Md Nasir Uddin Rana, Sarder Abdulla Al Shiam, Sarmin Akter Shochona, Md Rasibul Islam, Md Asrafuzzaman, Proshanta Kumar Bhowmik, Refat Naznin, Sandip Kumar Ghosh, Md Ariful Islam Sarkar, Md Asaduzzaman
{"title":"银行业决策的革命性变革：预测客户行为的深度学习方法","authors":"Md Nasir Uddin Rana, Sarder Abdulla Al Shiam, Sarmin Akter Shochona, Md Rasibul Islam, Md Asrafuzzaman, Proshanta Kumar Bhowmik, Refat Naznin, Sandip Kumar Ghosh, Md Ariful Islam Sarkar, Md Asaduzzaman","doi":"10.32996/jbms.2024.6.3.3","DOIUrl":null,"url":null,"abstract":"This article explores a machine learning approach focused on predicting bank customer behavior, emphasizing deep learning methods. Various architectures, including CNNs like VGG16, ResNet50, and InceptionV3, are compared with traditional algorithms such as Random Forest and SVM. Results show deep learning models, particularly ResNet50, outperform traditional ones, with an accuracy of 86.66%. A structured methodology ensures ethical data use. Investing in infrastructure and expertise is crucial for successful deep learning integration, offering a competitive edge in banking decision-making.","PeriodicalId":250160,"journal":{"name":"Journal of Business and Management Studies","volume":"3 2","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Revolutionizing Banking Decision-Making: A Deep Learning Approach to Predicting Customer Behavior\",\"authors\":\"Md Nasir Uddin Rana, Sarder Abdulla Al Shiam, Sarmin Akter Shochona, Md Rasibul Islam, Md Asrafuzzaman, Proshanta Kumar Bhowmik, Refat Naznin, Sandip Kumar Ghosh, Md Ariful Islam Sarkar, Md Asaduzzaman\",\"doi\":\"10.32996/jbms.2024.6.3.3\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This article explores a machine learning approach focused on predicting bank customer behavior, emphasizing deep learning methods. Various architectures, including CNNs like VGG16, ResNet50, and InceptionV3, are compared with traditional algorithms such as Random Forest and SVM. Results show deep learning models, particularly ResNet50, outperform traditional ones, with an accuracy of 86.66%. A structured methodology ensures ethical data use. Investing in infrastructure and expertise is crucial for successful deep learning integration, offering a competitive edge in banking decision-making.\",\"PeriodicalId\":250160,\"journal\":{\"name\":\"Journal of Business and Management Studies\",\"volume\":\"3 2\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-05-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Business and Management Studies\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.32996/jbms.2024.6.3.3\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Business and Management Studies","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.32996/jbms.2024.6.3.3","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Revolutionizing Banking Decision-Making: A Deep Learning Approach to Predicting Customer Behavior
This article explores a machine learning approach focused on predicting bank customer behavior, emphasizing deep learning methods. Various architectures, including CNNs like VGG16, ResNet50, and InceptionV3, are compared with traditional algorithms such as Random Forest and SVM. Results show deep learning models, particularly ResNet50, outperform traditional ones, with an accuracy of 86.66%. A structured methodology ensures ethical data use. Investing in infrastructure and expertise is crucial for successful deep learning integration, offering a competitive edge in banking decision-making.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
