The Role of AI-Driven Analytics in Enhancing Operational Agility among Post-Pandemic Retail SMEs

• Abiodun Okunola

  Ladoke Akintola University Technology

  Author

The COVID-19 pandemic fundamentally disrupted retail small and medium enterprises (SMEs), exposing the fragility of intuition-based operational decision-making and accelerating demands for data-driven agility. While digital transformation has been widely studied, the specific contribution of AI-driven analytics to operational agility in post-pandemic retail SMEs remains underexplored, particularly regarding predictive accuracy and implementation pathways. This study addresses this gap by developing and validating a hybrid machine learning framework that integrates point-of-sale transaction data, inventory signals, and demand forecasts to enhance operational responsiveness. Using a quantitative, design-based research approach, the study analyzes a stratified sample of 412 retail SMEs across urban and semi-urban markets over 18 months (January 2023–June 2024). The hybrid Random Forest–XGBoost ensemble model achieved 89.4% predictive accuracy in forecasting stockout events and reduced inventory holding costs by 23.7% compared to static reorder baselines (p < 0.001). Feature importance analysis identified demand volatility, supplier lead-time variability, and promotional calendar density as the strongest predictors of agility outcomes. The findings demonstrate that AI-driven analytics can transform operational agility from a reactive posture to a predictive capability, with implications for SME managers, technology providers, and policymakers seeking to strengthen retail resilience in post-crisis economies.

• PDF

Copyright (c) 2026 Abiodun Okunola (Author)

This work is licensed under a Creative Commons Attribution 4.0 International License.