Title: Learning to Sort: Hybrid AI-Based Adaptive Sorting for Real-Time Logistics Automation
Authors: Reema Abu Zaina, Samy S. Abu-Naser
Volume: 10
Issue: 7
Pages: 91-96
Publication Date: 2026/07/28
Abstract:
Sorting algorithm selection is a fundamental challenge in computer science because the performance of sorting algorithms varies according to dataset characteristics. This theoretical study examines the role of machine learning in improving algorithm selection by analyzing previous research on sorting algorithms and intelligent selection techniques. The paper reviews the characteristics of widely used sorting algorithms, including Quick Sort, Merge Sort, Heap Sort, Insertion Sort, and Timsort, and discusses how machine learning can support adaptive algorithm selection based on dataset features. Although no experimental implementation is conducted, the study proposes a conceptual framework illustrating how machine learning may enhance sorting efficiency and reduce the limitations of manual algorithm selection. The findings suggest that intelligent algorithm selection represents a promising direction for future research in algorithm optimization and adaptive computing.