The impact of engineering students' performance in the first three years on their graduation result using educational data mining

Research studies on educational data mining are on the increase due to the benefits obtained from the knowledge acquired from machine learning processes which help to improve decision making processes in higher institutions of learning. In this study, predictive analysis was carried out to determine the extent to which the fifth year and final Cumulative Grade Point Average (CGPA) of engineering students in a Nigerian University can be determined using the program of study, the year of entry and the Grade Point Average (GPA) for the first three years of study as inputs into a Konstanz Information Miner (KNIME) based data mining model. Six data mining algorithms were considered, and a maximum accuracy of 89.15% was achieved. The result was verified using both linear and pure quadratic regression models, and R2 values of 0.955 and 0.957 were recorded for both cases. 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.