Abstract
Given the variability in student learning, it is becoming increasingly important to tailor courses as well as course sequences to student needs. This paper presents a systematic methodology for offering personalized course sequence recommendations to students. First, a forward-search backward-induction algorithm is developed that can optimally select course sequences to decrease the time required for a student to graduate. The algorithm accounts for prerequisite requirements (typically present in higher level education) and course availability. Second, using the tools of multiarmed bandits, an algorithm is developed that can optimally recommend a course sequence that both reduces the time to graduate while also increasing the overall GPA of the student. The algorithm dynamically learns how students with different contextual backgrounds perform for given course sequences and, then, recommends an optimal course sequence for new students. Using real-world student data from the UCLA Mechanical and Aerospace Engineering Department, we illustrate how the proposed algorithms outperform other methods that do not include student contextual information when making course sequence recommendations.
| Original language | English (US) |
|---|---|
| Article number | 7524023 |
| Pages (from-to) | 5340-5352 |
| Number of pages | 13 |
| Journal | IEEE Transactions on Signal Processing |
| Volume | 64 |
| Issue number | 20 |
| DOIs | |
| State | Published - Oct 15 2016 |
Fingerprint
Keywords
- contextual bandits
- course sequence recommendation
- dynamic programming
- Personalized education
ASJC Scopus subject areas
- Signal Processing
- Electrical and Electronic Engineering
Cite this
Personalized Course Sequence Recommendations. / Xu, Jie; Xing, Tianwei; Van Der Schaar, Mihaela.
In: IEEE Transactions on Signal Processing, Vol. 64, No. 20, 7524023, 15.10.2016, p. 5340-5352.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Personalized Course Sequence Recommendations
AU - Xu, Jie
AU - Xing, Tianwei
AU - Van Der Schaar, Mihaela
PY - 2016/10/15
Y1 - 2016/10/15
N2 - Given the variability in student learning, it is becoming increasingly important to tailor courses as well as course sequences to student needs. This paper presents a systematic methodology for offering personalized course sequence recommendations to students. First, a forward-search backward-induction algorithm is developed that can optimally select course sequences to decrease the time required for a student to graduate. The algorithm accounts for prerequisite requirements (typically present in higher level education) and course availability. Second, using the tools of multiarmed bandits, an algorithm is developed that can optimally recommend a course sequence that both reduces the time to graduate while also increasing the overall GPA of the student. The algorithm dynamically learns how students with different contextual backgrounds perform for given course sequences and, then, recommends an optimal course sequence for new students. Using real-world student data from the UCLA Mechanical and Aerospace Engineering Department, we illustrate how the proposed algorithms outperform other methods that do not include student contextual information when making course sequence recommendations.
AB - Given the variability in student learning, it is becoming increasingly important to tailor courses as well as course sequences to student needs. This paper presents a systematic methodology for offering personalized course sequence recommendations to students. First, a forward-search backward-induction algorithm is developed that can optimally select course sequences to decrease the time required for a student to graduate. The algorithm accounts for prerequisite requirements (typically present in higher level education) and course availability. Second, using the tools of multiarmed bandits, an algorithm is developed that can optimally recommend a course sequence that both reduces the time to graduate while also increasing the overall GPA of the student. The algorithm dynamically learns how students with different contextual backgrounds perform for given course sequences and, then, recommends an optimal course sequence for new students. Using real-world student data from the UCLA Mechanical and Aerospace Engineering Department, we illustrate how the proposed algorithms outperform other methods that do not include student contextual information when making course sequence recommendations.
KW - contextual bandits
KW - course sequence recommendation
KW - dynamic programming
KW - Personalized education
UR - http://www.scopus.com/inward/record.url?scp=84984987651&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84984987651&partnerID=8YFLogxK
U2 - 10.1109/TSP.2016.2595495
DO - 10.1109/TSP.2016.2595495
M3 - Article
AN - SCOPUS:84984987651
VL - 64
SP - 5340
EP - 5352
JO - IEEE Transactions on Signal Processing
JF - IEEE Transactions on Signal Processing
SN - 1053-587X
IS - 20
M1 - 7524023
ER -