Fraud Detection
Recently Published Documents





Abukari Abdul Aziz Danaa ◽  
Mohammed Ibrahim Daabo ◽  
Alhassan Abdul-Barik

Recent researches have revealed the capability of Machine Learning (ML) techniques to effectively detect fraud in electronic banking transactions since they have the potential to detect new and unknown intrusions. A major challenge in the application of ML to fraud detection is the presence of highly imbalanced data sets. In many available datasets, majority of transactions are genuine with an extremely small percentage of fraudulent ones. Designing an accurate and efficient fraud detection system that is low on false positives but detects fraudulent activity effectively is a significant challenge for researchers. In this paper, a framework based on Hidden Markov Models (HMM), modified Density Based Spatial Clustering of Applications with Noise (DBSCAN) and Synthetic Minority Oversampling Technique Techniques (SMOTE) is proposed to effectively detect fraud in a highly imbalanced electronic banking dataset. The various transaction types, transaction amounts and the frequency of transactions are taken into consideration by the proposed model to enable effective detection. With different number of hidden states for the proposed HMMs, simulations are performed for four (4) different approaches and their performances compared using precision, recall rate and F1-Score as the evaluation metrics. The study revealed that, our proposed approach is able to detect fraudulent transactions more effectively with reasonably low number of false positives.

Aishwarya Priyadarshini ◽  
Sanhita Mishra ◽  
Debani Prasad Mishra ◽  
Surender Reddy Salkuti ◽  
Ramakanta Mohanty

<p>Nowadays, fraudulent or deceitful activities associated with financial transactions, predominantly using credit cards have been increasing at an alarming rate and are one of the most prevalent activities in finance industries, corporate companies, and other government organizations. It is therefore essential to incorporate a fraud detection system that mainly consists of intelligent fraud detection techniques to keep in view the consumer and clients’ welfare alike. Numerous fraud detection procedures, techniques, and systems in literature have been implemented by employing a myriad of intelligent techniques including algorithms and frameworks to detect fraudulent and deceitful transactions. This paper initially analyses the data through exploratory data analysis and then proposes various classification models that are implemented using intelligent soft computing techniques to predictively classify fraudulent credit card transactions. Classification algorithms such as K-Nearest neighbor (K-NN), decision tree, random forest (RF), and logistic regression (LR) have been implemented to critically evaluate their performances. The proposed model is computationally efficient, light-weight and can be used for credit card fraudulent transaction detection with better accuracy.</p>

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Ezekiel Oluwagbemiga Oyerogba

PurposeThis study investigates the perception of professionals in the field of accounting, and those associated with forensic auditing, about the knowledge and skills, experience and technique that a forensic auditor should possess to provide high-quality services in fraud detection. The study also shows the impact of forensic auditing tools on fraud detection.Design/methodology/approachWith the use of a self-administered questionnaire, the study adopts a survey design in which 298 respondents participated. Data were subjected to descriptive statistics (ranking, mean and standard deviation), inferential statistics (binary logistic regression and ordinary least square regression).FindingsThe findings indicate that adequate knowledge of economic damage calculation and financial statement valuation is essential for forensic auditors' service. The results also reveal that forensic auditor skills and techniques is a significant predictor for fraud detection in the Nigerian public sector.Practical implicationsThe paper draws attention of the federal government parastatals to the need to improve their internal control system to reduce the fraudulent practices in their parastatal. The study also draws the attention of the Nigeria University Commission and the Institute of Chartered Accountants of Nigeria on the needs for revision of the accounting curricular for the training of accounting graduates and professional accountants in Nigeria.Social implicationsThe paper is of importance to other developing nation as it provides empirical evidence on the needs to do periodic forensic audits of government corporations.Originality/valueWith the persistent increase in the number of fraudulent cases, current views of those associated with forensic auditing (judiciaries, parastatals, forensic auditors and academics) on mechanisms for timely detection of fraud are needed.

Ashley A. Austin ◽  
Tina D Carpenter

Regulators express concern over auditors’ failure to respond to fraud risks. Audit firms communicate the importance of remaining skeptical and alert for fraud, but busy auditors give these messages insufficient attention. Building on psychology theory, we develop an innovative intervention designed to improve audit firm communication by incorporating game-like elements. We expect game-like elements to pique auditors’ interest, deepen their cognitive processing, enhance their awareness of important fraud concepts, and make them more alert for fraud. We experimentally demonstrate that the intervention improves auditors’ awareness of important fraud concepts, and these benefits persist to improve auditors’ fraud detection actions. Importantly, auditors receiving communication that simulates current practice fail to respond to heightened fraud risk, confirming regulators’ concerns. In additional analyses, a model supports our intervention promoting deeper processing of the communication, enabling auditors’ subsequent recognition of heightened fraud risk and effective actions. Thus, our results contribute to theory and practice.

2021 ◽  
Vol 6 (4) ◽  
pp. 355-358
Putri Intan Prastiwi ◽  
. Payamta

This study aims to identify methods in the detection of fraud in financial statements conducted by researchers in Indonesia. This research has been published on the website of the Ministry of Research and Technology with the SINTA 1 and SINTA 2 indexes. This research was conducted with a literature study on financial statement fraud in Indonesia. The research method used is a descriptive qualitative method by taking data from literacy studies on the research of fraud detection methods in Indonesia. The results of this study indicate that the fraud detection method used in financial reports in Indonesia is using the fraud Triangle method. The article of these studies is expected to provide input, insight, and information to all parties such as company management, auditors, and users of financial statements about various methods of detecting financial statement fraud in Indonesia.

Upasana Mukherjee ◽  
Vandana Thakkar ◽  
Shawni Dutta ◽  
Utsab Mukherjee ◽  
Samir Kumar Bandyopadhyay

The growth of regularly generated data from many financial activities has significant implications for every corner of financial modelling. This study has investigated the utilization of these continuous growing data by a means of an automated process. The automated process can be developed by using Machine learning based techniques that analyze the data and gain experience from the underlying data. Different important domains of financial fields such as Credit card fraud detection, bankruptcy detection, loan default prediction, investment prediction, marketing and many more can be modelled by implementing machine learning methods. Among several machine learning based techniques, the use of parametric and non-parametric based methods are approached by this research. Two parametric models namely Logistic Regression, Gaussian Naive Bayes models and two non-parametric methods such as Random Forest, Decision Tree are implemented in this paper. All the mentioned models are developed and implemented in the field of Credit card fraud detection, bankruptcy detection, loan default prediction. In each of the aforementioned cases, the comparative study among the classification techniques is drawn and the best model is identified. The performance of each classifier on each considered domain is evaluated by various performance metrics such as accuracy, F1-score and mean squared error. In the credit card fraud detection model the decision tree classifier performs the best with an accuracy of 99.1% and, in the loan default prediction and bankruptcy detection model, the random forest classifier gives the best accuracy of  97% and 96.84% respectively.

Sign in / Sign up

Export Citation Format

Share Document