A language processing algorithm for predicting tactical solutions to an operational planning problem under uncertainty

TL;DR

This paper demonstrates how neural machine translation algorithms can rapidly predict solutions to stochastic discrete optimization problems, offering a fast alternative with acceptable accuracy for time-sensitive operational planning under uncertainty.

Contribution

It introduces a novel application of NMT algorithms for predicting solutions in stochastic optimization, emphasizing rapid computation suitable for real-time decision-making.

Findings

NMT can predict solutions within milliseconds.

Predictions are slightly less accurate than stochastic programming methods.

NMT offers faster solutions with less variability.

Abstract

This paper is devoted to the prediction of solutions to a stochastic discrete optimization problem. Through an application, we illustrate how we can use a state-of-the-art neural machine translation (NMT) algorithm to predict the solutions by defining appropriate vocabularies, syntaxes and constraints. We attend to applications where the predictions need to be computed in very short computing time -- in the order of milliseconds or less. The results show that with minimal adaptations to the model architecture and hyperparameter tuning, the NMT algorithm can produce accurate solutions within the computing time budget. While these predictions are slightly less accurate than approximate stochastic programming solutions (sample average approximation), they can be computed faster and with less variability.