TY  - JOUR
TI  - DETECTING FINANCIAL INFORMATION MANIPULATION BY USING SUPERVISED MACHINE LEARNING TECHNICS: SVM, PNN, KNN, DT
AB  - Within the scope of this paper, traditional estimation algorithms and supervised machine learning methodsare used to estimate the manipulation of financial information. Traditional estimation algorithms, such aslogit, and supervised machine learning methods, which are support vector machine (SVM), probabilisticneural network (PNN), k-nearest neighbor (KNN) and decision tree (DT) algorithms, are utilized. According toprevious studies, support vector machine and probabilistic neural network algorithms perform higher thantraditional estimation ones in terms of the accuracy of financial information manipulation estimation.Comparative analysis is made to decide better algorithm for classification by applying all algorithms separatelyto the financial information manipulation dataset that is collected by skimming weekly bulletins of CapitalMarkets Board of Turkey and Borsa Istanbul between 2009 and 2018. Thus, it is determined which algorithmsperform better in financial information manipulation by looking at performance of classification accuracy,sensitivity and specificity statistics. The obtained results show that KNN and SVM have better performancethan the other algorithms and all utilized algorithms have high performance compared to the previousliterature’s results
AU  - Aydın, Osman Musa
AU  - Aktaş, Ramazan
DO  - ulikidince.748742
PY  - 2020
JO  - Uluslararası İktisadi ve İdari İncelemeler Dergisi
VL  - 0
IS  - 29
SN  - 1307-9832
SP  - 165
EP  - 174
DB  - TRDizin
UR  - http://search/yayin/detay/426403
ER  -