Learning enabled optimization for data and decision sciences

2019-03-21Several emerging applications call for a fusion of statistical learning (SL) and stochastic programming (SP). The Learning Enabled Optimization paradigm fuses concepts from these disciplines in a manner which not only enriches both SL and SP, but also provides a framework which supports rapid model updates and optimization, together with a methodology for rapid model-validation, assessment, and selection. Moreover, in many “big data/big decisions” applications, these steps are repetitive, and realizable only through a continuous cycle involving data analysis, optimization, and validation. This thesis sets forth the foundation for such a framework by introducing several novel concepts such as statistical optimality, hypothesis tests for model-fidelity, generalization error of stochastic programming, and finally, a non-parametric methodology for model selection. These new concepts provide a formal framework for modeling, solving, validating, and reporting solutions for Predictive Stochastic Programming (PSP). We illustrate the PSP framework by applying it to an inventory control model in which we use demand data available for ARIMA modeling in the statistical package “R”. In addition, we introduced a computational Operations Research exchange Platform, which is intended to help users to build the entire pipeline of LEO applications in software