Counterfactual Methods for Detecting Unfairness in Anti-Money Laundering Algorithms

The application of machine learning-based predictive algorithms to Anti-Money Laundering (AML) has grown rapidly, driven by the vast volume of financial transaction data available to banks. These algorithms are typically trained not only on transactional data but also on sensitive client information, which may raise fairness concerns. Despite this, AML detection systems remain largely underexplored from a fairness perspective, even though deeper analytical methods based on counterfactuals are now available. Such techniques enable the decomposition of the direct and indirect effects of potentially sensitive features on model predictions, thereby supporting the evaluation of whether their influence is acceptable from a fairness perspective. Closing this gap, we consider the synthetic IBM AMLSim transaction dataset and construct additional features of the country of an account and its average behaviour. This improves the predictive performance of diverse machine learning models, ranging from baseline decision trees to state-of-the-art graph neural networks. We assess the potential unfairness associated with these features through a counterfactual, path-specific effect analysis. This reveals that fairness violations tend to be more pronounced for models whose predictive performance benefits the most from the extended features. Such a finding highlights a concrete instance of the trade-off between predictive accuracy and fairness in AML applications, thus underscoring the urgency of a systematic fairness analysis in such critical domains.

Improving Post-Earthquake Crack Detection using Semi-Synthetic Generated Images

Following an earthquake, it is vital to quickly evaluate the safety of the impacted areas. Damage detection systems, powered by computer vision and deep learning, can assist experts in this endeavor. However, the lack of extensive, labeled datasets poses a challenge to the development of these systems. In this study, we introduce a technique for generating semi-synthetic images to be used as data augmentation during the training of a damage detection system. We specifically aim to generate images of cracks, which are a prevalent and indicative form of damage. The central concept is to employ parametric meta-annotations to guide the process of generating cracks on 3D models of real-word structures. The governing parameters of these meta-annotations can be adjusted iteratively to yield images that are optimally suited for improving detectors' performance. Comparative evaluations demonstrated that a crack detection system trained with a combination of real and semi-synthetic images outperforms a system trained on real images alone.