparison rules, the proposed framework enables intelligent decision-making through continuous learning and real-time adjustment of priority values. The framework focuses on improving critical logistics processes, including shipment prioritization, warehouse sorting, dynamic routing, and inventory management. Performance evaluation is conducted conceptually using key operational metrics such as processing latency, throughput, and adaptability under changing supply chain conditions. The proposed AI-enhanced sorting strategy demonstrates the potential to transform conventional deterministic sorting mechanisms into intelligent, self-adaptive systems capable of supporting resilient and autonomous logistics networks.