Implementing AI-Driven Decision Support Systems in Data Management

Authors

  • Yazeed Alshuaibany College of Business, Al Yamamah University, Al Khobar, Saudi Arabia Author
  • Shabir Ahmad College of Business, Al Yamamah University, Al Khobar, Saudi Arabia Author

DOI:

https://doi.org/10.67887/PD2601202004

Keywords:

AI-Driven DSS, credit card fraud detection, SMOTE, XGBoost, SHAP, data management, machine learning, explainable AI, risk scoring, imbalanced classification, calibration, PR-AUC, MLOps, cost-sensitive learning

Abstract

Introduction: The rapid growth of digital financial transactions has increased exposure to fraud and highlighted the limitations of traditional decision support systems (DSS). Rule-based and scorecard-driven approaches struggle to operate effectively under conditions of extreme class imbalance, evolving fraud patterns, and regulatory requirements for transparency and auditability. This study aimed to design and evaluate an AI-driven DSS for credit card fraud detection that integrated machine learning, class-imbalance mitigation, explainability, and cost-sensitive decision logic to support operational fraud analysis.

Method: The study used the publicly available Kaggle Credit Card Fraud dataset comprising 284,807 transactions, of which 0.17% were fraudulent. A stratified 80/20 split yielded a hold-out test set of 4,000 transactions, including 7 fraud cases. Class imbalance was addressed using the Synthetic Minority Oversampling Technique (SMOTE) applied exclusively within training folds. Logistic Regression, Random Forest, and XGBoost models were trained and evaluated. Given the extreme imbalance, Precision–Recall Area Under the Curve (PR–AUC) was treated as the primary evaluation metric, with recall, precision, F1-score, and ROC–AUC reported as complementary measures. Performance uncertainty was quantified using bootstrap confidence intervals. Probability calibration was applied to XGBoost outputs, and a cost-sensitive threshold optimisation framework was used to define operational risk tiers. SHapley Additive exPlanations (SHAP) were incorporated to support model transparency.

Results: XGBoost achieved the highest PR–AUC (0.568) compared with Random Forest (0.512) and Logistic Regression (0.341), while exhibiting comparable recall (0.571) to Random Forest on the imbalanced test set. Bootstrap confidence intervals indicated substantial uncertainty due to the limited number of fraud cases, underscoring the need for cautious interpretation of point estimates. Calibration improved probability reliability, and cost-sensitive thresholding produced consistent low-, medium-, and high-risk classifications. SHAP analysis provided global and local explanations of model behaviour, although the use of anonymised PCA-derived features constrained interpretability.

Conclusion: The findings demonstrated that integrating SMOTE, XGBoost, calibration, and SHAP within an AI-driven DSS supported improved fraud prioritisation under severe class imbalance while maintaining transparency and operational feasibility. Rather than replacing existing systems, the proposed framework illustrated how AI models can augment DSS by enabling calibrated risk scoring, uncertainty-aware evaluation, and analyst-oriented triage in regulated financial environments.

References

Biswas TR, Hossain MZ, Comite U. Role of Management Information Systems in Enhancing Decision-Making in Large-Scale Organizations. Pacific J Bus Innov Strategy. 2024; 1(1): 5-18. https://doi.org/10.70818/pjbis.2024.v01i01.03

Gade KR. Data-driven decision making in a complex world. J Comput Innov. 2021;1(1). Available from: https://researchworkx.com/index.php/jci/article/view/2/2

Alojail M, Alturki M, Bhatia Khan S. An informed decision support framework from a strategic perspective in the health sector. Inf. 2023; 14(7): 363. https://doi.org/10.3390/info14070363

Pourrahimian E, Salhab D, Hamzeh F, AbouRizk S. A decision support system for evaluating construction project recovery plans. Can J Civ Eng. 2025. https://doi.org/10.1139/cjce-2024-0525

Talari G, Cummins E, McNamara C, O'Brien J. State of the art review of Big Data and web-based Decision Support Systems (DSS) for food safety risk assessment with respect to climate change. Trends Food Sci Technol. 2022; 126: 192-204. https://doi.org/10.1016/j.tifs.2021.08.032

Ekundayo F. Leveraging AI-driven decision intelligence for complex systems engineering. Int J Res Publ Rev. 2024; 5(11): 1-10. https://doi.org/10.55248/gengpi.5.1124.3343.

Kovari A. AI for decision support: Balancing accuracy, transparency, and trust across sectors. Inf. 2024; 15(11): 725. https://doi.org/10.3390/info15110725

Al-Jumaili AHA, Muniyandi RC, Hasan MK, Paw JKS, Singh MJ. Big data analytics using cloud computing-based frameworks for power management systems: Status, constraints, and future recommendations. Sensors. 2023; 23(6): 2952. https://doi.org/10.3390/s23062952

Agarwal G. Robust Data Pipelines for AI Workloads: Architectures, Challenges, and Future Directions. Int J Adv Res Sci Commun Technol. 2024; 5(2): 622-632. https://doi.org/10.48175/IJARSCT-23391

Jayavel M. International Journal of Innovative Research in Computer and Communication Engineering. Int J Innov Res Comput Commun Eng. 2025; 13(3): 2039-2045. http://dx.doi.org/10.2139/ssrn.5162705

Pillai V. Anomaly detection in financial and insurance data-systems. J AI-Assisted Sci Discov. 2024; 4(2): 144-183. Available from: https://www.researchgate.net/publication/386382514_Anomaly_Detection_in_Financial_and_Insurance_Data-Systems

