Home
Resource
Developing an intelligent assistant for the audit plan brainstorming session
PDF
PDF format is widely accepted and good for printing.
Plug-in required
PDF-1(5.11 MB)
Citation & Export
View Usage Statistics
Staff View

Citation & Export
Hide

Simple citation

Li, Qiao. Developing an intelligent assistant for the audit plan brainstorming session. Retrieved from https://doi.org/doi:10.7282/t3-k6vm-ep16

Export

Click here for information about Citation Management Tools at Rutgers.

Statistics
Hide

Description

TitleDeveloping an intelligent assistant for the audit plan brainstorming session
NameLi, Qiao (author); Vasarhelyi, Miklos (chair); Kogan, Alexander (internal member); Brown-Liburd, Helen (internal member); Warren, Donald (outside member); Rutgers University; Graduate School - Newark
Date Created2019
Other Date2019-01 (degree)
SubjectManagement, Auditing--Data processing
Extent1 online resource (141 pages) : illustrations
DescriptionDuring the initial stages of an audit, audit engagement teams are required to conduct brainstorming sessions to evaluate risk factors and discuss the susceptibility of the entity’s financial statements to material misstatement, either as a result of error or fraud (AICPA 2012). At present, the most commonly used decision support tool for audit plan brainstorming is the checklist (Bellovary and Johnstone 2007), which has shown limitations. Large audit firms have been investing in substantive resources to the utilization of Artificial Intelligence (AI) to take advantage of their past audit experience and industry knowledge (Kokina and Davenport 2017). This dissertation suggests that the latest intelligent assistant technology can be applied in the auditing domain to provide risk assessment decision supports to audit engagement teams during audit plan brainstorming discussions.
Firstly, an interactive audit cognitive assistant framework is proposed to provide auditors with information retrieval and risk assessment help. The proposed framework provides a new method of knowledge organization for the audit domain, which potentially develops a knowledge base that stores many auditors’ knowledge and experience in audit risk identification and assessment.
Furthermore, a Natural Language Processing (NLP)-based audit plan knowledge discovery system (APKDS) is proposed. By applying NLP techniques, the proposed system can continuously collect auditors’ professional experience and expertise in audit brainstorming discussions and transfer the discussion into classified knowledge for future use. The output of the proposed system can provide insights into how auditors identify and assess risks during the audit plan and how audit decisions are made.
Finally, we propose a prototype for the APKDS framework and illustrate the development of important modules in the system. Experimental brainstorming meeting recordings are used as training and testing datasets in model building and training. We demonstrate that the proposed objectives of the system can be realized and the proposed system can provide effective decision-making support to auditors. In the end, we proposed the potential application of the audit cognitive assistant to other audit phases.
NotePh.D.
NoteIncludes bibliographical references
Noteby Qiao Li
Genretheses, ETD doctoral
Persistent URLhttps://doi.org/doi:10.7282/t3-k6vm-ep16
Languageeng
CollectionGraduate School - Newark Electronic Theses and Dissertations
Organization NameRutgers, The State University of New Jersey
RightsThe author owns the copyright to this work.
Version 8.5.1
Rutgers University Libraries - Copyright ©2023