Roman Kvуetnyy, Yu. Bunyak, Olga Sofina, Oleksandr Kaduk, O. Mamyrbayev, Vladyslav Baklaiev, B. Yeraliyeva
{"title":"ADVERTISING BIDDING OPTIMIZATION BY TARGETING BASED ON SELF-LEARNING DATABASE","authors":"Roman Kvуetnyy, Yu. Bunyak, Olga Sofina, Oleksandr Kaduk, O. Mamyrbayev, Vladyslav Baklaiev, B. Yeraliyeva","doi":"10.35784/iapgos.5376","DOIUrl":null,"url":null,"abstract":"The method of targeting advertising on Internet sites based on a structured self-learning database is considered. The database accumulates data on previously accepted requests to display ads from a closed auction, data on participation in the auction and the results of displaying ads – the presence of a click and product installation. The base is structured by streams with features – site, place, price. Each such structural stream has statistical properties that are much simpler compared to the general ad impression stream, which makes it possible to predict the effectiveness of advertising. The selection of bidding requests only promising in terms of the result allows to reduce the cost of displaying advertising.","PeriodicalId":504633,"journal":{"name":"Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2023-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.35784/iapgos.5376","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
The method of targeting advertising on Internet sites based on a structured self-learning database is considered. The database accumulates data on previously accepted requests to display ads from a closed auction, data on participation in the auction and the results of displaying ads – the presence of a click and product installation. The base is structured by streams with features – site, place, price. Each such structural stream has statistical properties that are much simpler compared to the general ad impression stream, which makes it possible to predict the effectiveness of advertising. The selection of bidding requests only promising in terms of the result allows to reduce the cost of displaying advertising.
京公网安备 11010802042870号
京ICP备2023020795号-1
分享
求助内容：
应助结果提醒方式：
扫码关注我们
