Machine learning meets climate readiness: unlocking the power of renewable energy investments

Purpose: This paper aims to evaluate the impact of renewable energy investment on climate readiness within the MEAN region using the ND-Gain index, which includes extensive information on climate adaptations globally. Design/methodology/approach: The study used the time from 2002 to 2020 for 14 MENA countries. Both the traditional and machine learning techniques, such as the random effect model based on the result of the Hausman test, and decision tree, random forest, and gradient boosting, were used to capture both linear and non-linear relationships. Findings: The results dictate that renewable energy investment enhances climate readiness, but only slightly. And the most important variable in that regard is GDP per capita. The results of the machine learning technique were more robust, indicating the presence of non-linear relationships among data. Originality/value: This study presents three key contributions. First, it utilizes the ND-GAIN index, which has not been employed in prior literature. Second, it integrates both traditional econometric methods and machine learning techniques to produce more robust and comprehensive insights. Third, it focuses on the MENA region, a context that remains underexplored in existing research on climate readiness.