Machine Learning based Students Performance Evaluation for Decision Making of Dropout or Course Continuation

Abstract

Higher institutions are setup to provide quality education capable of transforming the level of awareness, knowledge, and the capacity of the human mind. In India, the educational sector has suffered many setbacks due to under development, economic hardship, insufficient budget and corruption. The academic performance of engineering students from their first year to the third year is very vital in terms of acquisition of foundational knowledge, and its impact on their final graduation Cumulative Grade Point Average (CGPA). It is often said that beyond the third year it is very challenging for a student to move from the current class of grade. Six data mining algorithms were considered, and a maximum accuracy of 91% was achieved. The result was verified using both linear and pure quadratic regression models. This creates an opportunity for identifying students that may graduate with poor results or may not graduate at all, so that early intervention may be deployed.