MODELING ELECTRONIC MONEY TRANSACTION FRAUD VOLUMES IN KENYA USING GENERALISED AUTOREGRESSIVE CONDITIONAL HETEROSKEDASTIC MODEL

Autores/as

  • Ondiwa Simon Oluoch Adjunct Lecturer, Dr., Department of Accounting and Finance, Maseno University, Kenya
  • Ondiwa Micah Oketch MSc, Financial Engineering, World Quant University, New Orleans, Louisiana, United States of America
  • Ondiwa Domnic Odoyo Adjunct Lecturer, Department of Accounting and Finance, KCA University, Nairobi, Kenya
  • Martin Sure Ondiwa Geospatial Engineer, School of Surveying and Geospatial Science, The Technical University of Kenya, Kenya

DOI:

https://doi.org/10.46827/ejefr.v8i7.1883

Palabras clave:

modelling, electronic money, GARCH, machine learning, deep learning, fraud detection

Resumen

Electronic transaction fraud has been on the increase in recent times. Though technology advancement is cited as a major milestone in the global business environment, at times, it comes with challenges, such as financial risks. Businesses and individuals have been losing their hard-earned funds through online-related transaction frauds, and the trend continues to increase. Studies reviewed heavily used deep learning and machine learning to investigate the detection of online-related fraudulent activities. The current study, however, deviated from this norm by focusing on modelling electronic transaction fraud volumes using the Generalised Auto-regressive Conditional Heteroscedastic (GARCH) model. The study employed grid search cross-validation parameter optimisation techniques and popular loss functions, including Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Akaike Information Criterion (AIC), and Bayesian Information Criterion (BIC) to find the best-fitting model. The study objective was to establish a suitable model for forecasting changes (Variations) in the volume of money lost from fraudulent transactions in Kenya. The study is anchored on the fraud triangle model and fraud diamond model. The study revealed that GARCH (1,1) model predicts electronic transaction fraud volume deviations in Kenya; with the prediction, the risk of financial losses can be averted. This study is important to stakeholders such as the public, corporations, regulators such as the Central Bank of Kenya, financial institutions such as commercial banks, and scholars.

 

JEL: E52, E43, G21, G23, C25, D12, E42

 

Article visualizations:

Hit counter

Biografía del autor/a

  • Ondiwa Simon Oluoch, Adjunct Lecturer, Dr., Department of Accounting and Finance, Maseno University, Kenya

    Dr. Ondiwa Simon is an MSME consultant, and he is currently working with DT Global International Development EA Limited. Previously, he worked as an adjunct lecturer in the School of Business and Economics at Maseno University in Kenya. He has also been a collaborator in research by The University of Maryland, USA, and Maseno University, assessing the current status of the cassava value chain and food security in Kenya and the Democratic Republic of Congo. Dr. Ondiwa holds a PhD in Business Administration, a Finance Major, an MBA, a Finance Major and a Bachelor of Business Administration Finance. His research interest is the operations of financial institutions and markets.

  • Ondiwa Micah Oketch, MSc, Financial Engineering, World Quant University, New Orleans, Louisiana, United States of America

    Mr. Micah Oketch Ondiwa holds a Bachelor of Science in Actuarial Science from Jomo Kenyatta University of Agriculture and Technology and a Master of Science in Financial Engineering from WorldQuant University, New Orleans, Louisiana, United States of America. Mr. Micah is a professional data analyst with top-notch knowledge of deep learning and machine learning coupled with software engineering. Currently, Mr. Micah works with The Kenya National Highway Authority. With over seven years of experience, Mr. Micah’s research interest is in software engineering and machine learning.

  • Ondiwa Domnic Odoyo, Adjunct Lecturer, Department of Accounting and Finance, KCA University, Nairobi, Kenya

    Mr. Domnic Odoyo holds a bachelor’s degree in business administration with IT, specialising in accounting. Furthermore, he is a professional accountant in Kenya. He is a registered member of the Institute of Certified Public Accountants of Kenya (ICPAK). Dominic is also an adjunct lecturer at KCA University in Kenya. Domnic’s interest is auditing and taxation. He has cumulatively over eight years of industry and academic experience.

