Article · КазУТБ · March 30, 2026
BENCHMARKING CALIBRATED GRADIENT BOOSTING WITH BEHAVIOURAL FEATURES FOR TRANSACTION-LEVEL AML DETECTION
T.K. Azbergen, Arailym Tleubayeva, Askar Aituov, Y.T. Sabyrzhan
Abstract
Reliable transaction-level anti-money-laundering (AML) systems require not only accurate ranking of suspicious activity but also well-calibrated probabilistic risk estimates to support operational decision-making and risk prioritisation. In this context, this work provides an empirical evaluation of calibrated gradient boosting models with temporal behavioural features, focusing on the combined impact of probabilistic calibration and behavioural feature modelling on probability reliability and operationally relevant performance metrics. The proposed framework integrates gradient boosting algorithms (CatBoost and XGBoost) with post-hoc probability calibration techniques (Platt scaling and isotonic regression) and behavioural features computed over rolling time windows of 1, 7, and 30 days to capture both short-term volatility and longer-term transaction patterns. Experimental evaluation is conducted on the publicly available IBM Anti-Money Laundering (IBM–AML) dataset, which contains approximately seven million synthetic transactions simulating realistic banking activity. Model performance is assessed using ranking-, calibration-, and operationally oriented metrics, including AUPRC, AUROC, Brier score, Precision@Top k, and Lift@Top k. Among the evaluated baselines, the calibrated CatBoost model achieved the strongest overall balance between ranking quality and probability reliability (AUPRC = 0.367, AUROC = 0.959, Brier = 0.0062, Lift@1% = 40.9). The results indicate that probability calibration improves the reliability of predicted risk scores without degrading ranking performance, while temporal behavioural features contribute to improved detection sensitivity in highly imbalanced settings. This study provides benchmark-based empirical evidence regarding the role of probability calibration and behavioural dynamics in AML systems and offers a reproducible experimental pipeline for future comparative research. The applicability of the findings to real-world AML systems is discussed in light of the synthetic nature of the dataset, and directions for further validation on real banking data are outlined.
More by Askar Aituov
- Calibration-Aware Gradient Boosting With Temporal Behavioral Features for Anti-Money Laundering DetectionIEEE International Conference on Smart Information Systems and Technologies · 2026
- Digital Transformation in IT Project Management: The Impact of Cloud Technologies on Efficiency and Agile PerformanceIEEE International Conference on Smart Information Systems and Technologies · 2026
- The role of human and knowledge related artifacts in IT value co-creation2026
- Integrating CRM and CVM in Telecommunications: A Resource-Based View of Digital Targeted MarketingTrudy Universiteta · 2026
