Digital Marketing Data Classification by Using Machine Learning Algorithms

Noor Saud Abd, Oqbah Salim Atiyah, Mohammed Taher Ahmed, Ali Bakhit
{"title":"Digital Marketing Data Classification by Using Machine Learning Algorithms","authors":"Noor Saud Abd, Oqbah Salim Atiyah, Mohammed Taher Ahmed, Ali Bakhit","doi":"10.37917/ijeee.20.1.23","DOIUrl":null,"url":null,"abstract":"Early in the 20th century, as a result of technological advancements, the importance of digital marketing significantly increased as the necessity for digital customer experience, promotion, and distribution emerged. Since the year 1988, in the case when the term \"Digital Marketing\" first appeared, the business sector has undergone drastic growth, moving from small startups to massive corporations on a global scale. The marketer must navigate a chaotic environment caused by the vast volume of generated data. Decision-makers must contend with the fact that user data is dynamic and changes every day. Smart applications must be used within enterprises to better evaluate, classify, enhance, and target audiences. Customers who are tech-savvy are pushing businesses to make bigger financial investments and use cutting-edge technologies. It was only natural that marketing and trade could be one of the areas to move to such development, which helps to move to the speed of spread, advertisements, along with other things to facilitate things for reaching and winning customers. In this study, we utilized machine learning (ML) algorithms (Decision tree (DT), K-Nearest Neighbor (KNN), CatBoost, and Random Forest (RF) (for classifying data in customers to move to development. Improve the ability to forecast customer behavior so one can gain more business from them more quickly and easily. With the use of the aforementioned dataset, the suggested system was put to the test. The results show that the system can accurately predict if a customer will buy something or not; the random forest (RF) had an accuracy of 0.97, DT had an accuracy of 0. 95, KNN had an accuracy of 0. 91, while the CatBoost algorithm had the execution time 15.04 of seconds, and gave the best result of highest f1_score and accuracy (0.91, 0. 98) respectively. Finally, the study's future goals involve being created a web page, thereby helping many banking institutions with speed and forecast accuracy. Using more techniques of feature selection in conjunction with the marketing dataset to improve diagnosis.","PeriodicalId":159746,"journal":{"name":"Iraqi Journal for Electrical and Electronic Engineering","volume":"13 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Iraqi Journal for Electrical and Electronic Engineering","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.37917/ijeee.20.1.23","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Early in the 20th century, as a result of technological advancements, the importance of digital marketing significantly increased as the necessity for digital customer experience, promotion, and distribution emerged. Since the year 1988, in the case when the term "Digital Marketing" first appeared, the business sector has undergone drastic growth, moving from small startups to massive corporations on a global scale. The marketer must navigate a chaotic environment caused by the vast volume of generated data. Decision-makers must contend with the fact that user data is dynamic and changes every day. Smart applications must be used within enterprises to better evaluate, classify, enhance, and target audiences. Customers who are tech-savvy are pushing businesses to make bigger financial investments and use cutting-edge technologies. It was only natural that marketing and trade could be one of the areas to move to such development, which helps to move to the speed of spread, advertisements, along with other things to facilitate things for reaching and winning customers. In this study, we utilized machine learning (ML) algorithms (Decision tree (DT), K-Nearest Neighbor (KNN), CatBoost, and Random Forest (RF) (for classifying data in customers to move to development. Improve the ability to forecast customer behavior so one can gain more business from them more quickly and easily. With the use of the aforementioned dataset, the suggested system was put to the test. The results show that the system can accurately predict if a customer will buy something or not; the random forest (RF) had an accuracy of 0.97, DT had an accuracy of 0. 95, KNN had an accuracy of 0. 91, while the CatBoost algorithm had the execution time 15.04 of seconds, and gave the best result of highest f1_score and accuracy (0.91, 0. 98) respectively. Finally, the study's future goals involve being created a web page, thereby helping many banking institutions with speed and forecast accuracy. Using more techniques of feature selection in conjunction with the marketing dataset to improve diagnosis.
使用机器学习算法进行数字营销数据分类
20 世纪初,随着技术的进步,数字营销的重要性显著增加,因为数字客户体验、推广和分销的必要性也随之出现。自 1988 年 "数字营销 "一词首次出现以来,商业领域经历了从小型初创企业到全球大型企业的急剧发展。营销人员必须在大量数据产生的混乱环境中游刃有余。决策者必须面对用户数据每天都在动态变化这一事实。企业内部必须使用智能应用程序来更好地评估、分类、增强和定位受众。精通技术的客户正在推动企业加大资金投入,使用尖端技术。市场营销和贸易自然也会成为此类发展的领域之一,这有助于加快传播速度、广告以及其他便于接触和赢得客户的东西。在这项研究中,我们利用机器学习(ML)算法(决策树(DT)、K-近邻(KNN)、CatBoost 和随机森林(RF))对客户数据进行分类,以促进发展。提高预测客户行为的能力,以便更快、更轻松地从客户那里获得更多业务。利用上述数据集,对建议的系统进行了测试。结果表明,该系统可以准确预测客户是否会购买商品;随机森林(RF)的准确率为 0.97,DT 的准确率为 0.95,KNN 的准确率为 0.91,而 CatBoost 算法的执行时间为 15.04 秒,并分别给出了最高的 f1_score 和准确率(0.91、0.98)。最后,这项研究的未来目标是创建一个网页,从而帮助许多银行机构提高速度和预测准确性。结合营销数据集使用更多的特征选择技术来改进诊断。
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 求助全文
来源期刊
CiteScore
2.00
自引率
0.00%
发文量
0
×
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:604180095
Book学术官方微信
小红书