  • Martin Sure Ondiwa, Geospatial Engineer, School of Surveying and Geospatial Science, The Technical University of Kenya, Kenya

    Mr. Martin Sure holds a Bachelor of Science in Land Survey from The Technical University of Kenya. Mr. Martin is, therefore, a land surveyor and software developer. Besides, Mr. Martin’s interest is in agriculture. His work in agriculture was recognised and rewarded by anzisha price, the African Leadership Academy, YALI-East Africa and the Global Student Entrepreneurs Award.

Referencias

Abdel-Rahman, L. A., & Andriansyah, Y. (2023). The Role of Artificial Intelligence in Modern Banking: An Exploration of AI-Driven Approaches for Enhanced Fraud Prevention, Risk Management, and Regulatory Compliance. RCBA 6(1) https://orcid.org/0000-0003-3394-5222, 110-132.

Adedoyin, A. (2018). Predicting Fraud in Mobile Money Transfer. Unpublished PhD Thesis at The University of Brighton.

Ahmad, I., Iqbal, S., Jamil, S., & Kamran, M. (2021). A Systematic Literature Review of E-Banking Frauds: Scenario and Security Techniques. Lingustica Antyerpiesia 2, 3509-3517.

Amiri, M., & Hekmat, S. (2021). Banking Fraud: A Consumer-side Overview of Categories and Frameworks of Detection and Prevention. Journal of Applied Intelligent Systems and Information Sciences 2(2) www.journal.research.fanap.com, 58-68.

Arkhipov, A., Arkhipova, N., & Karminsky, A. (2021). Regulation of Financial Risks in Emerging Markets: Past, Present, and Future. In Risk Assessment and Financial Regulation in Emerging Market's Banking. Trends and Prospects https://link.springer.com/chapter/10.1007/978-3-030-69748-8_2.

Bache, I. W. (2024). Financial Infrastructure Report. Oslo: Norges Bank, Norway https://norges-bank.brage.unit.no/norges-bank xmlui/bitstream/handle/11250/3132845/fi_2024_eng_web_1245.pdf?sequence=1.

Bankole, O. A. (2024). Implementation of Posti’s Mail and Parcel Logistics System for the Modernization and Efficiency Enhancement of Nigerian Postal Services. Bachelor's Thesis at Jamk University of Applied Sciences, https://www.theseus.fi/bitstream/handle/10024/863436/Bankole_Omotoyosi.pdf?sequence=2&isAllowed=y.

Burgalassi, D., & Matsumoto, T. (2024). Demographic change in cities: Trends, challenges and insights from G7 economies. OECDilibrary https://www.oecd-ilibrary.org/content/paper/f2aec988-en.

CBK. (2024). The Central Bank of Kenya Official Website. Nairobi: Central Bank of Kenya https://www.centralbank.go.ke/national-payments-system/payment-cards/value-of-transactions-ksh-millions/.

Cohen, L., Manion, L., & Morrison, K. (2000). Research methods in education. London: Routledge Falmer.

Cressey, D. R. (1950). The Criminal Violation of Financial Trust. American Sociological Review https://doi.org/doi:10.2307/2086606, 738-743.

Creswell, J. W. (2013). Qualitative inquiry and research design: Choosing among five approaches (3rd ed). Thousand Oaks: CA: Sage.

Crotty, M. (1998). The foundation of social research: Meaning and perspective in the research process. Thousand Oaks: CA: Sage.

Gabudeanu, L., Brici, I., Mare, C., Mihai, I. C., & Scheau, M. C. (2021). Privacy Intrusiveness in Financial- Banking Fraud Detection. Risks 9: 104.

