Uncertainty Modelling in Risk-averse Supply Chain Systems Using Multi-objective Pareto Optimization

TL;DR

This paper introduces a Pareto Optimization methodology using genetic algorithms to model uncertainties in supply chain systems, aiming to create robust, risk-averse models that outperform classical methods.

Contribution

The paper presents a novel Pareto Optimization approach for uncertainty modeling in supply chains, explicitly bounding entropy and improving robustness over traditional algorithms.

Findings

Pareto Optimization effectively handles uncertainties in supply chains.

The approach outperforms classical genetic algorithms and MILP models.

Results demonstrate increased robustness and reactiveness in supply chain models.

Abstract

One of the arduous tasks in supply chain modelling is to build robust models against irregular variations. During the proliferation of time-series analyses and machine learning models, several modifications were proposed such as acceleration of the classical levenberg-marquardt algorithm, weight decaying and normalization, which introduced an algorithmic optimization approach to this problem. In this paper, we have introduced a novel methodology namely, Pareto Optimization to handle uncertainties and bound the entropy of such uncertainties by explicitly modelling them under some apriori assumptions. We have implemented Pareto Optimization using a genetic approach and compared the results with classical genetic algorithms and Mixed-Integer Linear Programming (MILP) models. Our results yields empirical evidence suggesting that Pareto Optimization can elude such non-deterministic errors and is a formal approach towards producing robust and reactive supply chain models.