Research Papers

Anti-Money Laundering Machine Learning Pipelines; A Technical Analysis on Identifying High-risk Bank Clients with Supervised Learning

Khashayar Namdar, Pin-Chien Wang, Tushar Raju +3

Anti-money laundering (AML) actions and measurements are among the priorities of financial institutions, for which machine learning (ML) has shown to have a high potential. In this paper, we propose a comprehensive and systematic approach for developing ML pipelines to identify high-risk bank clients in a dataset curated for Task 1 of the University of Toronto 2023-2024 Institute for Management and Innovation (IMI) Big Data and Artificial Intelligence Competition. The dataset included 195,789 customer IDs, and we employed a 16-step design and statistical analysis to ensure the final pipeline was robust. We also framed the data in a SQLite database, developed SQL-based feature engineering algorithms, connected our pre-trained model to the database, and made it inference-ready, and provided explainable artificial intelligence (XAI) modules to derive feature importance. Our pipeline achieved a mean area under the receiver operating characteristic curve (AUROC) of 0.961 with a standard deviation (SD) of 0.005. The proposed pipeline achieved second place in the competition.

The rise of misinformation underscores the need for scalable and reliable fact-checking solutions. Large language models (LLMs) hold promise in automating fact verification, yet their effectiveness across global contexts remains uncertain. We systematically evaluate nine established LLMs across multiple categories (open/closed-source, multiple sizes, diverse architectures, reasoning-based) using 5,000 claims previously assessed by 174 professional fact-checking organizations across 47 languages. Our methodology tests model generalizability on claims postdating training cutoffs and four prompting strategies mirroring both citizen and professional fact-checker interactions, with over 240,000 human annotations as ground truth. Findings reveal a concerning pattern resembling the Dunning-Kruger effect: smaller, accessible models show high confidence despite lower accuracy, while larger models demonstrate higher accuracy but lower confidence. This risks systemic bias in information verification, as resource-constrained organizations typically use smaller models. Performance gaps are most pronounced for non-English languages and claims originating from the Global South, threatening to widen existing information inequalities. These results establish a multilingual benchmark for future research and provide an evidence base for policy aimed at ensuring equitable access to trustworthy, AI-assisted fact-checking.

In our age of digital platforms, human attention has become a scarce and highly valuable resource, rivalrous, tradable, and increasingly subject to market dynamics. This article explores the commodification of attention within the framework of the attention economy, arguing that attention should be understood as a common good threatened by over-exploitation. Drawing from philosophical, economic, and legal perspectives, we first conceptualize attention not only as an individual cognitive process but as a collective and infrastructural phenomenon susceptible to enclosure by digital intermediaries. We then identify and analyze negative externalities of the attention economy, particularly those stemming from excessive screen time: diminished individual agency, adverse health outcomes, and societal and political harms, including democratic erosion and inequality. These harms are largely unpriced by market actors and constitute a significant market failure. In response, among a spectrum of public policy tools ranging from informational campaigns to outright restrictions, we propose a Pigouvian tax on attention capture as a promising regulatory instrument to internalize the externalities and, in particular, the social cost of compulsive digital engagement. Such a tax would incentivize structural changes in platform design while preserving user autonomy. By reclaiming attention as a shared resource vital to human agency, health, and democracy, this article contributes a novel economic and policy lens to the debate on digital regulation. Ultimately, this article advocates for a paradigm shift: from treating attention as a private, monetizable asset to protecting it as a collective resource vital for humanity.

RelAItionship Building: Analyzing Recruitment Strategies for Participatory AI

Eugene Kim, Vaibhav Balloli, Berelian Karimian +2

Participatory AI, in which impacted community members and other stakeholders are involved in the design and development of AI systems, holds promise as a way to ensure AI is developed to meet their needs and reflect their values. However, the process of identifying, reaching out, and engaging with all relevant stakeholder groups, which we refer to as recruitment methodology, is still a practical challenge in AI projects striving to adopt participatory practices. In this paper, we investigate the challenges that researchers face when designing and executing recruitment methodology for Participatory AI projects, and the implications of current recruitment practice for Participatory AI. First, we describe the recruitment methodologies used in AI projects using a corpus of 37 projects to capture the diversity of practices in the field and perform an initial analysis on the documentation of recruitment practices, as well as specific strategies that researchers use to meet goals of equity and empowerment. To complement this analysis, we interview five AI researchers to learn about the outcomes of recruitment methodologies. We find that these outcomes are shaped by structural conditions of their work, researchers' own goals and expectations, and the relationships built from the recruitment methodology and subsequent collaboration. Based on these analyses, we provide recommendations for designing and executing relationship-forward recruitment methods, as well as reflexive recruitment documentation practices for Participatory AI researchers.