Lee JH, You SJ. Balancing privacy and accuracy: Exploring the impact of data anonymization on deep learning models in computer vision. IEEE Access. 2024; 12: 8346-8358. https://doi.org/10.1109/ACCESS.2024.3352146

Altalhan M, Algarni A, Alouane MTH. Imbalanced data problem in machine learning: A review. IEEE Access. 2025; 13:13686-13699. https://doi.org/10.1109/ACCESS.2025.3531662

Hajek P, Abedin MZ, Sivarajah U. Fraud detection in mobile payment systems using an XGBoost-based framework. Inf Syst Front. 2023; 25(5): 1985-2003. https://doi.org/10.1007/s10796-022-10346-6

Ravichandran P, Machireddy JR, Rachakatla SK. AI-Enhanced data analytics for real-time business intelligence: Applications and challenges. J AI Healthcare Med. 2022; 2(2): 168-195. Available from: https://www.researchgate.net/publication/389139259_AI-Enhanced_Data_Analytics_for_Real-Time_Business_Intelligence_Applications_and_Challenges.

Rainy TA, Goswami D, Rabbi MS, Al Maruf A. A systematic review of ai-enhanced decision support tools in information systems: strategic applications in service-oriented enterprises and enterprise planning. Rev Appl Sci Technol. 2023; 2(01): 26-52. https://doi.org/10.63125/73djw422

Ashfaq T, Khalid R, Yahaya AS, Aslam S, Azar AT, Alsafari S, Hameed IA. A machine learning and blockchain-based efficient fraud detection mechanism. Sensors. 2022; 22(19): 7162. https://doi.org/10.3390/s22197162

Malik P, Chourasia A, Pandit R, Bawane S, Surana J. Credit risk assessment and fraud detection in financial transactions using machine learning. J Electr Syst. 2024; 20(3s): 2061-2069. https://doi.org/10.52783/jes.1807.

Olushola A, Mart J. Fraud detection using machine learning. SciOpen Preprints. 2024. https://doi.org/10.14293/PR2199.000647.v1

Bello OA, Ogundipe A, Mohammed D, Adebola F, Alonge OA. AI-driven approaches for real-time fraud detection in US financial transactions: Challenges and opportunities. Eur J Comput Sci Inf Technol. 2023; 11(6): 84-102. https://doi.org/10.37745/ejcsit.2013/vol11n684102

Alzaabi FR, Mehmood A. A review of recent advances, challenges, and opportunities in malicious insider threat detection using machine learning methods. IEEE Access. 2024; 12: 30907-30927. https://doi.org/10.1109/ACCESS.2024.3369906

Trigka M, Dritsas E. Improving cardiovascular disease prediction with deep learning and correlation-aware SMOTE. IEEE Access. 2025. https://doi.org/10.1109/ACCESS.2025.3549417

Khan D, Akram W, Ullah S. Enhancing landslide susceptibility predictions with XGBoost and SHAP: a data-driven explainable AI method. Geocarto Int. 2025; 40(1): 2514725. https://doi.org/10.1080/10106049.2025.2514725

Komati D. Real-Time AI Systems for Fraud Detection and Credit Risk Management: A Framework for Financial Institutions. IJSAT-Int J Sci Technol. 2025; 16(1): 1-13. https://doi.org/10.71097/IJSAT.v16.i1.2974

Teles G, Rodrigues JJ, Kozlov SA, Rabêlo RA, Albuquerque VHC. Decision support system on credit operation using linear and logistic regression. Expert Syst. 2021; 38(6): e12578. https://doi.org/10.1111/exsy.12578

Li M, Sun H, Huang Y, Chen H. Shapley value: from cooperative game to explainable artificial intelligence. Auton Intell Syst. 2024; 4(1): 2. https://doi.org/10.1007/s43684-023-00060-8

Ortigossa ES, Gonçalves T, Nonato LG. Explainable artificial intelligence (XAI) from theory to methods and applications. IEEE Access. 2024; 12: 80799-80846. https://doi.org/10.1109/ACCESS.2024.3409843

Favour AA. Regulatory compliance challenges in cloud-based ai fraud detection systems. 2022. Available from: https://www.researchgate.net/profile/Akintan-Favour/publication/391454540_Regulatory_Compliance_Challenges_in_Cloud-Based_AI_Fraud_Detection_Systems/links/6818ebbc60241d514022afe4/Regulatory-Compliance-Challenges-in-Cloud-Based-AI-Fraud-Detection-Systems.pdf (Accessed on: 19 September, 2022).

Pratama SF, Wahid AMA. Fraudulent transaction detection in online systems using random forest and gradient boosting. J Cyber Law. 2025; 1(1): 88-115. https://doi.org/10.63913/jcl.v1i1.5

Vishwakarma SK. AI-driven predictive risk modelling for aerospace supply chains. Int Interdiscip Bus Econ Adv J. 2025; 6(05): 102-134. https://doi.org/10.55640/business/volume06issue05-06

Dekker R. The importance of having data-sets. Available from: https://www.researchgate.net/publication/42581175_The_importance_of_having_data-sets (Accessed on Jan, 2006).

Singhal A, Srivastava J. Research dataset discovery from research publications using web context. Web Intell. 2017; 15(2): 81-99. https://doi.org/10.3233/web-170354

Downloads

Published

2026-05-04

Issue

Section

Articles