{"title":"用户Shopee根据推广分类使用Naive Bayes","authors":"T. Rahmadanti, M. Jajuli, Intan Purnamasari","doi":"10.29407/gj.v5i2.15998","DOIUrl":null,"url":null,"abstract":"Online shopping is a transaction of buying and selling goods or services through intermediary media, namely social networks. There has been a change in consumption patterns and the way people spend their money, which was originally conventional to switch to E-Commerce services due to several factors, namely the increasing public interest in online shopping due to the COVID-19 virus outbreak, and throughout 2019 E-Commerce users who made transactions reached 168.3 million people. . Based on iprice report data in 2020, Shopee is the most visited E-Commerce with a total of 129,320,800 visitors. Shopee is only a third party that provides a place to sell and payment facilities, therefore Shopee is not responsible for marketing the products sold. To attract consumers, sellers need attractive promotions. Therefore, research is needed to classify E-Commerce users. The purpose of this research is to classify E-Commerce users based on the promotion used using the Naïve Bayes algorithm with the Knowledge Discovery in Database (KDD) methodology. Nine test scenarios were carried out with cross validation which showed that the best performance was a test scenario using 3 folds which resulted in performance with an accuracy value of 88.73%, and with a kappa value of 0.451 which was included in the moderate category. Based on these results, the model generated by the Naïve Bayes algorithm is quite consistent.","PeriodicalId":200108,"journal":{"name":"Generation Journal","volume":"58 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Klasifikasi Pengguna Shopee Berdasarkan Promosi Menggunakan Naïve Bayes\",\"authors\":\"T. Rahmadanti, M. Jajuli, Intan Purnamasari\",\"doi\":\"10.29407/gj.v5i2.15998\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Online shopping is a transaction of buying and selling goods or services through intermediary media, namely social networks. There has been a change in consumption patterns and the way people spend their money, which was originally conventional to switch to E-Commerce services due to several factors, namely the increasing public interest in online shopping due to the COVID-19 virus outbreak, and throughout 2019 E-Commerce users who made transactions reached 168.3 million people. . Based on iprice report data in 2020, Shopee is the most visited E-Commerce with a total of 129,320,800 visitors. Shopee is only a third party that provides a place to sell and payment facilities, therefore Shopee is not responsible for marketing the products sold. To attract consumers, sellers need attractive promotions. Therefore, research is needed to classify E-Commerce users. The purpose of this research is to classify E-Commerce users based on the promotion used using the Naïve Bayes algorithm with the Knowledge Discovery in Database (KDD) methodology. Nine test scenarios were carried out with cross validation which showed that the best performance was a test scenario using 3 folds which resulted in performance with an accuracy value of 88.73%, and with a kappa value of 0.451 which was included in the moderate category. Based on these results, the model generated by the Naïve Bayes algorithm is quite consistent.\",\"PeriodicalId\":200108,\"journal\":{\"name\":\"Generation Journal\",\"volume\":\"58 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-06-28\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Generation Journal\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.29407/gj.v5i2.15998\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Generation Journal","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.29407/gj.v5i2.15998","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
摘要
网上购物是一种通过中介媒体,即社交网络买卖商品或服务的交易。消费模式和消费方式发生了变化,人们原本习惯转向电子商务服务,原因有几个因素,即由于新冠肺炎疫情爆发,公众对网上购物的兴趣日益浓厚,2019年全年电子商务交易用户达到1.683亿人。根据iprice在2020年的报告数据,Shopee是访问量最大的电子商务,共有129,320,800名访客。Shopee仅是提供销售场所和支付设施的第三方,因此Shopee不负责所售产品的营销。为了吸引消费者,卖家需要有吸引力的促销活动。因此,需要对电子商务用户进行分类研究。本研究的目的是利用Naïve贝叶斯算法和KDD (Knowledge Discovery in Database)方法对电子商务用户进行分类。共进行了9个测试场景的交叉验证,结果表明,使用3个折叠的测试场景表现最佳,准确度值为88.73%,kappa值为0.451,属于中等类别。基于这些结果,Naïve贝叶斯算法生成的模型是相当一致的。
Klasifikasi Pengguna Shopee Berdasarkan Promosi Menggunakan Naïve Bayes
Online shopping is a transaction of buying and selling goods or services through intermediary media, namely social networks. There has been a change in consumption patterns and the way people spend their money, which was originally conventional to switch to E-Commerce services due to several factors, namely the increasing public interest in online shopping due to the COVID-19 virus outbreak, and throughout 2019 E-Commerce users who made transactions reached 168.3 million people. . Based on iprice report data in 2020, Shopee is the most visited E-Commerce with a total of 129,320,800 visitors. Shopee is only a third party that provides a place to sell and payment facilities, therefore Shopee is not responsible for marketing the products sold. To attract consumers, sellers need attractive promotions. Therefore, research is needed to classify E-Commerce users. The purpose of this research is to classify E-Commerce users based on the promotion used using the Naïve Bayes algorithm with the Knowledge Discovery in Database (KDD) methodology. Nine test scenarios were carried out with cross validation which showed that the best performance was a test scenario using 3 folds which resulted in performance with an accuracy value of 88.73%, and with a kappa value of 0.451 which was included in the moderate category. Based on these results, the model generated by the Naïve Bayes algorithm is quite consistent.