2025 ASEE Annual Conference & Exposition

This paper explores the use of machine learning to identify key factors that may connect to a student's academic performance and how it may be used to predict student learning outcome at an early stage, specifically, by utilizing two machine learning models: the Random Forest classifier and the Multi-Output classifier. The Random Forest Classifier is widely used for classification tasks. It operates by constructing multiple decision trees during training and selecting the mode of their predictions for a given input, identifying the most significant factors affecting outcomes. On the other hand, a Multi-Output Classifier is specifically designed for multi-label or multi-output classification tasks, where each instance can be linked to multiple labels or output variables. It may be used for predicting several target variables simultaneously, for example, assessing a student's grade and engagement level simultaneously, and our Multi-Output classifier uses a neural network backend. In this paper, several datasets sourced from Kaggle containing student background information and academic engagement and performance data were processed using the above two classifier models. The steps for cleaning, preparing and analyzing the data were discussed in this paper. The results show that the Random Forest classifier is very effective in identifying key factors that may connect to a student's academic engagement and performance such as number of units completed in previous semester, grades from previous semester, and tuition fee payment status with an accuracy of 85.9% for the predictions on the test data: 94.5% correctly on the prediction of non-dropouts and 67.9% correctly on the prediction of dropouts. Furthermore, the same set of data was processed by the Multi-Output Classifier neural network resulting in accuracy scores ranging from 83.5% to 94.2% for the five target variables, providing valuable insights to educators for advocating tailored support for at-risk students.