Reinforcement-Guided Hyper-Heuristic Hyperparameter Optimization for Fair and Explainable Spiking Neural Network-Based Financial Fraud Detection

2025-08-23

AI Summary

To address the joint deficiency in accuracy, fairness, and interpretability of fraud detection models in home banking systems, this paper proposes MoSSTI—a novel framework integrating cortical spiking neural networks (CSNNs) with biologically inspired population coding to enhance robustness; a Reinforcement-learning-driven Hybrid Optimization Strategy for Spiking models (RHOSS), which combines Q-learning with fairness-aware constraints for efficient and stable hyperparameter optimization; and a dual interpretability verification mechanism unifying saliency-based attribution and spike activity spectrum analysis. Evaluated on the BAF dataset, MoSSTI achieves 90.8% recall at a 5% false positive rate and attains 98.2% predictive parity across key demographic attributes—outperforming state-of-the-art spiking and conventional deep learning baselines. Its core contribution lies in the first unified integration of fairness-aware reinforcement learning, population-coded spiking modeling, and multi-source interpretability validation within financial fraud detection.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Mixture of Experts (MoE)
• Computer Vision: Multi-modal Vision

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Social Networks and Social Media: Fairness and bias in social network and social media analysis

Abstract

The growing adoption of home banking systems has heightened the risk of cyberfraud, necessitating fraud detection mechanisms that are not only accurate but also fair and explainable. While AI models have shown promise in this domain, they face key limitations, including computational inefficiency, the interpretability challenges of spiking neural networks (SNNs), and the complexity and convergence instability of hyper-heuristic reinforcement learning (RL)-based hyperparameter optimization. To address these issues, we propose a novel framework that integrates a Cortical Spiking Network with Population Coding (CSNPC) and a Reinforcement-Guided Hyper-Heuristic Optimizer for Spiking Systems (RHOSS). The CSNPC, a biologically inspired SNN, employs population coding for robust classification, while RHOSS uses Q-learning to dynamically select low-level heuristics for hyperparameter optimization under fairness and recall constraints. Embedded within the Modular Supervisory Framework for Spiking Network Training and Interpretation (MoSSTI), the system incorporates explainable AI (XAI) techniques, specifically, saliency-based attribution and spike activity profiling, to increase transparency. Evaluated on the Bank Account Fraud (BAF) dataset suite, our model achieves a $90.8%$ recall at a strict $5%$ false positive rate (FPR), outperforming state-of-the-art spiking and non-spiking models while maintaining over $98%$ predictive equality across key demographic attributes. The explainability module further confirms that saliency attributions align with spiking dynamics, validating interpretability. These results demonstrate the potential of combining population-coded SNNs with reinforcement-guided hyper-heuristics for fair, transparent, and high-performance fraud detection in real-world financial applications.

Problem

• Optimizing hyperparameters for fair and explainable fraud detection
• Addressing computational inefficiency in spiking neural networks
• Improving convergence stability in reinforcement learning optimization

Innovation

• Reinforcement-guided hyper-heuristic optimizer for hyperparameter tuning
• Cortical spiking network with population coding for classification
• Saliency-based XAI techniques integrated for model transparency