Two-Stage Bi-Objective Stochastic Models for Supplier Selection and Order Allocation Under Uncertainty
Year: 2025
Type: article
Abstract: In supply chain management practices, supplier selection (SS) is a critical strategic planning activity that usually constitutes an ex ante decision made under uncertainty, whereas order allocation (OA) represents a subsequent operational decision determined ex post, contingent upon both the selected suppliers and actual operational conditions observed during the execution phase—specifically, the realized scenarios of uncertain circumstances. The practical performance of an SS decision inherently depends on its subsequent OA outcomes, while the OA decision itself is constrained by the preceding SS choices. Nevertheless, existing studies typically tackle the SS and OA problems separately or formulate them within a single-stage programming model, failing to adequately capture their sequential interdependence and the impact of OA on SS evaluation. To address this gap, this study develops novel two-stage bi-objective stochastic programming models in which the first-stage SS decisions are evaluated based on two key criteria—total cost and purchasing value—both of which depend on the second-stage OA decisions in response to realized operational scenarios. The stochastic performance of a given SS scheme, arising from adaptive OA decisions under uncertainty, is measured by expected value and conditional value-at-risk. An integrated approach combining weighted-satisfaction sum, linearization, Monte Carlo simulation, and genetic algorithm is developed to solve the models. Computational experiments demonstrate the effectiveness of the proposed methodology and reveal the influence of objective preferences and risk-aversion levels on the optimal supplier selection.
Source: Systems
Authors: Lingzhen Zhang, Ke Wang
Institutions: Tongji University, Shanghai University
Language: English
Field: Decision Sciences
Domain: Social Sciences
Open Access status: gold
Estimated APC paid: $2,896
OpenAlex ID: W7117305227