A Comparative Analysis to Measure Scholastic Success of Students Using Data Science Methods

Abstract

AbstractPrognosticating students’ output remains a critical commotion for the sustainability of the global education segment. But, due to the vast volumes of data within educational databases, the challenge continues to be difficult. Conversely, certain institutions do not have programmers in place to analyze and track students’ progress. Aforementioned issue may be exacerbated by a short of appreciating of the value of forecasting students’ results. Furthermore, current research on concert forecast methods is still insufficient in identifying and persuading educators to use the most appropriate tool for forecasting students’ concert. The present study examines the most widely used data science techniques for forecasting student concert in previous studies in order to determine the most appropriate technology for forecasting student performance. This study’s findings revealed that the clustering algorithm is the best technique for forecasting student success because it provides reliable and precise results. Forecasting student success aids in the tracking of students’ progress, both pass and fail, and thus offers a window for early intercession and supervisory on the part of educators. The present incentive significantly aids in the promotion of the education segment by improving educational principles.KeywordsScholastic systemStudent performanceData science methods