Publication

A dynamic thompson sampling hyper-heuristic framework for learning activity planning in personalized learning

Aslan, A., Bakir, I. & Vis, I. F. A., 16-Oct-2020, In : European Journal of Operational Research. 286, 2, p. 673-688 16 p.

Research output: Contribution to journalArticleAcademicpeer-review

APA

Aslan, A., Bakir, I., & Vis, I. F. A. (2020). A dynamic thompson sampling hyper-heuristic framework for learning activity planning in personalized learning. European Journal of Operational Research, 286(2), 673-688. https://doi.org/10.1016/j.ejor.2020.03.038

Author

Aslan, Ayse ; Bakir, Ilke ; Vis, Iris F. A. / A dynamic thompson sampling hyper-heuristic framework for learning activity planning in personalized learning. In: European Journal of Operational Research. 2020 ; Vol. 286, No. 2. pp. 673-688.

Harvard

Aslan, A, Bakir, I & Vis, IFA 2020, 'A dynamic thompson sampling hyper-heuristic framework for learning activity planning in personalized learning', European Journal of Operational Research, vol. 286, no. 2, pp. 673-688. https://doi.org/10.1016/j.ejor.2020.03.038

Standard

A dynamic thompson sampling hyper-heuristic framework for learning activity planning in personalized learning. / Aslan, Ayse; Bakir, Ilke; Vis, Iris F. A.

In: European Journal of Operational Research, Vol. 286, No. 2, 16.10.2020, p. 673-688.

Research output: Contribution to journalArticleAcademicpeer-review

Vancouver

Aslan A, Bakir I, Vis IFA. A dynamic thompson sampling hyper-heuristic framework for learning activity planning in personalized learning. European Journal of Operational Research. 2020 Oct 16;286(2):673-688. https://doi.org/10.1016/j.ejor.2020.03.038


BibTeX

@article{add4871f61a34e218b854d3d810dc003,
title = "A dynamic thompson sampling hyper-heuristic framework for learning activity planning in personalized learning",
abstract = "Personalized learning is emerging in schools as an alternative to one-size-fits-all education. This study introduces and explores a weekly demand-driven flexible learning activity planning problem of own-pace own-method personalized learning. The introduced problem is a computationally intractable optimization problem involving many decision dimensions and also many soft constraints. We propose batch and decomposition methods to generate good-quality initial solutions and a dynamic Thompson sampling based hyper-heuristic framework, as a local search mechanism, which explores the large solution space of this problem in an integrative way. The characteristics of our test instances comply with average secondary schools in the Netherlands and are based on expert opinions and surveys. The experiments, which benchmark the proposed heuristics against Gurobi MIP solver on small instances, illustrate the computational challenge of this problem numerically. According to our experiments, the batch method seems quicker and also can provide better quality solutions for the instances in which resource levels are not scarce, while the decomposition method seems more suitable in resource scarcity situations. The dynamic Thompson sampling based online learning heuristic selection mechanism is shown to provide significant value to the performance of our hyper-heuristic local search. We also provide some practical insights; our experiments numerically demonstrate the alleviating effects of large school sizes on the challenge of satisfying high-spread learning demands.",
keywords = "Timetabling, Hyper-heuristics, Dynamic thompson sampling, Personalized learning, OR in education",
author = "Ayse Aslan and Ilke Bakir and Vis, {Iris F. A.}",
year = "2020",
month = oct,
day = "16",
doi = "10.1016/j.ejor.2020.03.038",
language = "English",
volume = "286",
pages = "673--688",
journal = "European Journal of Operational Research",
issn = "0377-2217",
publisher = "ELSEVIER SCIENCE BV",
number = "2",

}

RIS

TY - JOUR

T1 - A dynamic thompson sampling hyper-heuristic framework for learning activity planning in personalized learning

AU - Aslan, Ayse

AU - Bakir, Ilke

AU - Vis, Iris F. A.

PY - 2020/10/16

Y1 - 2020/10/16

N2 - Personalized learning is emerging in schools as an alternative to one-size-fits-all education. This study introduces and explores a weekly demand-driven flexible learning activity planning problem of own-pace own-method personalized learning. The introduced problem is a computationally intractable optimization problem involving many decision dimensions and also many soft constraints. We propose batch and decomposition methods to generate good-quality initial solutions and a dynamic Thompson sampling based hyper-heuristic framework, as a local search mechanism, which explores the large solution space of this problem in an integrative way. The characteristics of our test instances comply with average secondary schools in the Netherlands and are based on expert opinions and surveys. The experiments, which benchmark the proposed heuristics against Gurobi MIP solver on small instances, illustrate the computational challenge of this problem numerically. According to our experiments, the batch method seems quicker and also can provide better quality solutions for the instances in which resource levels are not scarce, while the decomposition method seems more suitable in resource scarcity situations. The dynamic Thompson sampling based online learning heuristic selection mechanism is shown to provide significant value to the performance of our hyper-heuristic local search. We also provide some practical insights; our experiments numerically demonstrate the alleviating effects of large school sizes on the challenge of satisfying high-spread learning demands.

AB - Personalized learning is emerging in schools as an alternative to one-size-fits-all education. This study introduces and explores a weekly demand-driven flexible learning activity planning problem of own-pace own-method personalized learning. The introduced problem is a computationally intractable optimization problem involving many decision dimensions and also many soft constraints. We propose batch and decomposition methods to generate good-quality initial solutions and a dynamic Thompson sampling based hyper-heuristic framework, as a local search mechanism, which explores the large solution space of this problem in an integrative way. The characteristics of our test instances comply with average secondary schools in the Netherlands and are based on expert opinions and surveys. The experiments, which benchmark the proposed heuristics against Gurobi MIP solver on small instances, illustrate the computational challenge of this problem numerically. According to our experiments, the batch method seems quicker and also can provide better quality solutions for the instances in which resource levels are not scarce, while the decomposition method seems more suitable in resource scarcity situations. The dynamic Thompson sampling based online learning heuristic selection mechanism is shown to provide significant value to the performance of our hyper-heuristic local search. We also provide some practical insights; our experiments numerically demonstrate the alleviating effects of large school sizes on the challenge of satisfying high-spread learning demands.

KW - Timetabling

KW - Hyper-heuristics

KW - Dynamic thompson sampling

KW - Personalized learning

KW - OR in education

U2 - 10.1016/j.ejor.2020.03.038

DO - 10.1016/j.ejor.2020.03.038

M3 - Article

VL - 286

SP - 673

EP - 688

JO - European Journal of Operational Research

JF - European Journal of Operational Research

SN - 0377-2217

IS - 2

ER -

ID: 127065439