Model Tree with Modified L1 Loss Function for Predicting Missing Attendance Data of Faculties

DOI

10.2991/icoiese-18.2019.10How to use a DOI?

Keywords

model tree; loss function; prediction; attendance

Abstract

The problem of missing attendance data in our university often arises due to the negligence of faculties. In this study, we address the problem by directly predicting the work duration of faculties. The nature of the problem require us to not only make accurate predictions, but also minimize the rate of overestimation. To address the problem, we propose the implementation of model tree with modified L1 loss function and simple prediction result reduction. Experimental results show that our proposed method is able to lower the overestimation rate while maintaining accuracy within acceptable range.

Copyright

© 2019, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Mohammad Arif Rasyidi
AU  - Rachmadita Andreswari
PY  - 2019/03
DA  - 2019/03
TI  - Model Tree with Modified L1 Loss Function for Predicting Missing Attendance Data of Faculties
BT  - Proceedings of the 2018 International Conference on Industrial Enterprise and System Engineering (IcoIESE 2018)
PB  - Atlantis Press
SP  - 53
EP  - 57
SN  - 2589-4943
UR  - https://doi.org/10.2991/icoiese-18.2019.10
DO  - 10.2991/icoiese-18.2019.10
ID  - Rasyidi2019/03
ER  -