{"title":"神经霍克斯:加密货币市场中的高维非参数估计和因果关系分析","authors":"Timothée Fabre, Ioane Muni Toke","doi":"arxiv-2401.09361","DOIUrl":null,"url":null,"abstract":"We propose a novel approach to marked Hawkes kernel inference which we name\nthe moment-based neural Hawkes estimation method. Hawkes processes are fully\ncharacterized by their first and second order statistics through a Fredholm\nintegral equation of the second kind. Using recent advances in solving partial\ndifferential equations with physics-informed neural networks, we provide a\nnumerical procedure to solve this integral equation in high dimension. Together\nwith an adapted training pipeline, we give a generic set of hyperparameters\nthat produces robust results across a wide range of kernel shapes. We conduct\nan extensive numerical validation on simulated data. We finally propose two\napplications of the method to the analysis of the microstructure of\ncryptocurrency markets. In a first application we extract the influence of\nvolume on the arrival rate of BTC-USD trades and in a second application we\nanalyze the causality relationships and their directions amongst a universe of\n15 cryptocurrency pairs in a centralized exchange.","PeriodicalId":501478,"journal":{"name":"arXiv - QuantFin - Trading and Market Microstructure","volume":"143 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Neural Hawkes: Non-Parametric Estimation in High Dimension and Causality Analysis in Cryptocurrency Markets\",\"authors\":\"Timothée Fabre, Ioane Muni Toke\",\"doi\":\"arxiv-2401.09361\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We propose a novel approach to marked Hawkes kernel inference which we name\\nthe moment-based neural Hawkes estimation method. Hawkes processes are fully\\ncharacterized by their first and second order statistics through a Fredholm\\nintegral equation of the second kind. Using recent advances in solving partial\\ndifferential equations with physics-informed neural networks, we provide a\\nnumerical procedure to solve this integral equation in high dimension. Together\\nwith an adapted training pipeline, we give a generic set of hyperparameters\\nthat produces robust results across a wide range of kernel shapes. We conduct\\nan extensive numerical validation on simulated data. We finally propose two\\napplications of the method to the analysis of the microstructure of\\ncryptocurrency markets. In a first application we extract the influence of\\nvolume on the arrival rate of BTC-USD trades and in a second application we\\nanalyze the causality relationships and their directions amongst a universe of\\n15 cryptocurrency pairs in a centralized exchange.\",\"PeriodicalId\":501478,\"journal\":{\"name\":\"arXiv - QuantFin - Trading and Market Microstructure\",\"volume\":\"143 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-01-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - QuantFin - Trading and Market Microstructure\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2401.09361\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - QuantFin - Trading and Market Microstructure","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2401.09361","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Neural Hawkes: Non-Parametric Estimation in High Dimension and Causality Analysis in Cryptocurrency Markets
We propose a novel approach to marked Hawkes kernel inference which we name
the moment-based neural Hawkes estimation method. Hawkes processes are fully
characterized by their first and second order statistics through a Fredholm
integral equation of the second kind. Using recent advances in solving partial
differential equations with physics-informed neural networks, we provide a
numerical procedure to solve this integral equation in high dimension. Together
with an adapted training pipeline, we give a generic set of hyperparameters
that produces robust results across a wide range of kernel shapes. We conduct
an extensive numerical validation on simulated data. We finally propose two
applications of the method to the analysis of the microstructure of
cryptocurrency markets. In a first application we extract the influence of
volume on the arrival rate of BTC-USD trades and in a second application we
analyze the causality relationships and their directions amongst a universe of
15 cryptocurrency pairs in a centralized exchange.