Designing Predictive Autonomous Model for Primary School Dropout Risk Assessment using Double Edged Sword Algorithm

Abstract

Dropout rates in primary schools pose significant challenges to educational systems worldwide. As the objective of this research is to design a new autonomous prediction model that accurately identifies primary school students at risk of dropping out by considering a range of factors including student activities, concentration levels, motivation, curiosity, and behaviours related to learning and ethical values, the model aims to provide a comprehensive assessment of dropout risk. Utilizing advanced data mining and machine learning techniques, the study incorporates these multifaceted factors into the predictive model. The performance of the model is evaluated through various metrics to ensure its reliability and accuracy. The insights gained from this research will assist educators and policymakers in developing targeted interventions to enhance student engagement and reduce dropout rates. The core of our model employs an enhanced genetic algorithm, referred to as the "double-edged sword" algorithm, combined with a random forest algorithm. This combination results in superior performance and accuracy in predicting student outcomes compared to traditional methods. Our approach involves the creation of a tailored form designed to collect essential data from primary students and schools, focusing on the main parameters crucial for our model's predictions.