Predicting Education Quality and Standards in Higher Educational Institutions Using Hybrid XGBoost and Logistic Regression Models

Demand for HE has skyrocketed due to systemic changes in the last ten to twenty years. Higher standards of education and higher levels of student accomplishment in primary and secondary schools are largely responsible for this upsurge. Rising demand from the public and the government, which aims to establish the country as a regional centre for intellectual success, has caused competition in the higher education sector to reach monopolistic levels. These changes have had a major influence on HEIs, therefore new ways of assessing and meeting student needs are required. A data-driven strategy is utilised to improve decision-making in HEIs. To improve the quality of data, data must undergo preprocessing, which includes cleaning, integration, reduction, and transformation. Students’ data is efficiently analysed using the LR-XGB algorithm, which is a hybrid model for predicting customer attrition that combines LR with XGB. A remarkable 97% accuracy was achieved when the suggested model was used to forecast student attrition in HEIs. The study emphasises the need of advanced prediction models in HEIs and the rising demand and competitiveness for higher education. In order to stay ahead of the competition in the ever-changing educational landscape, HEIs can increase student retention rates by using data-driven tactics.