Dalarna University's logo and link to the university's website

du.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • chicago-author-date
  • chicago-note-bibliography
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Systematic Review of Application of Machine Learning and ArtificialIntelligence Tools in Accounting Research
Dalarna University, School of Information and Engineering.
Dalarna University, School of Information and Engineering.
2022 (English)Independent thesis Advanced level (degree of Master (One Year)), 10 credits / 15 HE creditsStudent thesis
Abstract [en]

In finance and more specifically accounting and auditing fields, machine learning (ML) alongwith artificial intelligence (AI) have been increasingly used in the last few years. This paperprovides a systematic review of the selected articles depicting the use of ML and AI tools inaccounting research in the last thirty-eight years. The ‘Library’ database of Dalarna Universityand the PRISMA protocol is applied for data search technique of the top 20 journals ofaccounting to get the most relevant and optimised data. The evolution of the application of MLand AI use in the field of accounting research in the last 38 years has been analysed. ‘LDA(Latent Dirichlet Allocation) Topic Modeling’ has been applied to check the dimensionalityand diversification in the collected data. Human classification was then applied to validate theoutcome of topic modeling. The results had shown that there is concentration of research workon specialized use of ML and AI in accounting research in last decade or so. The topicmodeling results obtained during this systematic review were summarized under five-topicdimensionality i.e. ‘ audit decision / prediction’, ‘financial risk analysis’, ‘firms decisionmaking’,’ business fraud analytics’ and ‘identify financial model’ so that shows that these arethe major arenas on the subject of ML and AI in accounting research. This thesis can be of itskind that provides methodology of applying topic modeling for systematic review at least inthe field of accounting. Given the limitations of ‘Library’ database and LDA topic modeling;expanding the use of different databases and application of other topic modeling algorithmslike NMF (non-negative matrix factorization), for future research are recommended.

Place, publisher, year, edition, pages
2022.
Keywords [en]
machine learning, artificial intelligence, data mining, big data, accounting, LDA topic modeling, Natural language processing (NLP).
National Category
Social Sciences Interdisciplinary
Identifiers
URN: urn:nbn:se:du-39640OAI: oai:DiVA.org:du-39640DiVA, id: diva2:1639528
Subject / course
Microdata Analysis
Presentation
2022-02-21, 16:29
Available from: 2022-02-21 Created: 2022-02-21

Open Access in DiVA

No full text in DiVA

By organisation
School of Information and Engineering
Social Sciences Interdisciplinary

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 617 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • chicago-author-date
  • chicago-note-bibliography
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf