[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-139168-105":3,"doc-detail-139168-en":81,"detail-sidebar-cat-0-en-105":98},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","carrot-simultaneous-prediction-of-anomalies-from-groups-of-correlated-cryptocurrency-trends","CARROT - Simultaneous prediction of anomalies from groups of correlated cryptocurrency trends","","Cryptocurrencies are decentralized digital currencies with high market volatility, making their time-series prone to market anomalies. Accurate anomaly prediction is important for traders, investors, and financial institutions to improve profitability and reduce losses. This paper presents CARROT, a method that exploits temporal correlations among cryptocurrencies to form clusters with similar trends and then uses multiple multi-target LSTM models—one per cluster—to predict anomalies. Experiments on 17 cryptocurrencies show CARROT outperforming single-target LSTM and other neural approaches by up to 20% in macro F1-score.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/carrot-simultaneous-prediction-of-anomalies-from-groups-of-correlated-cryptocurrency-trends/139168/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/carrot-simultaneous-prediction-of-anomalies-from-groups-of-correlated-cryptocurrency-trends/139168.png","ImageObject",300,407,{"name":42,"@type":43},"Felix Montgomery","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-17","2026-08-23",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",10,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What problem does CARROT address in cryptocurrency markets?","Question",{"text":63,"@type":64},"CARROT targets the prediction of market anomalies in cryptocurrency time series, which are hard to detect due to large price volatility and frequent abnormal behaviors.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How does CARROT use relationships among cryptocurrencies?",{"text":68,"@type":64},"CARROT analyzes temporal correlations between different cryptocurrencies, identifies clusters with similar trend patterns, and leverages these groups to improve anomaly prediction.",{"name":70,"@type":61,"acceptedAnswer":71},"What model architecture does CARROT use for prediction?",{"text":72,"@type":64},"CARROT trains multiple multi-target LSTM models, with one model dedicated to each identified cluster, and uses them to predict anomalies across targets.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},139168,1787505536,{"code":4,"msg":82,"data":83},"success",{"doc_id":79,"user_id":84,"nickname":42,"user_avatar":85,"doc_module":4,"category_id":86,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":87,"file_id":88,"file_url":89,"file_type":90,"file_size":91,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":92,"language":93,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":94,"faqs":95,"seo_title":96,"seo_description":12,"update_tm":80,"read_time":97},549768064778,"https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8",8,"Expert Systems With Applications 260 (2025) 125457  \n| CARROT: Simultaneous prediction of anomalies from groups of correlated cryptocurrency trends\u003Cbr>Antonio Pellicani a, Gianvito Pio a,b,∗, Michelangelo Ceci a,b,ca Department of Computer Science, University of Bari, Via Orabona, 4, 70125 Bari, Italy\u003Cbr>b Big Data Lab, National Interuniversity Consortium for Informatics (CINI), Via Volturno, 58, 00185 Roma, Italy c Jožef Stefan Institute, Jamova 39, 1000 Ljubljana, Slovenia |  | |\n| --- | --- | --- |\n| A R T I C L E I N F O | A B S T R A C T |  |\n| Dataset link: [https://figshare.com/collections/](https://figshare.com/collections/)[ ](https://figshare.com/collections/)[Processed_17S_Cryptocurrency_datasets/73599](Processed_17S_Cryptocurrency_datasets/73599)[ ](Processed_17S_Cryptocurrency_datasets/73599)85 | Cryptocurrencies are virtual currencies that exploit cryptography to perform secure financial transactions. They gained widespread popularity in recent years due to their decentralized nature,(pseudo-)anonymity, and ability to facilitate cross-border transactions without the need for intermediaries. However, their price on the market exhibits a huge volatility, that makes them prone to market anomalies. Therefore, predicting anomalies in cryptocurrency time series can be considered an important task for financial institutions, traders, and investors, to maximize their profit or minimize losses.\u003Cbr>In this paper, we propose a novel approach for predicting anomalies in cryptocurrency time series by exploiting temporal correlations among different cryptocurrencies. Our approach, called CARROT, is based on the idea that groups of cryptocurrencies exhibit similar trends, possibly due to common influencing factors. CARROT analyzes the temporal correlation between different cryptocurrencies, and identifies clusters showing similar patterns that can be useful for gaining insights into future anomalies. Subsequently, CARROT exploits multiple (i.e., one for each cluster) multi-target LSTM models to predict anomalies.