R. Islam

J. West, Maumita Bhattacharya, R. Islam

Financial fraud is an issue with far reaching consequences in the finance industry, government, corporate sectors, and for ordinary consumers. Increasing dependence on new technologies such as cloud and mobile computing in recent years has compounded the problem. Traditional methods of detection involve extensive use of auditing, where a trained individual manually observes reports or transactions in an attempt to discover fraudulent behaviour. This method is not only time consuming, expensive and inaccurate, but in the age of big data it is also impractical. Not surprisingly, financial institutions have turned to automated processes using statistical and computational methods. This paper presents a comprehensive investigation on financial fraud detection practices using such data mining methods, with a particular focus on computational intelligence-based techniques. Classification of the practices based on key aspects such as detection algorithm used, fraud type investigated, and success rate have been covered. Issues and challenges associated with the current practices and potential future direction of research have also been identified.

Maumita Bhattacharya, R. Islam, A. Mahmood

Evolutionary algorithms (EA) have been widely accepted as efficient solvers for complex real world optimization problems, including engineering optimization. However, real world optimization problems often involve uncertain environment including noisy and/or dynamic environments, which pose major challenges to EA-based optimization. The presence of noise interferes with the evaluation and the selection process of EA, and thus adversely affects its performance. In addition, as presence of noise poses challenges to the evaluation of the fitness function, it may need to be estimated instead of being evaluated. Several existing approaches attempt to address this problem, such as introduction of diversity (hyper mutation, random immigrants, special operators) or incorporation of memory of the past (diploidy, case based memory). However, these approaches fail to adequately address the problem. In this paper we propose a Distributed Population Switching Evolutionary Algorithm (DPSEA) method that addresses optimization of functions with noisy fitness using a distributed population switching architecture, to simulate a distributed self-adaptive memory of the solution space. Local regression is used in the pseudo-populations to estimate the fitness. Successful applications to benchmark test problems ascertain the proposed method's superior performance in terms of both robustness and accuracy.