Predicting Tactical Solutions to Operational Planning Problems under Imperfect Information
This addresses computational bottlenecks in operations research for applications like rail transportation load planning, but it is incremental as it applies existing machine learning methods to a specific optimization context.
The paper tackles the problem of predicting tactical descriptions of operational solutions in two-stage stochastic programming where the second stage is computationally demanding, and results show that deep learning models achieve accurate predictions in milliseconds, with accuracy close to lower bounds from sample average approximations.
This paper offers a methodological contribution at the intersection of machine learning and operations research. Namely, we propose a methodology to quickly predict expected tactical descriptions of operational solutions (TDOSs). The problem we address occurs in the context of two-stage stochastic programming where the second stage is demanding computationally. We aim to predict at a high speed the expected TDOS associated with the second stage problem, conditionally on the first stage variables. This may be used in support of the solution to the overall two-stage problem by avoiding the online generation of multiple second stage scenarios and solutions. We formulate the tactical prediction problem as a stochastic optimal prediction program, whose solution we approximate with supervised machine learning. The training dataset consists of a large number of deterministic operational problems generated by controlled probabilistic sampling. The labels are computed based on solutions to these problems (solved independently and offline), employing appropriate aggregation and subselection methods to address uncertainty. Results on our motivating application on load planning for rail transportation show that deep learning models produce accurate predictions in very short computing time (milliseconds or less). The predictive accuracy is close to the lower bounds calculated based on sample average approximation of the stochastic prediction programs.