Forecasting sustainable development level of selected Asian countries using M-EDAS and k-NN algorithm

Abstract

This study aims to forecast the sustainable development levels of countries with the least possible parameters based on social, economic, and environmental dimensions. For this purpose, a hybrid model consisting of multi-criteria decision-making and machine learning methods is proposed. First, using the M-EDAS method, selected Asian countries were ranked based on the main goals of the Sustainable Development Report. By using ranking findings, sustainability development levels were determined for 2017–2020. Using the last two years before the relevant year as a training dataset, the sustainable development levels determined for 2019-2020 were estimated using two basic macroeconomic variables. 2020 forecast findings are not successful as 2019. Additionally, the findings obtained from the ranking analysis were evaluated using Spearman's correlation to compare the periods before and during the COVID-19 pandemic.