在预测股市价格的联合学习中减少客户端训练的数据不平衡

IF 3.3 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS Journal of Sensor and Actuator Networks Pub Date : 2023-12-21 DOI:10.3390/jsan13010001
Momina Shaheen, M. Farooq, Tariq Umer
{"title":"在预测股市价格的联合学习中减少客户端训练的数据不平衡","authors":"Momina Shaheen, M. Farooq, Tariq Umer","doi":"10.3390/jsan13010001","DOIUrl":null,"url":null,"abstract":"The approach of federated learning (FL) addresses significant challenges, including access rights, privacy, security, and the availability of diverse data. However, edge devices produce and collect data in a non-independent and identically distributed (non-IID) manner. Therefore, it is possible that the number of data samples may vary among the edge devices. This study elucidates an approach for implementing FL to achieve a balance between training accuracy and imbalanced data. This approach entails the implementation of data augmentation in data distribution by utilizing class estimation and by balancing on the client side during local training. Secondly, simple linear regression is utilized for model training at the client side to manage the optimal computation cost to achieve a reduction in computation cost. To validate the proposed approach, the technique was applied to a stock market dataset comprising stocks (AAL, ADBE, ASDK, and BSX) to predict the day-to-day values of stocks. The proposed approach has demonstrated favorable results, exhibiting a strong fit of 0.95 and above with a low error rate. The R-squared values, predominantly ranging from 0.97 to 0.98, indicate the model’s effectiveness in capturing variations in stock prices. Strong fits are observed within 75 to 80 iterations for stocks displaying consistently high R-squared values, signifying accuracy. On the 100th iteration, the declining MSE, MAE, and RMSE (AAL at 122.03, 4.89, 11.04, respectively; ADBE at 457.35, 17.79, and 21.38, respectively; ASDK at 182.78, 5.81, 13.51, respectively; and BSX at 34.50, 4.87, 5.87, respectively) values corroborated the positive results of the proposed approach with minimal data loss.","PeriodicalId":37584,"journal":{"name":"Journal of Sensor and Actuator Networks","volume":"77 6","pages":""},"PeriodicalIF":3.3000,"publicationDate":"2023-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Reduction in Data Imbalance for Client-Side Training in Federated Learning for the Prediction of Stock Market Prices\",\"authors\":\"Momina Shaheen, M. Farooq, Tariq Umer\",\"doi\":\"10.3390/jsan13010001\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The approach of federated learning (FL) addresses significant challenges, including access rights, privacy, security, and the availability of diverse data. However, edge devices produce and collect data in a non-independent and identically distributed (non-IID) manner. Therefore, it is possible that the number of data samples may vary among the edge devices. This study elucidates an approach for implementing FL to achieve a balance between training accuracy and imbalanced data. This approach entails the implementation of data augmentation in data distribution by utilizing class estimation and by balancing on the client side during local training. Secondly, simple linear regression is utilized for model training at the client side to manage the optimal computation cost to achieve a reduction in computation cost. To validate the proposed approach, the technique was applied to a stock market dataset comprising stocks (AAL, ADBE, ASDK, and BSX) to predict the day-to-day values of stocks. The proposed approach has demonstrated favorable results, exhibiting a strong fit of 0.95 and above with a low error rate. The R-squared values, predominantly ranging from 0.97 to 0.98, indicate the model’s effectiveness in capturing variations in stock prices. Strong fits are observed within 75 to 80 iterations for stocks displaying consistently high R-squared values, signifying accuracy. On the 100th iteration, the declining MSE, MAE, and RMSE (AAL at 122.03, 4.89, 11.04, respectively; ADBE at 457.35, 17.79, and 21.38, respectively; ASDK at 182.78, 5.81, 13.51, respectively; and BSX at 34.50, 4.87, 5.87, respectively) values corroborated the positive results of the proposed approach with minimal data loss.\",\"PeriodicalId\":37584,\"journal\":{\"name\":\"Journal of Sensor and Actuator Networks\",\"volume\":\"77 6\",\"pages\":\"\"},\"PeriodicalIF\":3.3000,\"publicationDate\":\"2023-12-21\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Sensor and Actuator Networks\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.3390/jsan13010001\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"COMPUTER SCIENCE, INFORMATION SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Sensor and Actuator Networks","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3390/jsan13010001","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 0

