Capital Scheduling Decisions in Digital Supply Chain Finance based on Multi-Stage Stochastic Linear Programming

Abstract

The rapid evolution of financial technologies has transformed traditional supply chain management into a digitally integrated ecosystem, enabling real-time visibility and data-driven decision-making. This paper addresses the complex problem of capital scheduling within digital supply chain finance, where liquidity management is subject to significant uncertainties regarding market demand, repayment behaviors, and interest rate fluctuations. Unlike traditional static approaches, we propose a Multi-Stage Stochastic Linear Programming model that dynamically adjusts financing and repayment decisions over multiple time horizons. By leveraging the granular data availability inherent in digital platforms, the proposed framework allows financial planners to optimize working capital allocation while mitigating liquidity risks. We construct a scenario tree to represent the evolution of uncertain parameters and employ a decomposition algorithm to solve the resulting large-scale optimization problem. The study demonstrates that digital integration, when coupled with stochastic optimization, significantly outperforms deterministic planning methods by reducing the cost of capital and improving solvency ratios under volatile market conditions. The findings provide theoretical contributions to the intersection of operations research and financial engineering, offering practical guidelines for liquidity providers and supply chain managers operating in uncertain environments.