You are what apps you use: Demographic prediction based on user's apps

Eric Malmi, Ingmar Weber

Research output: Chapter in Book/Report/Conference proceedingConference contribution

17 Citations (Scopus)

Abstract

Understanding the demographics of app users is crucial, for example, for app developers, who wish to target their advertisements more effectively. Our work addresses this need by studying the predictability of user demographics based on the list of a user's apps which is readily available to many app developers. We extend previous work on the problem on three frontiers: (1) We predict new demographics (age, race, and income) and analyze the most informative apps for four demographic attributes included in our analysis. The most predictable attribute is gender (82.3 % accuracy), whereas the hardest to predict is income (60.3 % accuracy). (2)We compare several dimensionality reduction methods for high-dimensional app data, finding out that an unsupervised method yields superior results compared to aggregating the apps at the app category level, but the best results are obtained simply by the raw list of apps. (3) We look into the effect of the training set size and the number of apps on the predictability and show that both of these factors have a large impact on the prediction accuracy. The predictability increases, or in other words, a user's privacy decreases, the more apps the user has used, but somewhat surprisingly, after 100 apps, the prediction accuracy starts to decrease.

Original languageEnglish
Title of host publicationProceedings of the 10th International Conference on Web and Social Media, ICWSM 2016
PublisherAAAI Press
Pages635-638
Number of pages4
ISBN (Electronic)9781577357582
Publication statusPublished - 2016
Event10th International Conference on Web and Social Media, ICWSM 2016 - Cologne, Germany
Duration: 17 May 201620 May 2016

Other

Other10th International Conference on Web and Social Media, ICWSM 2016
CountryGermany
CityCologne
Period17/5/1620/5/16

Fingerprint

Application programs

ASJC Scopus subject areas

  • Computer Networks and Communications

Cite this

Malmi, E., & Weber, I. (2016). You are what apps you use: Demographic prediction based on user's apps. In Proceedings of the 10th International Conference on Web and Social Media, ICWSM 2016 (pp. 635-638). AAAI Press.

You are what apps you use : Demographic prediction based on user's apps. / Malmi, Eric; Weber, Ingmar.

Proceedings of the 10th International Conference on Web and Social Media, ICWSM 2016. AAAI Press, 2016. p. 635-638.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Malmi, E & Weber, I 2016, You are what apps you use: Demographic prediction based on user's apps. in Proceedings of the 10th International Conference on Web and Social Media, ICWSM 2016. AAAI Press, pp. 635-638, 10th International Conference on Web and Social Media, ICWSM 2016, Cologne, Germany, 17/5/16.
Malmi E, Weber I. You are what apps you use: Demographic prediction based on user's apps. In Proceedings of the 10th International Conference on Web and Social Media, ICWSM 2016. AAAI Press. 2016. p. 635-638
Malmi, Eric ; Weber, Ingmar. / You are what apps you use : Demographic prediction based on user's apps. Proceedings of the 10th International Conference on Web and Social Media, ICWSM 2016. AAAI Press, 2016. pp. 635-638
@inproceedings{b1b0b71c1aa944569fde063cf853249e,
title = "You are what apps you use: Demographic prediction based on user's apps",
abstract = "Understanding the demographics of app users is crucial, for example, for app developers, who wish to target their advertisements more effectively. Our work addresses this need by studying the predictability of user demographics based on the list of a user's apps which is readily available to many app developers. We extend previous work on the problem on three frontiers: (1) We predict new demographics (age, race, and income) and analyze the most informative apps for four demographic attributes included in our analysis. The most predictable attribute is gender (82.3 {\%} accuracy), whereas the hardest to predict is income (60.3 {\%} accuracy). (2)We compare several dimensionality reduction methods for high-dimensional app data, finding out that an unsupervised method yields superior results compared to aggregating the apps at the app category level, but the best results are obtained simply by the raw list of apps. (3) We look into the effect of the training set size and the number of apps on the predictability and show that both of these factors have a large impact on the prediction accuracy. The predictability increases, or in other words, a user's privacy decreases, the more apps the user has used, but somewhat surprisingly, after 100 apps, the prediction accuracy starts to decrease.",
author = "Eric Malmi and Ingmar Weber",
year = "2016",
language = "English",
pages = "635--638",
booktitle = "Proceedings of the 10th International Conference on Web and Social Media, ICWSM 2016",
publisher = "AAAI Press",

}

TY - GEN

T1 - You are what apps you use

T2 - Demographic prediction based on user's apps

AU - Malmi, Eric

AU - Weber, Ingmar

PY - 2016

Y1 - 2016

N2 - Understanding the demographics of app users is crucial, for example, for app developers, who wish to target their advertisements more effectively. Our work addresses this need by studying the predictability of user demographics based on the list of a user's apps which is readily available to many app developers. We extend previous work on the problem on three frontiers: (1) We predict new demographics (age, race, and income) and analyze the most informative apps for four demographic attributes included in our analysis. The most predictable attribute is gender (82.3 % accuracy), whereas the hardest to predict is income (60.3 % accuracy). (2)We compare several dimensionality reduction methods for high-dimensional app data, finding out that an unsupervised method yields superior results compared to aggregating the apps at the app category level, but the best results are obtained simply by the raw list of apps. (3) We look into the effect of the training set size and the number of apps on the predictability and show that both of these factors have a large impact on the prediction accuracy. The predictability increases, or in other words, a user's privacy decreases, the more apps the user has used, but somewhat surprisingly, after 100 apps, the prediction accuracy starts to decrease.

AB - Understanding the demographics of app users is crucial, for example, for app developers, who wish to target their advertisements more effectively. Our work addresses this need by studying the predictability of user demographics based on the list of a user's apps which is readily available to many app developers. We extend previous work on the problem on three frontiers: (1) We predict new demographics (age, race, and income) and analyze the most informative apps for four demographic attributes included in our analysis. The most predictable attribute is gender (82.3 % accuracy), whereas the hardest to predict is income (60.3 % accuracy). (2)We compare several dimensionality reduction methods for high-dimensional app data, finding out that an unsupervised method yields superior results compared to aggregating the apps at the app category level, but the best results are obtained simply by the raw list of apps. (3) We look into the effect of the training set size and the number of apps on the predictability and show that both of these factors have a large impact on the prediction accuracy. The predictability increases, or in other words, a user's privacy decreases, the more apps the user has used, but somewhat surprisingly, after 100 apps, the prediction accuracy starts to decrease.

UR - http://www.scopus.com/inward/record.url?scp=84979633224&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84979633224&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84979633224

SP - 635

EP - 638

BT - Proceedings of the 10th International Conference on Web and Social Media, ICWSM 2016

PB - AAAI Press

ER -