Analyzing The Influence Of Higher Education On Knowledge Management In Cyprus: An Advanced AI Approach Using Random Forest Classifiers

Abstract

This research article ventures into a novel exploration of the impact of higher education on knowledge management (KM) within the unique socio-economic context of Cyprus, a small island developing state. In an era where knowledge acts as a cornerstone for economic growth and societal progress, understanding this relationship is of paramount importance. The intricacies involved in this explo- ration are particularly pronounced in regions like Cyprus, which face distinct developmental challenges. At the heart of this study is the role of higher education institutions (HEIs) in Cyprus. These institutions are more than just academic centers; they are crucial in the processes of knowledge creation, dissemination, and application. This study is dedicated to examining how these facets of higher education contribute significantly to the enhancement of KM practices, a vital component for the country’s advancement in both economic and social arenas. Adopting a cutting-edge approach, this study utilizes a Random Forest Classifier, an advanced artificial intelligence (AI) algorithm. This choice marks a departure from the previously considered Structural Equation Modeling (SEM), bringing in a method known for its robustness and ability to handle complex, multifaceted datasets. The Random Forest model provides an in-depth analysis and predictive insights into the dynamics between higher education and KM. It is uniquely posi- tioned to identify, analyze, and predict the influence of various higher education aspects on KM practices, including knowledge creation, sharing, and application. The research harnesses secondary data, comprising academic publications, government and institutional reports, and statistical data from educational and economic databases. This rich dataset enables a comprehensive analysis of the impact of higher education on KM in Cyprus. A critical aspect of this study is the systematic model evaluation. The Random Forest Classifier is meticulously optimized and assessed through cross-validation techniques to ensure reliability and validity. Key performance metrics such as accuracy, precision, recall, and F1-score are employed to evaluate the model, providing a holistic view of its predictive power.