An RBF Neural Network Approach to Predict Preschool Teachers Integrative-Qualitative Intentional Behavior Based on Marzano’s Model of Teaching Effectiveness

The educational organizational climate denotes the composite interplay of relational, social, psychological, affective, intellectual, cultural, and moral elements that shape the landscape of educational and administrative activities within an educational institution. This study employs a rigorous analytical approach, utilizing the theoretical underpinnings of the theory of planned behavior framework and Marzano's Model of Teaching Effectiveness to assess preschool instructors’ deliberate integrative-qualitative behaviors. The Marzano Model defines educational practices and provides resources to teachers and administrators to assist them in becoming more effective. This investigation presumes that the four domains measured by Marzano’s Model of Teaching Effectiveness effectively predict preschool teachers integrative-qualitative intentional behavior, employing a Radial Basis Function Neural Network approach. An online survey of preschool instructors from Romania yielded a sample of 200 accurate answers. In this study, Marzano's Model of Teaching Effectiveness scale is utilized to assess preschool instructors’ efficacy in relation to purposeful integrative-qualitative behaviors, which are assessed using the IQIB scale. Utilizing a Radial Basis Function Neural Network approach, preschool teachers integrative-qualitative intentional behavior is correctly classified in 76% instances based on their responses to Marzano’s teaching effectiveness scale, confirming our hypothesis that neural networks represent a robust modeling tool for preschool teachers’ behavioral intention prediction. Analysis and consequences are presented from the perspective of sustainable educational management implemented in a top-down perspective. This chapter is dedicated to Acad. Florin Gheorghe Filip, to celebrate his 75th anniversary and his 15th anniversary as the Chairman of the Information Science and Technology Section of the Romanian Academy.