000			01899nam a2200289Ia 4500
008			210519s2019 xx 000 0 und d
040			_cManila Tytana Colleges
100			_aByrnes, Paul E.
245		0	_aAutomated clustering for data analytics / _cPaul E. Byrnes
260			_cFall 2019
336			_atext
337			_aunmediated
338			_avolume
440			_n16 : 2, page 43-58 _aJournal of Emerging Technologies in Accounting
520			_aToday, auditors must consider the risks of material misstatement due to fraud during the financial statement audit (Messier, Glover, and Prawitt 2016). Current audit guidance recommends the use of data mining methods such as clustering to improve the likelihood of discovering irregularities during fraud risk assessment (ASB 2012). Unfortunately, significant challenges exist relative to using clustering in practice, including data preprocessing, model construction, model selection, and outlier detection. The traditional auditor is not trained to effectively address these complexities. One solution entails automation of clustering, thus eliminating the difficult, manual decision points within the clustering process. This would allow practitioners to focus on problem investigation and resolution, rather than being burdened with the technical aspects of clustering. In this paper, automated clustering is explored. In the process, each manual decision point is addressed, and a suitable automated solution is developed. Upon conclusion, a clustering application is formulated and demonstrated.
521			_aAccountancy.
650			_aAnomaly detection.
650			_aAuditing.
650			_aClustering.
650			_aData mining.
650			_aExceptional exceptions.
650			_aFraud discovery.
650			_aIrregularity detection.
650			_aOutlier detection.
942			_2lcc _cA
998			_c86181 _d144544
999			_c82578 _d82578