用合成数据提升异常交易检测，让骗局更早被发现
Improving Cryptocurrency Pump-and-Dump Detection through Ensemble-Based Models and Synthetic Oversampling Techniques
- 用SMOTE合成稀有事件数据，缓解样本不平衡问题
- XGBoost和LightGBM召回率超93%，F1分数高且计算快
- 适合实时监控系统，助力打击加密货币操纵行为
本研究旨在检测加密货币市场中的“拉高出货”（P&D）操纵行为。由于此类事件稀少，导致严重类别不平衡，影响检测准确性。为此，本文采用合成少数类过采样技术（SMOTE）对数据进行平衡，并评估多种集成学习模型以区分操纵性交易与正常市场活动。实验结果表明，引入SMOTE显著提升了所有模型的检测能力，提高了召回率并优化了精确率与召回率之间的平衡。其中，XGBoost和LightGBM分别达到94.87%和93.59%的召回率，具备优异的F1分数和快速计算性能，适用于近实时监控。研究结果表明，结合数据平衡技术与集成方法可显著提升对操纵行为的早期识别能力，有助于构建更公平、透明、稳定的加密货币市场。
原文摘要 · Abstract (English)
This study aims to detect pump and dump (P&D) manipulation in cryptocurrency markets, where the scarcity of such events causes severe class imbalance and hinders accurate detection. To address this issue, the Synthetic Minority Oversampling Technique (SMOTE) was applied, and advanced ensemble learning models were evaluated to distinguish manipulative trading behavior from normal market activity. The experimental results show that applying SMOTE greatly enhanced the ability of all models to detect P&D events by increasing recall and improving the overall balance between precision and recall. In particular, XGBoost and LightGBM achieved high recall rates (94.87% and 93.59%, respectively) with strong F1-scores and demonstrated fast computational performance, making them suitable for near real time surveillance. These findings indicate that integrating data balancing techniques with ensemble methods significantly improves the early detection of manipulative activities, contributing to a fairer, more transparent, and more stable cryptocurrency market.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。