Predicting student performance in a blended learning environment using learning management system interaction data

Purpose Student attritions in tertiary educational institutes may play a significant role to achieve core values leading towards strategic mission and financial well-being. Analysis of data generated from student interaction with learning management systems (LMSs) blended (BL) environments assist the identification students at risk failing, but what extent this be possible is unknown. However, existing studies are limited address issues scale. Design/methodology/approach This study develops new approach harnessing applications machine (ML) models on dataset, that publicly available, relevant attrition identify potential risk. The dataset consists by LMS for their BL environment. Findings Identifying through an innovative will promote timely intervention process, such as improving academic progress. To evaluate performance proposed approach, accuracy compared other representational ML methods. Originality/value best algorithm random forest 85% selected support educators implementing various pedagogical practices improve students’ learning.