Pages 501–508
Abstract
Research summary supplied by the authors
The footwear manufacturing sector, particularly full shoe production lines, continues to rely heavily on Manual Monitoring Processes (MMP) for production tracking, quality control, and decision-making. Such dependence on human-centric monitoring leads to inefficiencies, limited transparency, delayed corrective actions, and challenges in achieving sustainable manufacturing objectives. This research investigates the integration of Artificial Intelligence (AI) and Machine Learning (ML) frameworks to transform conventional footwear production lines into intelligent, data-driven manufacturing systems. The study aims to comprehensively map the shoe production process, quantify the limitations of MMP using secondary macroeconomic indicators from the World Bank (2001– 2023) and primary data collected from leather footwear manufacturing units, and develop AI/MLenabled monitoring architectures for real-time production transparency. Methodologically, the work employs systematic literature review, workstation-level data acquisition, vector autoregressive modelling, and interrupted time series analysis to evaluate production dynamics. AI/ML-based simulation and visualization tools are designed, validated at laboratory scale, and proposed for phased factory-level deployment. Preliminary results reveal significant deficiencies in scalability, responsiveness, and predictive capability within MMP-driven systems, while AI/ML integration demonstrates strong potential for enhanced productivity, sustainability, and intelligent decision support. The study positions intelligent manufacturing as a critical enabler for the future competitiveness of footwear start-ups, MSMEs, and large-scale production units.