Using unsupervised machine learning to model tax practice learning theory

doi:10.14419/ijet.v7i2.4.13019

Using unsupervised machine learning to model tax practice learning theory

2018-03-10

0

OA

AI

DOI：10.14419/ijet.v7i2.4.13019

原文链接

原文求助

摘要

En 中文

The aim of this study was to utilize unsupervised machine learning framework to explore a dataset comprised of assessed output by Bachelors of Business, Taxation learners over four successive semesters. The researcher sought to motivate deployment of an evidence-supported, data-driven approach to understand the scope of student learning from a bachelor’s degree in business class taxation class, as a tool for accreditation reporting purposes. Outcomes from the data analysis identified four factors; two related to tax and two related to learning. These factors are, tax theory, and tax practice, along with practical learning and theoretical learning. Research motivated a grounded theory paradigm that explained taxation class learner’s scope of acquired knowledge. The resulting four factor model is a result of the study. The emergent paradigm further explains accounting student’s readiness for career success upon graduation and provides a novel way to meet outcomes reporting requirements mandated by programmatic business accreditors such as required by the Accreditation Council for Business Schools and Programs (ACBSP).

Using unsupervised machine learning to model tax practice learning theory

摘要

期刊

机构

引用论文