People's experiences of discrimination are often shaped by multiple intersecting factors, yet algorithmic fairness research rarely reflects this complexity. While intersectionality offers tools for understanding how forms of oppression interact, current approaches to intersectional algorithmic fairness tend to focus on narrowly defined demographic subgroups. These methods contribute important insights but risk oversimplifying social reality and neglecting structural inequalities. In this paper, we outline how a substantive approach to intersectional algorithmic fairness can reorient this research and practice. In particular, we propose Substantive Intersectional Algorithmic Fairness, extending Green's (2022) notion of substantive algorithmic fairness with insights from intersectional feminist theory. Aiming to provide as actionable guidance as possible, our approach is articulated as ten desiderata to guide the design, assessment, and deployment of algorithmic systems that address systemic inequities while mitigating harms to intersectionally marginalized communities. Rather than prescribing fixed operationalizations, these desiderata invite AI practitioners and experts to reflect on assumptions of neutrality, the use of protected attributes, the inclusion of multiply marginalized groups, and the transformative potential of algorithmic systems. By bridging computational and social science perspectives, the approach emphasizes that fairness cannot be separated from social context, and that in some cases, principled non-deployment may be necessary.

The growing adoption of home banking systems has increased cyberfraud risks, requiring detection models that are accurate, fair, and explainable. While AI methods show promise, they face challenges including computational inefficiency, limited interpretability of spiking neural networks (SNNs), and instability in reinforcement learning (RL)-based hyperparameter optimization. We propose a framework combining a Cortical Spiking Network with Population Coding (CSNPC) and a Reinforcement-Guided Hyper-Heuristic Optimizer (RHOSS). CSNPC leverages population coding for robust classification, while RHOSS applies Q-learning to adaptively select low-level heuristics under fairness and recall constraints. Integrated within the MoSSTI framework, the system incorporates explainable AI via saliency maps and spike activity profiling. Evaluated on the Bank Account Fraud (BAF) dataset, the model achieves 90.8% recall at 5% false positive rate, outperforming prior spiking and classical models while maintaining over 98% predictive equality across demographic groups. Although RHOSS introduces offline optimization cost, it is amortized at deployment. The sparse architecture of CSNPC further reduces energy consumption compared to dense ANNs. Results demonstrate that combining population-coded SNNs with RL-guided hyper-heuristics enables fair, interpretable, and high-performance fraud detection.

Understanding the factors that shape students' mathematics performance is vital for designing effective educational policies. This study applies explainable artificial intelligence (XAI) techniques to PISA 2018 data to predict math achievement and identify key predictors across ten countries (67,329 students). We tested four models: Multiple Linear Regression (MLR), Random Forest (RF), CATBoost, and Artificial Neural Networks (ANN), using student, family, and school variables. Models were trained on 70% of the data (with 5-fold cross-validation) and tested on 30%, stratified by country. Performance was assessed with R^2 and Mean Absolute Error (MAE). To ensure interpretability, we used feature importance, SHAP values, and decision tree visualizations. Non-linear models, especially RF and ANN, outperformed MLR, with RF balancing accuracy and generalizability. Key predictors included socio-economic status, study time, teacher motivation, and students' attitudes toward mathematics, though their impact varied across countries. Visual diagnostics such as scatterplots of predicted vs actual scores showed RF and CATBoost aligned closely with actual performance. Findings highlight the non-linear and context-dependent nature of achievement and the value of XAI in educational research. This study uncovers cross-national patterns, informs equity-focused reforms, and supports the development of personalized learning strategies.

Deep learning models in medical imaging often achieve strong in-distribution performance but struggle to generalise under distribution shifts, frequently relying on spurious correlations instead of clinically meaningful features. We introduce LCRReg, a novel regularisation approach that leverages Latent Concept Representations (LCRs) (e.g., Concept Activation Vectors (CAVs)) to guide models toward semantically grounded representations. LCRReg requires no concept labels in the main training set and instead uses a small auxiliary dataset to synthesise high-quality, disentangled concept examples. We extract LCRs for predefined relevant features, and incorporate a regularisation term that guides a Convolutional Neural Network (CNN) to activate within latent subspaces associated with those concepts. We evaluate LCRReg across synthetic and real-world medical tasks. On a controlled toy dataset, it significantly improves robustness to injected spurious correlations and remains effective even in multi-concept and multiclass settings. On the diabetic retinopathy binary classification task, LCRReg enhances performance under both synthetic spurious perturbations and out-of-distribution (OOD) generalisation. Compared to baselines, including multitask learning, linear probing, and post-hoc concept-based models, LCRReg offers a lightweight, architecture-agnostic strategy for improving model robustness without requiring dense concept supervision. Code is available at the following link: https://github.com/Trustworthy-AI-UU-NKI/lcr\_regularization

