Efficient Bitcoin Address Classification Using Quantum-Inspired Feature Selection

TL;DR

This paper introduces a quantum-inspired feature selection method using Simulated Annealing and Quantum Annealing to efficiently classify Bitcoin addresses, reducing training time while maintaining high accuracy.

Contribution

It presents a novel quantum-inspired approach for feature selection in Bitcoin address classification, improving efficiency and accuracy over traditional methods.

Findings

Feature selection reduced training time by 30.3%.

Achieved 91% F1-score for mixer address classification.

Quantum-inspired algorithms effectively identify high-risk Bitcoin addresses.

Abstract

Over 900 million Bitcoin transactions have been recorded, posing considerable challenges for machine learning in terms of computation time and maintaining prediction accuracy. We propose an innovative approach using quantum-inspired algorithms implemented with Simulated Annealing and Quantum Annealing to address the challenge of local minima in solution spaces. This method efficiently identifies key features linked to mixer addresses, significantly reducing model training time. By categorizing Bitcoin addresses into six classes: exchanges, faucets, gambling, marketplaces, mixers, and mining pools, and applying supervised learning methods, our results demonstrate that feature selection with SA reduced training time by 30.3% compared to using all features in a random forest model while maintaining a 91% F1-score for mixer addresses. This highlights the potential of quantum-inspired algorithms to swiftly and accurately identify high-risk Bitcoin addresses based on transaction features.