Kump, P. M., & August, I. (2024, June), Boosting Achieved-Learning Outcomes with Maritime-Specific Projects in a Machine Learning Course  Paper presented at 2024 ASEE Annual Conference & Exposition, Portland, Oregon. 10.18260/1-2--48401

\bibitem{asee_peer_48401}
  Kump, P. M., \& August, I. (2024, June), \emph{Boosting Achieved-Learning Outcomes with Maritime-Specific Projects in a Machine Learning Course}
  Paper presented at 2024 ASEE Annual Conference \& Exposition, Portland, Oregon.
  10.18260/1-2--48401

Paul Marty Kump and Ian August.  "Boosting Achieved-Learning Outcomes with Maritime-Specific Projects in a Machine Learning Course".  2024 ASEE Annual Conference & Exposition, Portland, Oregon, 2024, June.  ASEE Conferences, 2024.  https://peer.asee.org/48401 Internet.  16 May, 2025

\bibitem{asee_peer_48401}
  Paul Marty Kump and Ian August.
  "Boosting Achieved-Learning Outcomes with Maritime-Specific Projects in a Machine Learning Course".
  \emph{2024 ASEE Annual Conference \& Exposition, Portland, Oregon, 2024, June}.
  ASEE Conferences, 2024.
  https://peer.asee.org/48401 Internet.  16 May, 2025

@INPROCEEDINGS{asee_peer_48401
author = "Paul Marty Kump and Ian August"
title = "Boosting Achieved-Learning Outcomes with Maritime-Specific Projects in a Machine Learning Course"
booktitle = "2024 ASEE Annual Conference \& Exposition"
year = "2024"
month = "June"
address = "Portland, Oregon"
publisher = "ASEE Conferences"
note = {https://peer.asee.org/48401}
number = {10.18260/1-2--48401}
}

TY  - CPAPER
AB  - In 2022, we developed a maritime-specific course in machine learning (ML) for undergraduate maritime engineering and naval architecture students in an effort to boost low levels of achieved student outcomes articulated by the Accreditation Board for Engineering and Technology (ABET).  As a major component to the course, we designed a set of mini projects that all utilized the same maritime-related dataset—hypothesizing that domain-specific projects would increase student performance—and we made the projects and solutions publicly available for students and like-minded instructors.  This work was met with high praise from colleagues and students, with several positive comments and solicitations for downloads and solutions.  But just how important is domain-specific material to an ML course?  In this paper, we report on the effects our course had on student learning.  The results and lessons learned from our study are valuable information for course developers, instructional designers, and educators looking to boost student performance and craft a domain-specific ML course, be it maritime or other.

We measure the effects of our course on student outcomes by applying the difference-in-differences (DiD) statistical technique to course data before and after the 2022 course redesign.  Included in this analysis are the results of course surveys completed by students, achieved level of ABET learning outcomes, and students’ final grades in the course.  We find significant increase for ABET learning outcomes; a result that pleased ABET during our institution’s most-recent ABET review cycle.  We also find a significant increase of +0.50 grade point average (out of 4.00) to students’ final grades.  With regard to student attitude and perception via course evaluations, a positive change is observed, but we are unable to conclude that the change is statistically significant.

AU  - Paul Marty Kump
AU  - Ian August
CY  - Portland, Oregon
DA  - 2024/06/23
PB  - ASEE Conferences
TI  - Boosting Achieved-Learning Outcomes with Maritime-Specific Projects in a Machine Learning Course
UR  - https://peer.asee.org/48401
DO  - 10.18260/1-2--48401
ER  -