As AI systems are increasingly deployed to support decision-making in critical domains, explainability has become a means to enhance the understandability of these outputs and enable users to make more informed and conscious choices. However, despite growing interest in the usability of eXplainable AI (XAI), the accessibility of these methods, particularly for users with vision impairments, remains underexplored. This paper investigates accessibility gaps in XAI through a two-pronged approach. First, a literature review of 79 studies reveals that evaluations of XAI techniques rarely include disabled users, with most explanations relying on inherently visual formats. Second, we present a four-part methodological proof of concept that operationalizes inclusive XAI design: (1) categorization of AI systems, (2) persona definition and contextualization, (3) prototype design and implementation, and (4) expert and user assessment of XAI techniques for accessibility. Preliminary findings suggest that simplified explanations are more comprehensible for non-visual users than detailed ones, and that multimodal presentation is required for more equitable interpretability.

Large language models (LLMs) are increasingly deployed in sensitive contexts where fairness and inclusivity are critical. Pronoun usage, especially concerning gender-neutral and neopronouns, remains a key challenge for responsible AI. Prior work, such as the MISGENDERED benchmark, revealed significant limitations in earlier LLMs' handling of inclusive pronouns, but was constrained to outdated models and limited evaluations. In this study, we introduce MISGENDERED+, an extended and updated benchmark for evaluating LLMs' pronoun fidelity. We benchmark five representative LLMs, GPT-4o, Claude 4, DeepSeek-V3, Qwen Turbo, and Qwen2.5, across zero-shot, few-shot, and gender identity inference. Our results show notable improvements compared with previous studies, especially in binary and gender-neutral pronoun accuracy. However, accuracy on neopronouns and reverse inference tasks remains inconsistent, underscoring persistent gaps in identity-sensitive reasoning. We discuss implications, model-specific observations, and avenues for future inclusive AI research.

Theories of "Sexuality" in Natural Language Processing Bias Research

Jacob Hobbs

In recent years, significant advancements in the field of Natural Language Processing (NLP) have positioned commercialized language models as wide-reaching, highly useful tools. In tandem, there has been an explosion of multidisciplinary research examining how NLP tasks reflect, perpetuate, and amplify social biases such as gender and racial bias. A significant gap in this scholarship is a detailed analysis of how queer sexualities are encoded and (mis)represented by both NLP systems and practitioners. Following previous work in the field of AI fairness, we document how sexuality is defined and operationalized via a survey and analysis of 55 articles that quantify sexuality-based NLP bias. We find that sexuality is not clearly defined in a majority of the literature surveyed, indicating a reliance on assumed or normative conceptions of sexual/romantic practices and identities. Further, we find that methods for extracting biased outputs from NLP technologies often conflate gender and sexual identities, leading to monolithic conceptions of queerness and thus improper quantifications of bias. With the goal of improving sexuality-based NLP bias analyses, we conclude with recommendations that encourage more thorough engagement with both queer communities and interdisciplinary literature.

Fairness is a critical component of Trustworthy AI. In this paper, we focus on Machine Learning (ML) and the performance of model predictions when dealing with skin color. Unlike other sensitive attributes, the nature of skin color differs significantly. In computer vision, skin color is represented as tensor data rather than categorical values or single numerical points. However, much of the research on fairness across sensitive groups has focused on categorical features such as gender and race. This paper introduces a new technique for evaluating fairness in ML for image classification tasks, specifically without the use of annotation. To address the limitations of prior work, we handle tensor data, like skin color, without classifying it rigidly. Instead, we convert it into probability distributions and apply statistical distance measures. This novel approach allows us to capture fine-grained nuances in fairness both within and across what would traditionally be considered distinct groups. Additionally, we propose an innovative training method to mitigate the latent biases present in conventional skin tone categorization. This method leverages color distance estimates calculated through Bayesian regression with polynomial functions, ensuring a more nuanced and equitable treatment of skin color in ML models.