Using Machine Learning to Address Individual Learning Needs in Accounting Education

55 Pages Posted: 7 Dec 2023

See all articles by Janik Ole Wecks

Janik Ole Wecks

University of Bremen - Faculty of Business Studies and Economics - Chair of Accounting and Control

Johannes Voshaar

University of Bremen - Faculty of Business Studies and Economics - Chair of Accounting and Control; John Molson School of Business, Concordia University

Jochen Zimmermann

University of Bremen - Faculty of Business Studies and Economics; University of Bremen - Chair of Accounting and Control

Date Written: November 29, 2023

Abstract

This study examines the potential of supervised machine learning to enable personalized learning in large accounting classes. Lecturers must know students’ individual learning needs to personalize teaching and learning, which is hardly feasible in courses with many participants. Accounting classes tend to be particularly large due to their relevance to many study programs and their placement early in the curriculum, complicating personalized learning. To address this problem, we apply machine learning prediction models in a much-attended introductory accounting course. We train models to forecast (I) students’ general proficiency in accounting and (II) their capability in various learning areas to obtain relevant information for personalized learning at the beginning of the semester. The results show that Support Vector models significantly outperform simple benchmark models and naïve estimators, which equate to the predictive ability of lecturers. Only machine learning models are able to accurately predict students’ needs, enabling personalized learning in large classes. Thus, machine learning could be the grounding stone enabling personalized learning based on mobile learning tools and generative artificial intelligence to improve educational quality in accounting education. The study sheds light on how universities can harness their broad data to enhance teaching in accounting, utilizing supervised machine learning.

Keywords: Accounting Education, Machine Learning, Personalized Learning, Exam Performance, Prediction Models

Suggested Citation

Wecks, Janik Ole and Voshaar, Johannes and Zimmermann, Jochen and Zimmermann, Jochen, Using Machine Learning to Address Individual Learning Needs in Accounting Education (November 29, 2023). Available at SSRN: https://ssrn.com/abstract=4648223 or http://dx.doi.org/10.2139/ssrn.4648223

Janik Ole Wecks (Contact Author)

University of Bremen - Faculty of Business Studies and Economics - Chair of Accounting and Control ( email )

Bremen, D-28359
Germany

Johannes Voshaar

University of Bremen - Faculty of Business Studies and Economics - Chair of Accounting and Control ( email )

Bremen, D-28359
Germany

John Molson School of Business, Concordia University ( email )

Montreal
Canada

Jochen Zimmermann

University of Bremen - Faculty of Business Studies and Economics ( email )

Hochschulring 4
Germany
+49 421 218 9121 (Phone)

University of Bremen - Chair of Accounting and Control ( email )

Universitaetsallee GW I
Bremen, D-28334
Germany
+49 421 218-9119 (Phone)

HOME PAGE: http://www.controlling.uni-bremen.de

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
52
Abstract Views
219
Rank
701,323
PlumX Metrics