Prediction of children’s learning effectiveness using data mining technology

Abstract

This study aimed to predict children's learning effectiveness using data mining (DM) technology. The expansion of academic institutions is happening very rapidly since both the public and private sectors are opening up fresh institutions. Medium- and relatively low-risk learners nevertheless continue to confront unemployment. Thus, a novel fine-tuned seagull-optimized weighted k-nearest neighbor (FSOA-KNN) strategy was used in this work to increase the effectiveness of the kids' learning. Three hundred students participated in this study, and their features were gathered and examined. To improve the prediction performance, gathered data samples are used for pre-processing procedures. The proposed approach is put into practice and its effectiveness is evaluated using metrics for accuracy, recall, f-measure, and precision. The study results found that the proposed model has provided an accuracy of 98.7%, which helps in forecasting children's learning efficiency. Additionally, this article aids in identifying the students that require extra guidance or counseling from a teacher who provides high-quality instruction.