Tacit knowledge-informed approximate dynamic programming for last-mile delivery operations in online-to-offline pharmacies

Abstract

Purpose

Tacit knowledge in frontline operations is primarily reflected in the holders’ intuition about dynamic systems. Despite the implicit nature of tacit knowledge, the understanding of complex systems it encapsulates can be displayed through formalization methods. This study seeks to develop a methodology for formalizing tacit knowledge in a dynamic delivery system.

Design/methodology/approach

This study employs a structured survey to gather experiential knowledge from dispatchers engaged in last-mile delivery operations. This knowledge is then formalized using a value function approximation approach, which transforms tacit insights into structured inputs for dynamic decision-making. We apply this methodology to optimize delivery operations in an online-to-offline pharmacy context.

Findings

The raw system feature data are not strongly correlated with the system’s development trends, making them ineffective for guiding dynamic decision-making. However, the system features obtained through preprocessing the raw data increase the predictiveness of dynamic decisions and improve the overall effectiveness of decision-making in delivery operations.

Research limitations/implications

This research provides a foundational framework for studying sequential dynamic decision problems, highlighting the potential for improved decision quality and system optimization through the formalization and integration of tacit knowledge.

Practical implications

This approach proposed in this study offers a method to preserve and formalize critical operational expertise. By embedding tacit knowledge into decision-making systems, organizations can enhance real-time responsiveness and reduce operational costs.

Originality/value

This study presents a novel approach to integrating tacit knowledge into dynamic decision-making frameworks, demonstrated in a real-world last-mile delivery context. Unlike previous research that focuses primarily on explicit data-driven methods, our approach leverages the implicit, experience-based insights of operational staff, leading to more informed and effective decision-making strategies.

Citation

Yang, X., Luo, H., Nie, X. and Kong, X. (2025), "Tacit knowledge-informed approximate dynamic programming for last-mile delivery operations in online-to-offline pharmacies", Industrial Management & Data Systems, Vol. 125 No. 3, pp. 1078-1109. https://doi.org/10.1108/IMDS-09-2024-0874