[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127533-en":3,"doc-seo-127533-105":30,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},127533,687207017582,"Himbo","https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d",8,"Research & Report","Blockchain Transaction Fee Forecasting - A Comparison of Machine Learning Methods","Gas is Ethereum’s transaction-fee metering mechanism, and users must choose a gas price when submitting transactions, risking overpayment or delays/failures. This study analyzes post–London Hard Fork transaction data to clarify fee dynamics and updates earlier EthUSD/BitUSD–gas price work. Forecasting compares Direct-Recursive Hybrid LSTM, CNN-LSTM, and AttentionLSTM, enhanced with wavelet denoising and matrix profile processing across multiple lookaheads. Results show hybrid models outperform attention and CNN-LSTM under hardware constraints, with Direct-Recursive Hybrid LSTM achieving lower RMSE and improved R2 on block minimum gas-price prediction.","Blockchain Transaction Fee Forecasting: A Comparison of Machine Learning Methods  \nConall Butler 1 and Martin Crane 1,2,*  \n1 School of Computing, Dublin City University, Glasnevin, Dublin 9, Ireland; [conall.butler36@mail.dcu.ie](conall.butler36@mail.dcu.ie)  \n2 ADAPT Research Centre, Dublin City University, Glasnevin, Dublin 9, Ireland  \n* [Correspondence: martin.crane@dcu.ie](Correspondence: martin.crane@dcu.ie)  \nAbstract: Gas is the transaction-fee metering system of the Ethereum network. Users of the network are required to select a gas price for submission with their transaction, creating a risk of overpaying or delayed/unprocessed transactions involved in this selection. In this work, we investigate data in the aftermath of the London Hard Fork and shed insight into the transaction dynamics of the network after this major fork. As such, this paper provides an update on work previous to 2019 on the link between EthUSD/BitUSD and gas price. For forecasting, we compare a novel combination of machine learning methods such as Direct-Recursive Hybrid LSTM, CNN-LSTM, and AttentionLSTM. These are combined with wavelet threshold denoising and matrix profile data processing toward the forecasting of block minimum gas price, on a 5-min timescale, over multiple lookaheads. As the first application of the matrix profile being applied to gas price data and forecasting that weare aware of, this study demonstrates that matrix profile data can enhance attention-based models; however, given the hardware constraints, hybrid models outperformed attention and CNN-LSTM models. The wavelet coherence of inputs demonstrates correlation in multiple variables on a 1-daytimescale, which is a deviation of base free from gas price. A Direct-Recursive Hybrid LSTM strategy is found to outperform other models, with an average RMSE of 26.08 and R2 of 0.54 over a 50-min lookahead window compared to an RMSE of 26.78 and R2 of 0.452 in the best-performing attention model. Hybrid models are shown to have favorable performance up to a 20-min lookahead with performance being comparable to attention models when forecasting 25–50-min ahead. Forecasts over a range of lookaheads allow users to make an informed decision on gas price selection and the optimal window to submit their transaction in without fear of their transaction being rejected. This, in turn, gives more detailed insight into gas price dynamics than existing recommenders, oraclesand forecasting approaches, which provide simple heuristics or limited lookahead horizons.  \nKeywords: Ethereum; gas; LSTM; CNN-LSTM; Direct-Recursive Hybrid; attention; wavelet denoising; wavelet coherence; matrix profile  \nMSC: 62H20; 65C20; 68T01; 91B84  \n1. Introduction  \nBlockchain technologies and their applications such as cryptocurrencies, smart contracts, Non-Fungible Tokens (NFTs) and DeFi (Decentralized Finance) show great potential for disruption and innovation, and they are much discussed. The development of these decentralized applications is enabled through the Ether cryptocurrency, the associated blockchain Ethereum, and the Ethereum Virtual Machine. Ether (ETH) is the second largest cryptocurrency by market cap after Bitcoin. Use of the Ethereum network is growing; daily transactions rose from 500,000 to 2,000,000 between 2018 and 2023 [1] .  \nEthereum network transactions are cryptographically signed instructions between accounts. These instructions can be as simple as a transfer of ETH or more complex contract deployments that enable a variety of decentralized applications. Gas is the unit of computational work used when processing a transaction on the network. The number of  \ngas units consumed by a transaction is dependent on the computational complexity of the transaction. Gas has a price per unit in ETH, and the price is submitted by the sender with the transaction [2] . The process of packing transactions into blocks proceeds as follows: many transactions can go into a single block in Ethereum with ","cbCaid3AkBssB5GJ","https://ap.wps.com/l/cbCaid3AkBssB5GJ","pdf",2066896,1,27,"English","en",105,"# Introduction\n# Background and Motivation\n## Ethereum gas and transaction processing\n## London Hard Fork and fee-related changes\n# Forecasting Approach\n## Machine learning models compared\n## Feature engineering and denoising\n# Experimental Results\n## Lookahead-based performance\n## Comparative evaluation of model families\n# Practical Implications\n## Informing gas-price selection","[{\"question\":\"Why does gas price selection create risk for Ethereum users?\",\"answer\":\"Choosing too high increases fees unnecessarily, while too low can cause transaction wait times or failure to be processed if miners do not include it.\"},{\"question\":\"What changes are associated with the Ethereum London Hard Fork?\",\"answer\":\"The London Hard Fork was introduced on 5 August 2021 and included a move from Proof of Work to Proof of Stake, along with fee-related improvements.\"},{\"question\":\"Which forecasting model performs best for block minimum gas price prediction?\",\"answer\":\"A Direct-Recursive Hybrid LSTM strategy outperforms other tested models, with an average RMSE of 26.08 and R2 of 0.54 over a 50-minute lookahead window.\"}]","Blockchain Transaction Fee Forecasting - A Comparison of Machine Learning Methods | PDF",1785939809,68,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"blockchain-transaction-fee-forecasting-a-comparison-of-machine-learning-methods","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/blockchain-transaction-fee-forecasting-a-comparison-of-machine-learning-methods/127533/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-23","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Why does gas price selection create risk for Ethereum users?","Question",{"text":76,"@type":77},"Choosing too high increases fees unnecessarily, while too low can cause transaction wait times or failure to be processed if miners do not include it.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What changes are associated with the Ethereum London Hard Fork?",{"text":81,"@type":77},"The London Hard Fork was introduced on 5 August 2021 and included a move from Proof of Work to Proof of Stake, along with fee-related improvements.",{"name":83,"@type":74,"acceptedAnswer":84},"Which forecasting model performs best for block minimum gas price prediction?",{"text":85,"@type":77},"A Direct-Recursive Hybrid LSTM strategy outperforms other tested models, with an average RMSE of 26.08 and R2 of 0.54 over a 50-minute lookahead window.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]