摘要

联合学习(FL)方法解决了访问权限、隐私、安全和多样化数据可用性等重大挑战。然而,边缘设备是以非独立和同分布(non-IID)的方式生产和收集数据的。因此,边缘设备之间的数据样本数量可能会有所不同。本研究阐明了一种实施 FL 的方法,以实现训练准确性和不平衡数据之间的平衡。这种方法需要在数据分布过程中利用类估计和本地训练过程中的客户端平衡来实现数据增强。其次,在客户端利用简单的线性回归进行模型训练,以管理最佳计算成本,从而降低计算成本。为了验证所提出的方法,我们将该技术应用于由股票(AAL、ADBE、ASDK 和 BSX)组成的股票市场数据集,以预测股票的每日价值。所提出的方法取得了良好的效果,拟合度达到 0.95 及以上,误差率较低。R 平方值主要在 0.97 至 0.98 之间,表明该模型能有效捕捉股票价格的变化。在 75 至 80 次迭代中,可以观察到 R 平方值持续较高的股票具有较强的拟合能力,这表明了模型的准确性。在第 100 次迭代中,MSE、MAE 和 RMSE 值不断下降(AAL 分别为 122.03、4.89 和 11.04;ADBE 分别为 457.35、17.79 和 21.38;ASDK 分别为 182.78、5.81 和 13.51;BSX 分别为 34.50、4.87 和 5.87),证实了所提方法在数据损失最小的情况下取得了积极成果。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
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
Reduction in Data Imbalance for Client-Side Training in Federated Learning for the Prediction of Stock Market Prices
The approach of federated learning (FL) addresses significant challenges, including access rights, privacy, security, and the availability of diverse data. However, edge devices produce and collect data in a non-independent and identically distributed (non-IID) manner. Therefore, it is possible that the number of data samples may vary among the edge devices. This study elucidates an approach for implementing FL to achieve a balance between training accuracy and imbalanced data. This approach entails the implementation of data augmentation in data distribution by utilizing class estimation and by balancing on the client side during local training. Secondly, simple linear regression is utilized for model training at the client side to manage the optimal computation cost to achieve a reduction in computation cost. To validate the proposed approach, the technique was applied to a stock market dataset comprising stocks (AAL, ADBE, ASDK, and BSX) to predict the day-to-day values of stocks. The proposed approach has demonstrated favorable results, exhibiting a strong fit of 0.95 and above with a low error rate. The R-squared values, predominantly ranging from 0.97 to 0.98, indicate the model’s effectiveness in capturing variations in stock prices. Strong fits are observed within 75 to 80 iterations for stocks displaying consistently high R-squared values, signifying accuracy. On the 100th iteration, the declining MSE, MAE, and RMSE (AAL at 122.03, 4.89, 11.04, respectively; ADBE at 457.35, 17.79, and 21.38, respectively; ASDK at 182.78, 5.81, 13.51, respectively; and BSX at 34.50, 4.87, 5.87, respectively) values corroborated the positive results of the proposed approach with minimal data loss.
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
Journal of Sensor and Actuator Networks
Journal of Sensor and Actuator Networks Physics and Astronomy-Instrumentation
CiteScore
7.90
自引率
2.90%
发文量
70
审稿时长
11 weeks
期刊介绍: Journal of Sensor and Actuator Networks (ISSN 2224-2708) is an international open access journal on the science and technology of sensor and actuator networks. It publishes regular research papers, reviews (including comprehensive reviews on complete sensor and actuator networks), and short communications. Our aim is to encourage scientists to publish their experimental and theoretical results in as much detail as possible. There is no restriction on the length of the papers. The full experimental details must be provided so that the results can be reproduced.
期刊最新文献
Dynamic and Distributed Intelligence over Smart Devices, Internet of Things Edges, and Cloud Computing for Human Activity Recognition Using Wearable Sensors Output Stream from the AQM Queue with BMAP Arrivals Multi-Objective Optimization of Gateway Location Selection in Long-Range Wide Area Networks: A Tradeoff Analysis between System Costs and Bitrate Maximization Robust ISAC Localization in Smart Cities: A Hybrid Network Approach for NLOS Challenges with Uncertain Parameters Reduction in Data Imbalance for Client-Side Training in Federated Learning for the Prediction of Stock Market Prices
×
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