June 30th, 2020, PhD student Sergei Kornilov defended his dissertation: "Assessing Organizational Efficiency under Macroeconomic Uncertainty in Decision Support Systems: Ensemble Methods in Machine Learning with Two-Stage Nonparametric Efficiency Models“.

Kornilov notes that the modern environment, where we all live in, is the subject of constant changes over time. There is evidence, both from mass-media and science, that the modern economic setting is characterized by an increasing information flow gathered for the decision-making process, growing global competition on the macroeconomic level and limited physical resources.

With developing of technologies, the opportunity cost is getting higher on an explosive scale. Thus, the assessing of effectivity plays an enormous role in the decision-making process.

The large number of studies shows that assessment of efficiency analysis has become an important topic in operational research, public policy, energy-environment management, and regional development. There is a clear shift to more intelligent decision support systems adopting a wide range of information sources from financial ratios, financial statements to mathematical modeling and evaluations.

The research methods used in the study comprise analysis, synthesis and comparison of scientific literature to characterize uncertainty and efficiency. Due to the growing interest in machine-learning techniques and BigData, data-driven approaches are becoming very important in many scientific areas and real-world applications.

The main focus of the study was to elaborate approaches to carry out a framework for nonparametric efficiency assessment, which is on the one hand reinforced by economic science and on another hand, taking advantage of the machine learning algorithms to create plausible estimation results.