Efficient Bitcoin Address Classification Using Quantum-Inspired Feature Selection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sie, Ming-Fong, Chang, Yen-Jui, Lin, Chien-Lung, Chang, Ching-Ray, Liao, Shih-Wei
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915031462969344
author Sie, Ming-Fong
Chang, Yen-Jui
Lin, Chien-Lung
Chang, Ching-Ray
Liao, Shih-Wei
author_facet Sie, Ming-Fong
Chang, Yen-Jui
Lin, Chien-Lung
Chang, Ching-Ray
Liao, Shih-Wei
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2411_15425
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Efficient Bitcoin Address Classification Using Quantum-Inspired Feature Selection
Sie, Ming-Fong
Chang, Yen-Jui
Lin, Chien-Lung
Chang, Ching-Ray
Liao, Shih-Wei
Quantum Physics
Cryptography and Security
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.
title Efficient Bitcoin Address Classification Using Quantum-Inspired Feature Selection
topic Quantum Physics
Cryptography and Security
url https://arxiv.org/abs/2411.15425