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

TL;DR

This paper introduces a novel framework combining spiking neural networks with reinforcement-guided hyper-heuristics to improve fairness, interpretability, and accuracy in financial fraud detection, addressing efficiency and stability challenges.

Contribution

It proposes a new hybrid system integrating population-coded SNNs with RL-based hyper-heuristics for fair and explainable fraud detection, improving over prior models.

Findings

Achieves 90.8% recall at 5% false positive rate.

Maintains over 98% predictive equality across demographics.

Reduces energy consumption with sparse architecture.

Abstract

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.