Neural Network Based Approach For Predicting Learning Effect In Pre-Service Teachers

Abstract

This study examines a neural network based approach for predicting learning effect in students of Primary School Mathematics teacher. This investigation takes the passing-grades of all courses taken by first year pre-service teachers, including General Mathematics, Pure Mathematics, Analysis I, Analysis II, Geometry, Linear Algebra-I and uses these passing-grades as the input of the back-propagation neural network (BPNN). Additionally, the passing-grades of professional core courses at the upperclassman level, including Analysis3, Special Teaching Methods 2, Elementary Number Theory, Algebra, Problem Solving, are used as the output of the BPNN. The research methodology adopted in this study aims to explore the utilization of the BPNN model as a supportive decision-making tool for predicting learning effect for students of Primary School Mathematics teacher.