A Machine Learning Approach for Tracking and Predicting Student Performance in Degree Programs

Jie Xu, Kyeong Ho Moon, Mihaela Van Der Schaar

Research output: Contribution to journalArticle

17 Citations (Scopus)

Abstract

Accurately predicting students' future performance based on their ongoing academic records is crucial for effectively carrying out necessary pedagogical interventions to ensure students' on-time and satisfactory graduation. Although there is a rich literature on predicting student performance when solving problems or studying for courses using data-driven approaches, predicting student performance in completing degrees (e.g., college programs) is much less studied and faces new challenges: 1) Students differ tremendously in terms of backgrounds and selected courses; 2) courses are not equally informative for making accurate predictions; and 3) students' evolving progress needs to be incorporated into the prediction. In this paper, we develop a novel machine learning method for predicting student performance in degree programs that is able to address these key challenges. The proposed method has two major features. First, a bilayered structure comprising multiple base predictors and a cascade of ensemble predictors is developed for making predictions based on students' evolving performance states. Second, a data-driven approach based on latent factor models and probabilistic matrix factorization is proposed to discover course relevance, which is important for constructing efficient base predictors. Through extensive simulations on an undergraduate student dataset collected over three years at University of California, Los Angeles, we show that the proposed method achieves superior performance to benchmark approaches.

Original languageEnglish (US)
Article number7894238
Pages (from-to)742-753
Number of pages12
JournalIEEE Journal on Selected Topics in Signal Processing
Volume11
Issue number5
DOIs
StatePublished - Aug 1 2017

Fingerprint

Learning systems
Students
Factorization

Keywords

  • Data-driven course clustering
  • personalized education
  • student performance prediction

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

A Machine Learning Approach for Tracking and Predicting Student Performance in Degree Programs. / Xu, Jie; Moon, Kyeong Ho; Van Der Schaar, Mihaela.

In: IEEE Journal on Selected Topics in Signal Processing, Vol. 11, No. 5, 7894238, 01.08.2017, p. 742-753.

Research output: Contribution to journalArticle

@article{a9cf7e56b10147dea07996c1598b667a,
title = "A Machine Learning Approach for Tracking and Predicting Student Performance in Degree Programs",
abstract = "Accurately predicting students' future performance based on their ongoing academic records is crucial for effectively carrying out necessary pedagogical interventions to ensure students' on-time and satisfactory graduation. Although there is a rich literature on predicting student performance when solving problems or studying for courses using data-driven approaches, predicting student performance in completing degrees (e.g., college programs) is much less studied and faces new challenges: 1) Students differ tremendously in terms of backgrounds and selected courses; 2) courses are not equally informative for making accurate predictions; and 3) students' evolving progress needs to be incorporated into the prediction. In this paper, we develop a novel machine learning method for predicting student performance in degree programs that is able to address these key challenges. The proposed method has two major features. First, a bilayered structure comprising multiple base predictors and a cascade of ensemble predictors is developed for making predictions based on students' evolving performance states. Second, a data-driven approach based on latent factor models and probabilistic matrix factorization is proposed to discover course relevance, which is important for constructing efficient base predictors. Through extensive simulations on an undergraduate student dataset collected over three years at University of California, Los Angeles, we show that the proposed method achieves superior performance to benchmark approaches.",
keywords = "Data-driven course clustering, personalized education, student performance prediction",
author = "Jie Xu and Moon, {Kyeong Ho} and {Van Der Schaar}, Mihaela",
year = "2017",
month = "8",
day = "1",
doi = "10.1109/JSTSP.2017.2692560",
language = "English (US)",
volume = "11",
pages = "742--753",
journal = "IEEE Journal on Selected Topics in Signal Processing",
issn = "1932-4553",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "5",

}

TY - JOUR

T1 - A Machine Learning Approach for Tracking and Predicting Student Performance in Degree Programs

AU - Xu, Jie

AU - Moon, Kyeong Ho

AU - Van Der Schaar, Mihaela

PY - 2017/8/1

Y1 - 2017/8/1

N2 - Accurately predicting students' future performance based on their ongoing academic records is crucial for effectively carrying out necessary pedagogical interventions to ensure students' on-time and satisfactory graduation. Although there is a rich literature on predicting student performance when solving problems or studying for courses using data-driven approaches, predicting student performance in completing degrees (e.g., college programs) is much less studied and faces new challenges: 1) Students differ tremendously in terms of backgrounds and selected courses; 2) courses are not equally informative for making accurate predictions; and 3) students' evolving progress needs to be incorporated into the prediction. In this paper, we develop a novel machine learning method for predicting student performance in degree programs that is able to address these key challenges. The proposed method has two major features. First, a bilayered structure comprising multiple base predictors and a cascade of ensemble predictors is developed for making predictions based on students' evolving performance states. Second, a data-driven approach based on latent factor models and probabilistic matrix factorization is proposed to discover course relevance, which is important for constructing efficient base predictors. Through extensive simulations on an undergraduate student dataset collected over three years at University of California, Los Angeles, we show that the proposed method achieves superior performance to benchmark approaches.

AB - Accurately predicting students' future performance based on their ongoing academic records is crucial for effectively carrying out necessary pedagogical interventions to ensure students' on-time and satisfactory graduation. Although there is a rich literature on predicting student performance when solving problems or studying for courses using data-driven approaches, predicting student performance in completing degrees (e.g., college programs) is much less studied and faces new challenges: 1) Students differ tremendously in terms of backgrounds and selected courses; 2) courses are not equally informative for making accurate predictions; and 3) students' evolving progress needs to be incorporated into the prediction. In this paper, we develop a novel machine learning method for predicting student performance in degree programs that is able to address these key challenges. The proposed method has two major features. First, a bilayered structure comprising multiple base predictors and a cascade of ensemble predictors is developed for making predictions based on students' evolving performance states. Second, a data-driven approach based on latent factor models and probabilistic matrix factorization is proposed to discover course relevance, which is important for constructing efficient base predictors. Through extensive simulations on an undergraduate student dataset collected over three years at University of California, Los Angeles, we show that the proposed method achieves superior performance to benchmark approaches.

KW - Data-driven course clustering

KW - personalized education

KW - student performance prediction

UR - http://www.scopus.com/inward/record.url?scp=85029505112&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85029505112&partnerID=8YFLogxK

U2 - 10.1109/JSTSP.2017.2692560

DO - 10.1109/JSTSP.2017.2692560

M3 - Article

AN - SCOPUS:85029505112

VL - 11

SP - 742

EP - 753

JO - IEEE Journal on Selected Topics in Signal Processing

JF - IEEE Journal on Selected Topics in Signal Processing

SN - 1932-4553

IS - 5

M1 - 7894238

ER -