Detecting financial information manipulation by using supervised machine learning technics: Support vector machine, probabilistic neural network, k-nearest neighbor, decision tree

Within the scope of this thesis, traditional estimation algorithms and supervised machine learning methods are used to estimate the manipulation of financial information, which can be defined as distorting information in financial statements. Traditional estimation algorithms, such as logit, and supervised machine learning methods, which are support vector machine (SVM), probabilistic neural network (PNN), k-nearest neighbor (KNN) and decision tree (DT) algorithms, are utilized. According to the previous studies, support vector machine and probabilistic neural network algorithms perform higher than traditional estimation algorithms. Comparative analysis is made to decide better algorithm for classification by applying all algorithms separately to the data obtained from the Capital Market Board. Thus, it is determined which algorithms perform better in financial information manipulation by looking at performance of classification accuracy, sensitivity and specificity statistics. SVM and PNN have shown superior performance. So that it can be said that these algorithms can be used to detect manipulation in automated manner.