Document Type : Research Paper

Authors

• Ali Naghash Asadi
• Amin Mastourinejad
• Romina Aghili

Fouman Faculty of Engineering, College of Engineering, University of Tehran, Tehran, Iran

Abstract

Decision-making is a critical aspect of governance, and data mining and machine learning algorithms can significantly enhance this process. By leveraging predictive models generated through these algorithms, policymakers can make more informed and accurate decisions. Since such models rely on historical data, the Legatum prosperity index serves as a valuable source for this analysis. In this study, Bagging and Boosting algorithms are employed to develop predictive models and analyze various indicators across different continents. The results demonstrate the effectiveness of these algorithms in forecasting key indicators and reveal notable differences in the influential factors across regions. These findings can support policymakers in formulating targeted strategies to enhance governance and living standards, considering regional characteristics and priorities. Furthermore, providing predictive models for each indicator allows countries to forecast and assess the impact of improving a specific indicator on others.

Keywords

• Data mining
• Machine learning
• Prediction models
• Bagging and Boosting algorithms
• Legatum prosperity index