Paradise
Paradise | Life Science Engineering Business Natural Science
0
Citations
4.9k
Views
19
Articles
Volume 1 Number 1 2025
RESEARCH ARTICLE (Open Access)
AI in Fraud Detection and Forensic Accounting Detecting Anomalies and Fraudulent Transactions to Strengthen Financial Integrity
Muslima Jahan Diba1*, Md. Rezaul Haque2, Md Nazmuddin Moin Khan3
Paradise 1 (1) 1-8 https://doi.org/10.25163/paradise.1110494
Submitted: 05 March 2025 Revised: 07 May 2025 Accepted: 13 May 2025 Published: 15 May 2025
Abstract
Background: Financial operations in organizations face continuous threats from fraud which results in operational disruptions and damages the confidence of all stakeholders. Traditional auditing and manual forensic accounting methods often fail to detect complex anomalies in high-volume transactions.
Methods: A total of 210 financial professionals, including auditors, accountants, and financial analysts, were surveyed, and historical transaction data spanning 12 months were analyzed at January to December in 2024. The research team applied Long Short-Term Memory (LSTM) and Convolutional Neural Networks (CNN) and Random Forest (RF) and hybrid frameworks to detect anomalies through AI model implementation. The evaluation of model performance used detection share metrics together with precision and recall rates and correlation coefficients (r). The study used statistical methods including chi-square (χ²) tests and t-tests and p-values to determine how AI adoption levels affect model performance and fraud detection results.
Results: LSTM models achieved the highest detection share (24.5%), while hybrid AI frameworks reduced false positives by 15–20% and balanced precision and recall. Unauthorized transfers (21%) and inflated invoices (19%) were the most frequently detected anomalies. The chi-square analysis revealed that AI adoption links directly to anomaly detection success at χ² = 4.59 with p = 0.048 and t-tests showed that different adoption levels created distinct fraud reduction outcomes. The results showed positive correlations between AI intensity and fraud reduction with correlation coefficients (r = 0.28-0.56).
Conclusion: AI systems achieve superior results by integrating LSTM with hybrid frameworks which enhances financial integrity and advances anomaly detection systems.
Keywords: Artificial Intelligence, Forensic Accounting, Fraud Detection, Anomaly Detection, Financial Integrity
References
Alghofaili, Y., Albattah, A., & Rassam, M. A. (2020). A financial fraud detection model based on LSTM deep learning technique. Journal of Applied Security Research, 15(4), 498–516. https://doi.org/10.1080/19361610.2020.1815491
Azar, A. T., Shehab, E., Mattar, A. M., Hameed, I. A., & Elsaid, S. A. (2023). Deep learning based hybrid intrusion detection systems to protect satellite networks. Journal of Network and Systems Management, 31(4). https://doi.org/10.1007/s10922-023-09767-8
Bakhshi, T., & Ghita, B. (2021). Anomaly detection in encrypted internet traffic using hybrid deep learning. Security and Communication Networks, 2021, 1–16. https://doi.org/10.1155/2021/5363750
Bao, F., Wu, Y., Li, Z., Li, Y., Liu, L., & Chen, G. (2020). Effect improved for High-Dimensional and Unbalanced Data Anomaly Detection Model based on KNN-SMOTE-LSTM. Complexity, 2020, 1–17. https://doi.org/10.1155/2020/9084704
Benchaji, I., Douzi, S., Ouahidi, B. E., & Jaafari, J. (2021). Enhanced credit card fraud detection based on attention mechanism and LSTM deep model. Journal of Big Data, 8(1). https://doi.org/10.1186/s40537-021-00541-8
Beniwal, M., Singh, A., & Kumar, N. (2023). Forecasting long-term stock prices of global indices: A forward-validating Genetic Algorithm optimization approach for Support Vector Regression. Applied Soft Computing, 145, 110566. https://doi.org/10.1016/j.asoc.2023.110566
Bogaerts, T., Masegosa, A. D., Angarita-Zapata, J. S., Onieva, E., & Hellinckx, P. (2020). A graph CNN-LSTM neural network for short and long-term traffic forecasting based on trajectory data. Transportation Research Part C Emerging Technologies, 112, 62–77. https://doi.org/10.1016/j.trc.2020.01.010
Cascone, L., Sadiq, S., Ullah, S., Mirjalili, S., Siddiqui, H. U. R., & Umer, M. (2022). Predicting Household Electric Power Consumption Using Multi-step Time Series with Convolutional LSTM. Big Data Research, 31, 100360. https://doi.org/10.1016/j.bdr.2022.100360
Chakraborty, S. K., Chandel, N. S., Jat, D., Tiwari, M. K., Rajwade, Y. A., & Subeesh, A. (2022). Deep learning approaches and interventions for futuristic engineering in agriculture. Neural Computing and Applications, 34(23), 20539–20573. https://doi.org/10.1007/s00521-022-07744-x
Chithanuru, V., & Ramaiah, M. (2023). An anomaly detection on blockchain infrastructure using artificial intelligence techniques: Challenges and future directions – A review. Concurrency and Computation Practice and Experience, 35(22). https://doi.org/10.1002/cpe.7724
