Application of selected data mining techniques in unintentional accounting error detection

Research background: Even though unintentional accounting errors leading to financial restatements look like less serious distortion of publicly available information, it has been shown that impacts on markets are similar intentional fraudulent activities. Unintentional then affect value company shares in the short run which negatively all shareholders.
 Purpose article: The aim this manuscript is predict based information from statements companies. analysis if include sufficient would allow detection errors.
 Methods: Method classification and regression trees (decision tree) random forest have used fulfill manuscript. Data sample consisted 400 items 80 selected international results developed prediction models compared explained their accuracy, sensitivity, specificity, precision F1 score. Statistical relationship among variables tested by correlation analysis. Differences between group companies with without error means Kruskal-Wallis test. Levene T-tests.
 Findings & added: provided evidence possible detect high levels accuracy ratios (rather than Beneish variables) application method tree method).