Leveraging Prerequisites Engineering Students for Monitoring and Predicting Using Machine Learning

This study investigates the impact of leveraging prerequisite grades on first-year engineering students' performance. The primary goal of educational systems is to provide students with valuable and practical knowledge. Educational institutions devote a significant amount of their resources and efforts to evaluating students' performance to make learning decisions according to their priorities. The study explores and examines the significant effect of monitoring students' academic performance and highlights the value of decision-making and prediction tools in academic learning pathways to enhance the learning outcomes process. By analyzing performance, educators can identify students who require special attention and interventions to improve their academic achievements. Machine learning-based algorithms, such as decision tree algorithms and random forests, are employed to predict students' academic performance. The study compares the performance of two algorithms with existing ones using metrics like the confusion matrix, accuracy, precision, and recall. Utilizing technology-assisted learning platforms to collect educational data can enable the analysis of student behavior, leading to a better understanding of their challenges and facilitating their learning progress. Educational data empowers professionals to make informed decisions. Monitoring learning complements traditional classroom settings and allows teachers to assess students' progress, thereby reducing the likelihood of student failure. Forecasting students' academic performance has gained importance in research as it enables educators to address any issues that may arise promptly. Students typically have significant dropout rates and view basic engineering courses as difficult.