FRAUD DETECTION IN U.S. FINANCIAL STATEMENTS: INCORPORATING GOVERNANCE IN DETECTIVE MODELLING

Abstract

This thesis extends the financial fraud detection model from ”The Model of Fraud Detection in Financial Statements by Means of Financial Ratios” by Kanapickien˙e and Grundien˙e (2015) by integrating governance factors with traditional financial ratios. Our model aims to improve the detection of fraudulent activities in U.S.- listed companies, addressing the limitations of current methods that primarily rely on financial ratios. Utilizing logistic regression, we analyzed a dataset of financial statements from 1998 to 2018, discovering that the inclusion of governance metrics significantly increases the accuracy of fraud detection. Our findings contribute to the existing literature by demonstrating the benefits of a comprehensive analytical approach that combines financial and non-financial factors, potentially facilitating earlier identification and prevention of financial fraud.