Quantum and Classical Machine Learning in Decentralized Finance: Comparative Evidence from Multi-Asset Backtesting of Automated Market Makers
Chi-Sheng Chen and Aidan Hung-Wen Tsai
这项研究提出了自动做市商(AMM)和分散式金融(DeFi)交易策略中的量子机器学习(QML)和经典机器学习(CML)方法之间的全面经验比较,通过对多个加密货币资产的10个模型进行广泛的背对测试。 我们的分析包括经典的ML模型(Random Forest,Gradient Boosting,Logistic Regression),纯量子模型(VQE分类器,QNN,QSVM),混合量子经典模型(QASA Hybrid,QASA Sequence,QuantumRWKV)和变压器模型。 结果表明,混合量子模型以11.2%的平均回报率和1.42的平均夏普比实现了卓越的整体性能,而经典的ML模型则显示了9.8%的平均回报率和1.47的平均夏普比。 QASA序列混合模型实现了13.99%的最高个人回报率,最佳夏普比为1.76,证明了量子经典混合方法在AMM和DeFi交易策略中的潜力。
This study presents a comprehensive empirical comparison between quantum machine learning (QML) and classical machine learning (CML) approaches in Automated Market Makers (AMM) and Decentralized Finance (DeFi) trading strategies through extensive backtesting on 10 models across multiple cryptocurrency assets. Our analysis encompasses classical ML models (Random Forest, Gradient Boosting, Logistic Regression), pure quantum models (VQE Classifier, QNN, QSVM), hybrid quantum-classical models (QASA ...
