Students performance modeling based on behavior pattern

Abstract

Academic performance of college students is the main concern of educational institutions. Effective and timely predicting performance is not only conducive to the school’s Ministry to improve the efficiency of supervision, but also helps students to develop good study habits. With the rapid construction of digital campus, university as the main range for students’ life can not only serve convenience but also record daily life. The popular using of smart card makes it easy to outline students behavior pattern with rich data. The purpose of our work is to predict students performance based on their behavior pattern and analyze the correlation between them. In this paper, we propose a general framework to model students performance. Firstly, we describe students behavior pattern and extract behavior features in two perspectives including statistics and relevance. Then we employ a multi-task model to learn performance of every course simultaneously. Our experiments on a real world data set of college students show a good outcome. We do a further analysis on relation between students behavior and academic performance. Moreover, our experiments indicate that our framework is feasible for early warning.