Al-Gahmi, A., & Feuz, K., & Zhang, Y. (2022, August), On Time-based Exploration of LMS Data and Prediction of Student Performance  Paper presented at 2022 ASEE Annual Conference & Exposition, Minneapolis, MN. 10.18260/1-2--40852

\bibitem{asee_peer_40852}
  Al-Gahmi, A., \& Feuz, K., \& Zhang, Y. (2022, August), \emph{On Time-based Exploration of LMS Data and Prediction of Student Performance}
  Paper presented at 2022 ASEE Annual Conference \& Exposition, Minneapolis, MN.
  10.18260/1-2--40852

Abdulmalek Al-Gahmi, Kyle Feuz, and Yong Zhang.  "On Time-based Exploration of LMS Data and Prediction of Student Performance".  2022 ASEE Annual Conference & Exposition, Minneapolis, MN, 2022, August.  ASEE Conferences, 2022.  https://strategy.asee.org/40852 Internet.  17 Jul, 2024

\bibitem{asee_peer_40852}
  Abdulmalek Al-Gahmi, Kyle Feuz, and Yong Zhang.
  "On Time-based Exploration of LMS Data and Prediction of Student Performance".
  \emph{2022 ASEE Annual Conference \& Exposition, Minneapolis, MN, 2022, August}.
  ASEE Conferences, 2022.
  https://strategy.asee.org/40852 Internet.  17 Jul, 2024

@INPROCEEDINGS{asee_peer_40852
author = "Abdulmalek Al-Gahmi, Kyle Feuz, and Yong Zhang"
title = "On Time-based Exploration of LMS Data and Prediction of Student Performance"
booktitle = "2022 ASEE Annual Conference \& Exposition"
year = "2022"
month = "August"
address = "Minneapolis, MN"
publisher = "ASEE Conferences"
note = {https://strategy.asee.org/40852}
number = {10.18260/1-2--40852}
}

TY  - CPAPER
AB  - Learning Management Systems (LMS) gather extensive amounts of data about students' progression through courses. Such data is then made available via APIs for data exploration and utilization. A body of research has investigated using such data to predict student performance based on data collected earlier in a course. The driving question in such efforts has been whether student performance can be accurately predicted early enough to intervene and provide needed help. Two main issues have been pointed out in these attempts: the portability and robustness of these predictions.

In this work-in-progress study, we introduce a new approach to exploring LMS data. Such an approach looks at the data as a set of time series each representing the progress of a student within a course. This study explores how students advance through courses over time and the variability of student performance between any two time points. It utilizes the LMS data (Canvas in this case) obtained from multiple Computer Science courses taught by different instructors in different formats (online and face-to-face) over three years in a public four-year university. Ways for summarizing and visualizing such data are discussed, and useful predictor features are extracted and used to build and evaluate predictive models of student performance at any time point. The study explores questions such as: How does the progress of passed and failed students differ in these courses? How early can student performance be accurately predicted? Can data collected from one course be used to predict the performance of students in another course by the same or a different instructor? Are student journeys through courses unique, or are there patterns that transcend students and courses?
AU  - Abdulmalek Al-Gahmi
AU  - Kyle Feuz
AU  - Yong Zhang
CY  - Minneapolis, MN
DA  - 2022/08/23
PB  - ASEE Conferences
TI  - On Time-based Exploration of LMS Data and Prediction of Student Performance
UR  - https://strategy.asee.org/40852
DO  - 10.18260/1-2--40852
ER  -