基于神经网络的食用油批发价格预测

IF 8 Q1 ENERGY & FUELS
Xiaojie Xu, Yun Zhang
{"title":"基于神经网络的食用油批发价格预测","authors":"Xiaojie Xu,&nbsp;Yun Zhang","doi":"10.1016/j.nexus.2023.100250","DOIUrl":null,"url":null,"abstract":"<div><p>For a wide spectrum of agricultural market participants, building price forecasts of various agricultural commodities has always been a vital project. In this work, we approach this problem for the weekly wholesale price index of edible oil in the Chinese market during a ten-year period of January 1, 2010–January 3, 2020 through the exploration of the non-linear auto-regressive neural network as the forecast model. Specifically, we investigate forecast performance stemming from different settings of models, which include considerations of training algorithms, hidden neurons, delays, and how the data are segmented. With the analysis, a relatively simple model is constructed and it produces performance that is rather accurate and stable. Particularly, performance in terms of relative root mean square errors is 2.80%, 3.01%, and 1.80% for training, validation, and testing, respectively. Forecast results here could be utilized as part of technical analysis and/or combined with other fundamental forecasts as part of policy analysis.</p></div>","PeriodicalId":93548,"journal":{"name":"Energy nexus","volume":"12 ","pages":"Article 100250"},"PeriodicalIF":8.0000,"publicationDate":"2023-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Edible oil wholesale price forecasts via the neural network\",\"authors\":\"Xiaojie Xu,&nbsp;Yun Zhang\",\"doi\":\"10.1016/j.nexus.2023.100250\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>For a wide spectrum of agricultural market participants, building price forecasts of various agricultural commodities has always been a vital project. In this work, we approach this problem for the weekly wholesale price index of edible oil in the Chinese market during a ten-year period of January 1, 2010–January 3, 2020 through the exploration of the non-linear auto-regressive neural network as the forecast model. Specifically, we investigate forecast performance stemming from different settings of models, which include considerations of training algorithms, hidden neurons, delays, and how the data are segmented. With the analysis, a relatively simple model is constructed and it produces performance that is rather accurate and stable. Particularly, performance in terms of relative root mean square errors is 2.80%, 3.01%, and 1.80% for training, validation, and testing, respectively. Forecast results here could be utilized as part of technical analysis and/or combined with other fundamental forecasts as part of policy analysis.</p></div>\",\"PeriodicalId\":93548,\"journal\":{\"name\":\"Energy nexus\",\"volume\":\"12 \",\"pages\":\"Article 100250\"},\"PeriodicalIF\":8.0000,\"publicationDate\":\"2023-10-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Energy nexus\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2772427123000803\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ENERGY & FUELS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Energy nexus","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2772427123000803","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENERGY & FUELS","Score":null,"Total":0}
引用次数: 1

摘要

对于广泛的农业市场参与者来说,建立各种农产品的价格预测一直是一项至关重要的项目。在这项工作中,我们通过探索非线性自回归神经网络作为预测模型,对2010年1月1日至2020年1月3日十年间中国市场食用油每周批发价格指数进行了研究。具体来说,我们研究了来自不同模型设置的预测性能,其中包括训练算法、隐藏神经元、延迟和数据分割方式的考虑。通过分析,构建了一个相对简单的模型,并产生了相当准确和稳定的性能。特别是,在训练、验证和测试方面,相对均方根误差的性能分别为2.80%、3.01%和1.80%。这里的预测结果可以作为技术分析的一部分和/或与其他基本预测结合起来作为政策分析的一部分。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Edible oil wholesale price forecasts via the neural network

For a wide spectrum of agricultural market participants, building price forecasts of various agricultural commodities has always been a vital project. In this work, we approach this problem for the weekly wholesale price index of edible oil in the Chinese market during a ten-year period of January 1, 2010–January 3, 2020 through the exploration of the non-linear auto-regressive neural network as the forecast model. Specifically, we investigate forecast performance stemming from different settings of models, which include considerations of training algorithms, hidden neurons, delays, and how the data are segmented. With the analysis, a relatively simple model is constructed and it produces performance that is rather accurate and stable. Particularly, performance in terms of relative root mean square errors is 2.80%, 3.01%, and 1.80% for training, validation, and testing, respectively. Forecast results here could be utilized as part of technical analysis and/or combined with other fundamental forecasts as part of policy analysis.

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
Energy nexus
Energy nexus Energy (General), Ecological Modelling, Renewable Energy, Sustainability and the Environment, Water Science and Technology, Agricultural and Biological Sciences (General)
CiteScore
7.70
自引率
0.00%
发文量
0
审稿时长
109 days
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信