Personalized Student Attribute Inference
This work addresses the challenge of early intervention for at-risk students in educational settings, though it appears incremental as it builds on existing machine learning methods with a personalized twist.
The paper tackles the problem of predicting student performance to identify those at risk of failing a course, comparing a naive approach using existing attributes with a personalized method called PSAI that creates custom attributes for each student, resulting in improved prediction accuracy.
Accurately predicting their future performance can ensure students successful graduation, and help them save both time and money. However, achieving such predictions faces two challenges, mainly due to the diversity of students' background and the necessity of continuously tracking their evolving progress. The goal of this work is to create a system able to automatically detect students in difficulty, for instance predicting if they are likely to fail a course. We compare a naive approach widely used in the literature, which uses attributes available in the data set (like the grades), with a personalized approach we called Personalized Student Attribute Inference (PSAI). With our model, we create personalized attributes to capture the specific background of each student. Both approaches are compared using machine learning algorithms like decision trees, support vector machine or neural networks.