Machine Learning Methods for Detecting Patterns of Management Fraud

Abstract

Discovery of financial fraud has profound social consequences. Loss of stockholder value, bankruptcy, and loss of confidence in the professional audit firms have resulted from failure to detect financial fraud. Previous studies that have attempted to discover fraud patterns from publicly available information have achieved only moderate levels of success. This study explores the capabilities of recently developed statistical learning and data mining methods in an attempt to advance fraud discovery performance to levels that have potential for proactive discovery or mitigation of financial fraud. The partially adaptive methods we test have achieved success in a number of complex problem domains and are easily interpretable. Ensemble methods, which combine predictions from multiple models via boosting, bagging, or related approaches, have emerged as among the most powerful data mining and machine learning methods. Our study includes random forests, stochastic gradient boosting, and rule ensembles. The results for ensemble models show marked improvement over past efforts, with accuracy approaching levels of practical potential. In particular, rule ensembles do so while maintaining a degree of interpretability absent in the other ensemble methods.

Addressing imbalanced data with argument based rule learning

“…For example, in medical problems the number of patients requiring special attention (e.g., therapy or treatment) is much smaller than the number of patients who do not need it. The same phenomenon has been observed in fraud detection (Whiting, Hansen, McDonald, Albrecht, & Albrecht, 2012), oil spills detection in satellite images, financial risk analysis, predicting technical equipment failures, managing network intrusion and information filtering (Aggarwal, 2015;Chawla, 2005;He & Garcia, 2009;He & Ma, 2013;Krawczyk, Wozniak, & Schaefer, 2014;Weiss, 2004). In all those problems, the correct recognition of the minority class is of key importance, however, standard classifiers are biased toward the majority classes.…”

Information Management in Healthcare and Environment: Towards an Automatic System for Fake News Detection

“…As we have said, the main objective of our method is to define an adequate framework to automatically detect fake news. Many mathematical and computational techniques have been broadly applied in the similar context of the exchange of accounting and financial information (an introduction to this context can be found in References [13,16,17]. For our purposes, we have developed an algorithm that automatically constructs an evolutionary graph with information on a particular topic gathered from internet sources, using the timeline as the order criterion.…”

Evaluating the benefits of using proactive transformed-domain-based techniques in fraud detection tasks

“…In order to maximize the performance of the RF approach, we used the caret R package in order to detect the optimal value of the mtry (number of variables randomly sampled as candidates at each split) parameter 11 .…”

“…Nowadays, a fraud detection system can exploit many state-of-the-art techniques in order to evaluate a financial transaction. For instance, it can exploit: Data Mining techniques to generate rules from fraud patterns [5]; Artificial Intelligence techniques to identify data irregularities [6]; Neural Networks techniques to define predictive models [7]; Signature-based techniques aimed to maintain a statistical representation of normal account usage for rapid recalculation in real-time [8]; Fuzzy Logic techniques to perform a fuzzy analysis for a fraud detection task [9]; Decision Tree techniques to reduce the number of misclassifications [10]; Machine Learning techniques to define ensemble methods that combine predictions from multiple models [11,12]; Genetic Programming techniques to model and detect fraud through an Evolutionary Computation approach [13]; Statistical Inference techniques that adopt a flexible Bayesian model for fraud detection [14].…”