通过多源数据预警加密货币反转风险

IF 6.9 2区经济学 Q1 BUSINESS, FINANCE

Finance Research Letters Pub Date : 2025-07-15 DOI:10.1016/j.frl.2025.107890

Zong Ke , Yuqing Cao , Zhenrui Chen , Yuchen Yin , Shouchao He , Yu Cheng

{"title":"通过多源数据预警加密货币反转风险","authors":"Zong Ke , Yuqing Cao , Zhenrui Chen , Yuchen Yin , Shouchao He , Yu Cheng","doi":"10.1016/j.frl.2025.107890","DOIUrl":null,"url":null,"abstract":"<div><div>This study proposes a multi-source deep learning framework integrating blockchain metrics, social sentiment, and regulatory signals to predict cryptocurrency pin-bar reversal risk events. Long short-term memory networks effectively capture temporal anomalies (F1 <span><math><mo>=</mo></math></span> 0.703), with blockchain features, such as hash rate fluctuations and whale transactions, contributing <span><math><mo>></mo></math></span>33% predictive power (SHAP). Synthetic minority over-sampling technique increases rare-event recall by 19%, as confirmed by rolling-window tests (F1 <span><math><mo>=</mo></math></span> 0.64-0.72 across market cycles). Simulated profitability analysis supports its potential for risk monitoring. Future research may investigate cross-chain dynamics and advanced temporal models to mitigate financial uncertainty in the cryptocurrency market.</div></div>","PeriodicalId":12167,"journal":{"name":"Finance Research Letters","volume":"85 ","pages":"Article 107890"},"PeriodicalIF":6.9000,"publicationDate":"2025-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Early warning of cryptocurrency reversal risks via multi-source data\",\"authors\":\"Zong Ke , Yuqing Cao , Zhenrui Chen , Yuchen Yin , Shouchao He , Yu Cheng\",\"doi\":\"10.1016/j.frl.2025.107890\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>This study proposes a multi-source deep learning framework integrating blockchain metrics, social sentiment, and regulatory signals to predict cryptocurrency pin-bar reversal risk events. Long short-term memory networks effectively capture temporal anomalies (F1 <span><math><mo>=</mo></math></span> 0.703), with blockchain features, such as hash rate fluctuations and whale transactions, contributing <span><math><mo>></mo></math></span>33% predictive power (SHAP). Synthetic minority over-sampling technique increases rare-event recall by 19%, as confirmed by rolling-window tests (F1 <span><math><mo>=</mo></math></span> 0.64-0.72 across market cycles). Simulated profitability analysis supports its potential for risk monitoring. Future research may investigate cross-chain dynamics and advanced temporal models to mitigate financial uncertainty in the cryptocurrency market.</div></div>\",\"PeriodicalId\":12167,\"journal\":{\"name\":\"Finance Research Letters\",\"volume\":\"85 \",\"pages\":\"Article 107890\"},\"PeriodicalIF\":6.9000,\"publicationDate\":\"2025-07-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Finance Research Letters\",\"FirstCategoryId\":\"96\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S1544612325011481\",\"RegionNum\":2,\"RegionCategory\":\"经济学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"BUSINESS, FINANCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Finance Research Letters","FirstCategoryId":"96","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1544612325011481","RegionNum":2,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"BUSINESS, FINANCE","Score":null,"Total":0}

引用次数: 0

摘要

本研究提出了一个集成区块链指标、社会情绪和监管信号的多源深度学习框架，以预测加密货币针条反转风险事件。长短期记忆网络有效捕获时间异常（F1 = 0.703），具有区块链特征，如哈希率波动和鲸鱼交易，贡献了33%的预测能力（SHAP）。正如滚动窗口试验所证实的那样，合成少数派过采样技术将罕见事件召回率提高了19%（整个市场周期的F1 = 0.64-0.72）。模拟盈利能力分析支持其潜在的风险监控。未来的研究可能会调查跨链动态和先进的时间模型，以减轻加密货币市场的金融不确定性。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Early warning of cryptocurrency reversal risks via multi-source data

This study proposes a multi-source deep learning framework integrating blockchain metrics, social sentiment, and regulatory signals to predict cryptocurrency pin-bar reversal risk events. Long short-term memory networks effectively capture temporal anomalies (F1

=

0.703), with blockchain features, such as hash rate fluctuations and whale transactions, contributing

>

33% predictive power (SHAP). Synthetic minority over-sampling technique increases rare-event recall by 19%, as confirmed by rolling-window tests (F1

=

0.64-0.72 across market cycles). Simulated profitability analysis supports its potential for risk monitoring. Future research may investigate cross-chain dynamics and advanced temporal models to mitigate financial uncertainty in the cryptocurrency market.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Finance Research Letters BUSINESS, FINANCE-

CiteScore

11.10

自引率

14.40%

发文量

863

期刊介绍： Finance Research Letters welcomes submissions across all areas of finance, aiming for rapid publication of significant new findings. The journal particularly encourages papers that provide insight into the replicability of established results, examine the cross-national applicability of previous findings, challenge existing methodologies, or demonstrate methodological contingencies. Papers are invited in the following areas: Actuarial studies Alternative investments Asset Pricing Bankruptcy and liquidation Banks and other Depository Institutions Behavioral and experimental finance Bibliometric and Scientometric studies of finance Capital budgeting and corporate investment Capital markets and accounting Capital structure and payout policy Commodities Contagion, crises and interdependence Corporate governance Credit and fixed income markets and instruments Derivatives Emerging markets Energy Finance and Energy Markets Financial Econometrics Financial History Financial intermediation and money markets Financial markets and marketplaces Financial Mathematics and Econophysics Financial Regulation and Law Forecasting Frontier market studies International Finance Market efficiency, event studies Mergers, acquisitions and the market for corporate control Micro Finance Institutions Microstructure Non-bank Financial Institutions Personal Finance Portfolio choice and investing Real estate finance and investing Risk SME, Family and Entrepreneurial Finance