Ge, X. (2024). Design of an Enterprise Financial Information Management System Based on Virtual Reality for Hypertext System Interactive Devices. Computer-Aided Design & Applications 21(S17)

https://www.cad-journal.net/files/vol_21/CAD_21(S17)_2024_270-288.pdf, 270-288.

Hetzel, M. (2021). How Technological Frames Transform: The case of the global microgrid industry. Doctoral Dissertation https://iris.luiss.it/bitstream/11385/183510/5/Finance%20for%20Growth.pdf.

Jawad, M., & Naz, M. (2023). Financial Technological Innovation, Sustainable Operations, and Efficiency: A study of SMBs in Times of Crisis. Journal of the Knowledge Economy https://link.springer.com/article/10.1007/s13132-023-01574-5, 1-22.

KNBS. (2021). FinAccess Household Survey. Nairobi: Kenya National Bureau of Statistics.

Lokanan, M. E. (2023). Predicting mobile money transaction fraud using machine learning algorithms. Wiley.

Marakalala, M. C. (2023). Forensic Intelligence: The Effectiveness of the Biometric-based Solution to Combat Mobile Fraud. International Journal of Sustainable Development http://www.ssrn.com/link/OIDA-Intl-Journal-Sustainable-Dev.html, 20-30.

Mertens, D. M. (2010). Research and evaluation in education and Psychology: Integrating diversity with quantitative, qualitative, and mixed methods (3rd ed). Thousand Oaks: CA: Sage.

Mustafa, J. A. (2024). Integrating Financial Literacy, Regulatory Technology, and Decentralized Finance: A New Paradigm in Fintech Evolution. Investment Management and Financial Innovations, Business Perspectives 21(2) https://www.businessperspectives.org/images/pdf/applications/publishing/templates/article/assets/20066/IMFI_2024_02_Mustafa.pdf, 213-226.

Neuman, W. L. (2009). Social Research Methods: Qualitative and Quantitative approaches (7th ed). Pearson Education Inc: Boston.

Ogay, M. (2020). Capital markets development in the emerging market. https://tesi.univpm.it/bitstream/20.500.12075/1386/2/Ogay%20Marina_Capital%20markets%20development%20in%20the%20emerging%20markets_17.06.2021.pdf

Okoye, N. J., Onuoha, O. C., & Akuesodo, O. E. (2021). E-Commerce and Mobile Banking Fraud: Examining the Nexus on the Performance of Deposit Money Banks in Nigeria. IOSR Journal of Economics and Finance 12(3), 42-60.

Phiri, J., Lavhengwa, T., & Segooa, M. A. (2024). Online banking fraud detection: A comparative study of cases from South Africa and Spain. South Africa Journal of Information Management, 1-8.

Regnard-Weinrabe, B., Kikki, J., & Finlayson-Brown, J. (2024). Adapting to a Challenging Payments landscape. Elgaronline https://doi.org/10.4337/9781035314751.00012, 24-74.

Sanchez-Castany, R. (2024). Industry Insights About Translation Technologies: Current Needs and Future Trends. In New Translation Technology: Applications and Pedagogy. Springer Nature https://link.springer.com/chapter/10.1007/978-981-97-2958-6_6, 99-119.

Shrivastava, S., & Johari, P. K. (2022). Convolutional Neural Network Approach for Mobile Banking Fraudulent Transaction to Detect Financial Frauds. International Journal of Engineering Technology and Management Sciences, 30-37.

Wolfe, D. T., & Hermanson, D. R. (2004). The Fraud Diamond: Considering the Four Elements of Fraud. The CPA Journal 74(12), 38-42.

Zekos, G. I. (2021). E-Globalization and Digital Economy. Economics and Law of Artificial Intelligence: Finance, Economic Impacts, Risk Management and Governance. Springer https://link.springer.com/chapter/10.1007/978-3-030-64254-9_2, 13-66.

Descargas

Publicado

2025-01-05

Número

Vol. 8 Núm. 7 (2024)

Sección

Articles