Dua, N., Singh, S. N., Semwal, V. B., & Challa, S. K. (2022). Inception inspired CNN-GRU hybrid network for human activity recognition. Multimedia Tools and Applications, 82(4), 5369–5403. https://doi.org/10.1007/s11042-021-11885-x
Goel, A., Goel, A. K., & Kumar, A. (2022). The role of artificial neural network and machine learning in utilizing spatial information. Spatial Information Research, 31(3), 275–285. https://doi.org/10.1007/s41324-022-00494-x
Gupta, S. (2021). Deep learning based human activity recognition (HAR) using wearable sensor data. International Journal of Information Management Data Insights, 1(2), 100046. https://doi.org/10.1016/j.jjimei.2021.100046
Himeur, Y., Elnour, M., Fadli, F., Meskin, N., Petri, I., Rezgui, Y., Bensaali, F., & Amira, A. (2022). AI-big data analytics for building automation and management systems: a survey, actual challenges and future perspectives. Artificial Intelligence Review, 56(6), 4929–5021. https://doi.org/10.1007/s10462-022-10286-2
Hu, W., Wang, X., Tan, K., & Cai, Y. (2023). Digital twin-enhanced predictive maintenance for indoor climate: A parallel LSTM-autoencoder failure prediction approach. Energy and Buildings, 301, 113738. https://doi.org/10.1016/j.enbuild.2023.113738
Karpoff, J. M. (2020). The future of financial fraud. Journal of Corporate Finance, 66, 101694. https://doi.org/10.1016/j.jcorpfin.2020.101694
Lu, B., Xu, D., & Huang, B. (2021). Deep-learning-based anomaly detection for lace defect inspection employing videos in production line. Advanced Engineering Informatics, 51, 101471. https://doi.org/10.1016/j.aei.2021.101471
Mobtahej, P., Zhang, X., Hamidi, M., & Zhang, J. (2022). An LSTM-Autoencoder architecture for anomaly detection applied on compressors audio data. Computational and Mathematical Methods, 2022, 1–22. https://doi.org/10.1155/2022/3622426
Panjapornpon, C., Bardeeniz, S., Hussain, M. A., & Chomchai, P. (2022). Explainable deep transfer learning for energy efficiency prediction based on uncertainty detection and identification. Energy and AI, 12, 100224. https://doi.org/10.1016/j.egyai.2022.100224
Pocher, N., Zichichi, M., Merizzi, F., Shafiq, M. Z., & Ferretti, S. (2023). Detecting anomalous cryptocurrency transactions: An AML/CFT application of machine learning-based forensics. Electronic Markets, 33(1). https://doi.org/10.1007/s12525-023-00654-3
Rasheed, M. U., & Mahmood, S. A. (2023). A framework base on deep neural network (DNN) for land use land cover (LULC) and rice crop classification without using survey data. Climate Dynamics, 61(11–12), 5629–5652. https://doi.org/10.1007/s00382-023-06874-9
Remeikiene, R., & Gaspareniene, L. (2023). Effects of economic and financial crime on the government budget and the quality of public services. In Contributions to finance and accounting (pp. 173–204). https://doi.org/10.1007/978-3-031-34082-6_8
Selvarajan, S., Srivastava, G., Khadidos, A. O., Khadidos, A. O., Baza, M., Alshehri, A., & Lin, J. C. (2023). An artificial intelligence lightweight blockchain security model for security and privacy in IIoT systems. Journal of Cloud Computing Advances Systems and Applications, 12(1). https://doi.org/10.1186/s13677-023-00412-y
Thakkar, A., & Lohiya, R. (2021). A survey on intrusion detection system: feature selection, model, performance measures, application perspective, challenges, and future research directions. Artificial Intelligence Review, 55(1), 453–563. https://doi.org/10.1007/s10462-021-10037-9
Ullah, W., Ullah, A., Haq, I. U., Muhammad, K., Sajjad, M., & Baik, S. W. (2020). CNN features with bi-directional LSTM for real-time anomaly detection in surveillance networks. Multimedia Tools and Applications, 80(11), 16979–16995. https://doi.org/10.1007/s11042-020-09406-3
Xu, H., Sun, Z., Cao, Y., & Bilal, H. (2023). A data-driven approach for intrusion and anomaly detection using automated machine learning for the Internet of Things. Soft Computing, 27(19), 14469–14481. https://doi.org/10.1007/s00500-023-09037-4
Xuan, C. D., & Dao, M. H. (2021). A novel approach for APT attack detection based on combined deep learning model. Neural Computing and Applications, 33(20), 13251–13264. https://doi.org/10.1007/s00521-021-05952-5
Zarpala, L., & Casino, F. (2021). A blockchain-based forensic model for financial crime investigation: the embezzlement scenario. Digital Finance, 3(3–4), 301–332. https://doi.org/10.1007/s42521-021-00035-5
Zhang, F., & Wen, N. (2022). Carbon price forecasting: a novel deep learning approach. Environmental Science and Pollution Research, 29(36), 54782–54795. https://doi.org/10.1007/s11356-022-19713-x
Zonta, T., Da Costa, C. A., Zeiser, F. A., De Oliveira Ramos, G., Kunst, R., & Da Rosa Righi, R. (2022). A predictive maintenance model for optimizing production schedule using deep neural networks. Journal of Manufacturing Systems, 62, 450–462. https://doi.org/10.1016/j.jmsy.2021.12.013