Michael Carter, Jerry Fiala, Oved Hernandez, M. Mighell, J. Sacks, C. Tucker, Quanquan Gu, W. Scherer
{"title":"Advertising.com预装应用活动","authors":"Michael Carter, Jerry Fiala, Oved Hernandez, M. Mighell, J. Sacks, C. Tucker, Quanquan Gu, W. Scherer","doi":"10.1109/SIEDS.2016.7489332","DOIUrl":null,"url":null,"abstract":"The research detailed in this paper seeks to develop an algorithm to optimally select apps to be pre-installed on newly purchased Verizon smartphones. The research focuses on using consumer data sets provided by Advertising.com, a subsidiary of Verizon Communications, to identify and target consumers that are more likely to use pre-installed apps on their smartphones. Advertsing.com hopes to use these targeted campaigns as a means to raise overall app engagement rates. The paper begins with a background on the mobile advertising industry and Advertising.com's motivation for the project. Following the background, the paper discusses data collection and data management practices, detailing the method for granular attribute selection. The selected attributes for this research include but are not limited to a smartphone user's age, metro code, gender, and income level. Information on the time at which an app is opened and the time distance between the events of preloading and opening an app is also used when available. The paper then details the iterative methodology the team used to identify the highest performing user groups for each application campaign and overviews the predictive models used in forecasting app engagement rates. Finally, the paper concludes with a discussion of the preliminary results, which show an increase in app engagement rates for the app Retale following the team's initial recommendation.","PeriodicalId":426864,"journal":{"name":"2016 IEEE Systems and Information Engineering Design Symposium (SIEDS)","volume":"263 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2016-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Advertising.com pre-install app campaign\",\"authors\":\"Michael Carter, Jerry Fiala, Oved Hernandez, M. Mighell, J. Sacks, C. Tucker, Quanquan Gu, W. Scherer\",\"doi\":\"10.1109/SIEDS.2016.7489332\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The research detailed in this paper seeks to develop an algorithm to optimally select apps to be pre-installed on newly purchased Verizon smartphones. The research focuses on using consumer data sets provided by Advertising.com, a subsidiary of Verizon Communications, to identify and target consumers that are more likely to use pre-installed apps on their smartphones. Advertsing.com hopes to use these targeted campaigns as a means to raise overall app engagement rates. The paper begins with a background on the mobile advertising industry and Advertising.com's motivation for the project. Following the background, the paper discusses data collection and data management practices, detailing the method for granular attribute selection. The selected attributes for this research include but are not limited to a smartphone user's age, metro code, gender, and income level. Information on the time at which an app is opened and the time distance between the events of preloading and opening an app is also used when available. The paper then details the iterative methodology the team used to identify the highest performing user groups for each application campaign and overviews the predictive models used in forecasting app engagement rates. Finally, the paper concludes with a discussion of the preliminary results, which show an increase in app engagement rates for the app Retale following the team's initial recommendation.\",\"PeriodicalId\":426864,\"journal\":{\"name\":\"2016 IEEE Systems and Information Engineering Design Symposium (SIEDS)\",\"volume\":\"263 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2016-04-29\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2016 IEEE Systems and Information Engineering Design Symposium (SIEDS)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/SIEDS.2016.7489332\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2016 IEEE Systems and Information Engineering Design Symposium (SIEDS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SIEDS.2016.7489332","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
The research detailed in this paper seeks to develop an algorithm to optimally select apps to be pre-installed on newly purchased Verizon smartphones. The research focuses on using consumer data sets provided by Advertising.com, a subsidiary of Verizon Communications, to identify and target consumers that are more likely to use pre-installed apps on their smartphones. Advertsing.com hopes to use these targeted campaigns as a means to raise overall app engagement rates. The paper begins with a background on the mobile advertising industry and Advertising.com's motivation for the project. Following the background, the paper discusses data collection and data management practices, detailing the method for granular attribute selection. The selected attributes for this research include but are not limited to a smartphone user's age, metro code, gender, and income level. Information on the time at which an app is opened and the time distance between the events of preloading and opening an app is also used when available. The paper then details the iterative methodology the team used to identify the highest performing user groups for each application campaign and overviews the predictive models used in forecasting app engagement rates. Finally, the paper concludes with a discussion of the preliminary results, which show an increase in app engagement rates for the app Retale following the team's initial recommendation.