Research on Multi-modal Transportation Decision-making and Risk Control Strategies under Time-sensitivity Constraints

Abstract

This paper investigates the conflict between consumer demands for prompt delivery and the uncertainty of actual transit times in the e-commerce era. A novel cost optimization model is proposed that integrates transportation costs and penalty costs, aiming to optimize transportation mode selection while minimizing both explicit and implicit costs. By analyzing historical order data, the study fits the actual transit times for various transportation modes into normal distribution functions. Utilizing the Sample Average Approximation (SAA) method, the expected objective function is modeled in Python and solved using the Gurobi optimizer to determine the recommended transportation modes and associated costs. A comparison between actual costs and model-derived results indicates that the proposed model significantly reduces penalty costs and lowers total operational costs. Consequently, this approach safeguards corporate goodwill and mitigates intangible losses that are otherwise difficult to quantify. The findings suggest that enterprises should look beyond standalone transportation expenses and adopt a comprehensive cost model that incorporates penalty-based risk factors.