\u003Cbr>Our experiments, performed on a dataset of 17 cryptocurrencies, proved that CARROT outperforms singletarget LSTM models of up to 20%, as well as other approaches based on neural networks, i.e., MLP and CNN, in terms of macro F1-score. Therefore, the proposed approach can be considered as a promising tool for predicting anomalies in cryptocurrency time series data and can potentially be used to improve risk management and trading strategies in the cryptocurrency market. |  |\n| Keywords:\u003Cbr>Anomaly prediction Temporal clustering Long short-term memory Cryptocurrencies |  |  |\n\n1. Introduction  \nSince its debut, the cryptocurrency industry has grown at an incredible rate, reaching a capitalization peak of $3 trillion in November 2021. A cryptocurrency is a digital currency that can be used to make online payments and exchanged for other cryptocurrencies or Fiat currencies. Cryptocurrencies are not subject to control by any central authority and their transactions are stored on the blockchain. Even if the blockchain was first introduced by Haber and Stornetta (1990) asa cryptographically secured chain of blocks, it gained popularity in 2008 after Satoshi Nakamoto introduced the first (and most popular) cryptocurrency named Bitcoin (Nakamoto, 2008). The goal of Bitcoin was to provide an algorithmic decentralized replacement to the traditional economic system, which entirely relies on centralized trusted thirdparty organizations (such as banks) to validate and execute monetary transactions. Besides Bitcoin, many other cryptocurrencies have been launched over time, each living on a blockchain with its own features and functionalities.  \nThe environment related to the blockchain and cryptocurrencies, together with the technological advancements brought to several domains needing decentralization and transparency, has also attracted interest for its speculative aspects. Indeed, the huge market volatility observed for several","cbCaijyWz1e2x87m","https://ap.wps.com/l/cbCaijyWz1e2x87m","pdf",4469234,13,"English","# Introduction\n## Background and motivation\n## Financial time-series analysis and market unpredictability\n## Study aim: anomaly prediction via correlated cryptocurrency trends","[{\"question\":\"What problem does CARROT address in cryptocurrency markets?\",\"answer\":\"CARROT targets the prediction of market anomalies in cryptocurrency time series, which are hard to detect due to large price volatility and frequent abnormal behaviors.\"},{\"question\":\"How does CARROT use relationships among cryptocurrencies?\",\"answer\":\"CARROT analyzes temporal correlations between different cryptocurrencies, identifies clusters with similar trend patterns, and leverages these groups to improve anomaly prediction.\"},{\"question\":\"What model architecture does CARROT use for prediction?\",\"answer\":\"CARROT trains multiple multi-target LSTM models, with one model dedicated to each identified cluster, and uses them to predict anomalies across targets.\"}]","CARROT - Simultaneous prediction of anomalies from groups of correlated cryptocurrency trends | PDF",33,{"code":4,"msg":82,"data":99},[100,104,108,112,117,122,127,130,135,138,141],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":101,"show_sort_weight":102,"slug":103},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":105,"show_sort_weight":106,"slug":107},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":109,"show_sort_weight":110,"slug":111},"Exam",70,"exam",{"id":113,"doc_module":4,"doc_module_name":25,"category_name":114,"show_sort_weight":115,"slug":116},5,"Comic",60,"comic",{"id":118,"doc_module":4,"doc_module_name":25,"category_name":119,"show_sort_weight":120,"slug":121},6,"Technology",50,"technology",{"id":123,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":125,"slug":126},7,"Healthcare",40,"healthcare",{"id":86,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":128,"slug":129},30,"research-report",{"id":131,"doc_module":4,"doc_module_name":25,"category_name":132,"show_sort_weight":133,"slug":134},9,"Religion & Spirituality",20,"religion-spirituality",{"id":133,"doc_module":4,"doc_module_name":25,"category_name":136,"show_sort_weight":133,"slug":137},"World Cup","world-cup",{"id":55,"doc_module":4,"doc_module_name":25,"category_name":139,"show_sort_weight":55,"slug":140},"Lifestyle","lifestyle",{"id":142,"doc_module":4,"doc_module_name":25,"category_name":143,"show_sort_weight":113,"slug":144},19,"General","general"]