Spectral temporal graph neural network for multivariate agricultural price forecasting

IF 0.8 4区 农林科学 Q3 AGRONOMY Ciencia Rural Pub Date : 2024-01-01 DOI:10.1590/0103-8478cr20220677
Cevher Özden, Mutlu Bulut
{"title":"Spectral temporal graph neural network for multivariate agricultural price forecasting","authors":"Cevher Özden, Mutlu Bulut","doi":"10.1590/0103-8478cr20220677","DOIUrl":null,"url":null,"abstract":"ABSTRACT: Multivariate time series forecasting has an important role in many real-world domains. Especially, price prediction has always been on the focus of researchers. Yet, it is a challenging task that requires the capturing of intra-series and inter-series correlations. Most of the models in literature focus only on the correlation in temporal domain. In this paper, we have curated a new dataset from the official website of Turkish Ministry of Commerce. The dataset consists of daily prices and trade volume of vegetables and covers 1791 days between January 1, 2018 and November 26, 2022. A Spectral Temporal Graph Neural Network (StemGNN) is employed on the curated dataset and the results are given in comparison to Convolutional neural networks (CNN), Long short-term memory (LSTM) and Random Forest models. GNN architecture achieved a state-of-the-art result such as mean absolute error (MAE): 1,37 and root mean squared error (RMSE): 1.94). To our knowledge, this is one of the few studies that investigates GNN for time series analysis and the first study in architecture field.","PeriodicalId":10308,"journal":{"name":"Ciencia Rural","volume":"1 1","pages":""},"PeriodicalIF":0.8000,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Ciencia Rural","FirstCategoryId":"97","ListUrlMain":"https://doi.org/10.1590/0103-8478cr20220677","RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"AGRONOMY","Score":null,"Total":0}
引用次数: 1

Abstract

ABSTRACT: Multivariate time series forecasting has an important role in many real-world domains. Especially, price prediction has always been on the focus of researchers. Yet, it is a challenging task that requires the capturing of intra-series and inter-series correlations. Most of the models in literature focus only on the correlation in temporal domain. In this paper, we have curated a new dataset from the official website of Turkish Ministry of Commerce. The dataset consists of daily prices and trade volume of vegetables and covers 1791 days between January 1, 2018 and November 26, 2022. A Spectral Temporal Graph Neural Network (StemGNN) is employed on the curated dataset and the results are given in comparison to Convolutional neural networks (CNN), Long short-term memory (LSTM) and Random Forest models. GNN architecture achieved a state-of-the-art result such as mean absolute error (MAE): 1,37 and root mean squared error (RMSE): 1.94). To our knowledge, this is one of the few studies that investigates GNN for time series analysis and the first study in architecture field.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
多变量农产品价格预测的光谱时间图神经网络
摘要:多元时间序列预测在现实世界中有着重要的作用。特别是价格预测一直是研究人员关注的焦点。然而,这是一项具有挑战性的任务,需要捕获序列内和序列间的相关性。文献中的大多数模型只关注时域的相关性。在本文中,我们从土耳其商务部官方网站上整理了一个新的数据集。该数据集包括2018年1月1日至2022年11月26日1791天的蔬菜日价格和交易量。在整理的数据集上使用了谱时间图神经网络(StemGNN),并将结果与卷积神经网络(CNN)、长短期记忆(LSTM)和随机森林模型进行了比较。GNN架构实现了最先进的结果,例如平均绝对误差(MAE): 1.37,均方根误差(RMSE): 1.94。据我们所知,这是为数不多的将GNN用于时间序列分析的研究之一,也是建筑领域的第一个研究。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
Ciencia Rural
Ciencia Rural AGRONOMY-
CiteScore
1.70
自引率
0.00%
发文量
233
审稿时长
2-4 weeks
期刊介绍: The purpose of Ciência Rural is to publish the results of original research, note and reviews which contribute significantly to knowledge in Agricultural Sciences. Preference will be given to original articles that develop news concepts or experimental approaches and are not merely repositories of scientific data. The decison of acceptance for publication lies with the Editors and is based on the recommendations of Editorial Comission, Area Committee and/ or ad hoc reviewers. The editors and reviewers are external to the institution.
期刊最新文献
Antibiosis of strawberry genotypes to the spotted spider mite Intra-articular stabilization of a dog stifle with polyester thread: an ex vivo evaluation Seed sensor position on seeder performance at varying speeds Physicochemical characterization of fruits, biometry and dormancy of marula seeds Amitraz poisoning in a cat
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1