Enhanced financial fraud detection using cost‐sensitive cascade forest with missing value imputation

Abstract

Financial statement fraud is a global problem for investors, audit firms, regulators, and other stakeholders. Fraud detection can be regarded as a binary classification problem with a false negative being more expensive than a false positive. Although existing studies have made great efforts to detect fraud using various data-mining techniques, the difference in misclassification costs is seldom considered. In this study, we propose a cost-sensitive cascade forest (CSCF) for fraud detection, which places heavy penalty on false negative prediction and self-adjusts the depth of a cascade forest according to the classifier's recall (i.e. the classifier's sensitivity). As missing values are ubiquitous in fraud research, we also explore the effect of selected missing data treatments on prediction performance, including complete case analysis, three selected classic statistical mechanisms (zero, mean, and modified mean imputation), and two machine learning (K-nearest neighbor [KNN] and random forest [RF]) approaches. The experimental results show that the proposed CSCF significantly improves the fraud prediction in comparison with one of the latest fraud detection models using the RUSBoost algorithm. Comparing different missing value treatments, even though RUSBoost and CSCF perform well when using complete case analysis, we find that the best performance is achieved when CSCF is used with missing data imputed as zero. Such treatment further improves the performance, and results in an area under curve (AUC) score of 0.82 compared to the highest AUC (0.71) from the baseline model. Supplementary analysis further reveals that the low AUC of complete case analysis for the two examined models persists under different training sizes. Thus, our findings shed light on the potential benefits of missing value imputation for the model's performance for fraud detection.

Identification of fraudulent financial statements through a multi‐label classification approach

“…The inputs can typically be further subdivided into firm size, corporate reputation, profitability ratios, asset structure, business scenario, liquidity, leverage, and market value ratios (Hajek & Henriques, 2017). Except for financial ratios, raw financial data have also been considered, in studies such as those of Huang et al (2022) and Bao et al (2020), who used raw financial data based on the previous works of Dechow et al (2011) and Cecchini et al (2010). The latter two studies presented a thorough analysis of earlier research (Beneish, 1999; Cecchini et al, 2010; Dechow et al, 2011; Green & Choi, 1997; Summers & Sweeney, 1998) and developed a list of 40 variables such as sales, earnings per share, retained earnings, stockholders' equity, net income, long‐term debt, working capital, total assets, and interest expense.…”