Stochastic Collaborative Supply Chain Optimization With Fair Hierarchical Gain-Sharing

Horizontal supply chain collaboration (HSCC) offers substantial cost savings and carbon footprint reductions, yet commercial adoption remains hindered by non-scalable gain-sharing mechanisms and operational disruption risks. This study presents a scalable two-stage hierarchical framework for post-Pareto selection, integrating a two-stage stochastic mixed-integer linear program (MILP, Level 1) with an Equal Profit Method linear program (EPML, Level 2) to optimize multi-objective routing and equitable profit allocation across multi-partner logistics networks. Evaluated on a medium-scale benchmark network (15 partners, 8 demand nodes, and 50 stochastic scenarios), the framework achieves an alliance-wide cost reduction of 18.42% and a carbon reduction of 14.10% relative to non-cooperative baselines. At Level 2, the EPML engine executes in 0.32 s for 15 partners and 1.87 s for 30 partners, overcoming the exponential computational bottlenecks of traditional cooperative game theory methods while theoretically guaranteeing expected individual rationality $\left(E\left[\pi_i\right] \geq \pi_i^0\right)$, where $E\left[\pi_i\right]$ denotes partner $i$'s expected collaborative profit and $\pi_i^0$ denotes that partner's standalone baseline profit—provided that the selected physical solution satisfies the net-synergy feasibility condition $(\sum_{i \in I} E\left[\pi_i\right] \geq \sum_{i \in I} \pi_i^0)$, where $I$ is the set of alliance partners. The framework also achieves empirically verified core stability, with $e_{\max} \leq 0$, where $e_{\max}$ denotes the maximum excess across the tested subcoalition. Sensitivity analysis demonstrates robust customer fulfillment (99.59% service level) under high shortfall penalties $\left(p_j^{\text {pen}} \geq 2.5 \times p_j^{\text {sell}}\right)$ and a marginal abatement cost (MAC) of \$2,318.68 per metric ton of carbon dioxide equivalent (tCO$_2$e) at executive compromise configurations. To facilitate industry adoption, we translate these algorithmic outputs into a practical 4-step managerial decision protocol balancing ex-ante contractual rules, ex-post financial settlements, and alliance-level greenhouse gas (GHG) reporting boundaries. The framework effectively resolves the trade-off between allocation fairness and computational scalability in stochastic environments, providing supply chain decision-makers with a practical, mathematically rigorous, and computationally efficient post-Pareto decision-support tool to establish stable, equitable, and resilient horizontal logistics coalitions.

Authors

Publication Details

Journal
Journal of Engineering Management and Systems Engineering
Published
2026-11-19
DOI
https://doi.org/10.56578/jemse050407
Primary Topic
Supply Chain and Inventory Management
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Stochastic Collaborative Supply Chain Optimization With Fair Hierarchical Gain-Sharing

Asma Sbaï, Malika El Kyal, Hanan Ouhader
Journal of Engineering Management and Systems Engineering
Supply Chain and Inventory Management
article

Stochastic Collaborative Supply Chain Optimization With Fair Hierarchical Gain-Sharing

Asma Sbaï, Malika El Kyal, Hanan Ouhader
article en

Abstract

Horizontal supply chain collaboration (HSCC) offers substantial cost savings and carbon footprint reductions, yet commercial adoption remains hindered by non-scalable gain-sharing mechanisms and operational disruption risks. This study presents a scalable two-stage hierarchical framework for post-Pareto selection, integrating a two-stage stochastic mixed-integer linear program (MILP, Level 1) with an Equal Profit Method linear program (EPML, Level 2) to optimize multi-objective routing and equitable profit allocation across multi-partner logistics networks. Evaluated on a medium-scale benchmark network (15 partners, 8 demand nodes, and 50 stochastic scenarios), the framework achieves an alliance-wide cost reduction of 18.42% and a carbon reduction of 14.10% relative to non-cooperative baselines. At Level 2, the EPML engine executes in 0.32 s for 15 partners and 1.87 s for 30 partners, overcoming the exponential computational bottlenecks of traditional cooperative game theory methods while theoretically guaranteeing expected individual rationality $\left(E\left[\pi_i\right] \geq \pi_i^0\right)$, where $E\left[\pi_i\right]$ denotes partner $i$'s expected collaborative profit and $\pi_i^0$ denotes that partner's standalone baseline profit—provided that the selected physical solution satisfies the net-synergy feasibility condition $(\sum_{i \in I} E\left[\pi_i\right] \geq \sum_{i \in I} \pi_i^0)$, where $I$ is the set of alliance partners. The framework also achieves empirically verified core stability, with $e_{\max} \leq 0$, where $e_{\max}$ denotes the maximum excess across the tested subcoalition. Sensitivity analysis demonstrates robust customer fulfillment (99.59% service level) under high shortfall penalties $\left(p_j^{\text {pen}} \geq 2.5 \times p_j^{\text {sell}}\right)$ and a marginal abatement cost (MAC) of \$2,318.68 per metric ton of carbon dioxide equivalent (tCO$_2$e) at executive compromise configurations. To facilitate industry adoption, we translate these algorithmic outputs into a practical 4-step managerial decision protocol balancing ex-ante contractual rules, ex-post financial settlements, and alliance-level greenhouse gas (GHG) reporting boundaries. The framework effectively resolves the trade-off between allocation fairness and computational scalability in stochastic environments, providing supply chain decision-makers with a practical, mathematically rigorous, and computationally efficient post-Pareto decision-support tool to establish stable, equitable, and resilient horizontal logistics coalitions.

Journal of Engineering Management and Systems EngineeringVol. 5(4)
Supply Chain and Inventory Management
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon