Tortoise or Hare? Quantifying the Effects of Performance on Mobile App Retention

Tutkimustuotos: Artikkeli kirjassa/raportissa/konferenssijulkaisussaKonferenssiartikkeliTieteellinenvertaisarvioitu

Kuvaus

We contribute by quantifying the effect of network latency and battery consumption on mobile app performance and retention, i.e., user’s decisions to continue or stop using apps. We perform our analysis by fusing two large-scale crowdsensed datasets collected by piggybacking on information captured by mobile apps. We find that app performance has an impact in its retention rate. Our results demonstrate that high energy consumption and high latency decrease the likelihood of retaining an app. Conversely, we show that reducing latency or energy consumption does not guarantee higher likelihood of retention as long as they are within reasonable standards of performance. However, we also demonstrate that what is considered reasonable depends on what users have been accustomed to, with device and network characteristics, and app category playing a role. As our second contribution, we develop a model for predicting retention based on performance metrics. We demonstrate the benefits of our model through empirical benchmarks which show that our model not only predicts retention accurately, but generalizes well across application categories, locations and other factors moderating the effect of performance.
Alkuperäiskielienglanti
OtsikkoProceedings of the 2019 World Wide Web Conference (WWW '19)
Sivumäärä10
KustantajaInternational World Wide Web Conferences Steering Committee
Julkaisupäivätoukokuuta 2019
ISBN (elektroninen)978-1-4503-6674-8/19/05
DOI - pysyväislinkit
TilaHyväksytty/In press - toukokuuta 2019
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisuussa
TapahtumaInternational World Wide Web Conference on World Wide Web (WWW 2019) - Hyatt Regency San Francisco Hotel, San Francisco, Yhdysvallat (USA)
Kesto: 13 toukokuuta 201917 toukokuuta 2019
Konferenssinumero: 28
https://www2019.thewebconf.org/

Tieteenalat

  • 113 Tietojenkäsittely- ja informaatiotieteet

Lainaa tätä

Zuniga Corrales, W. A., Flores Macario, H. R., Lagerspetz, E., Tarkoma, S. A. O., Manner, J., Hui, P., & Nurmi, P. T. (Hyväksytty/painossa). Tortoise or Hare? Quantifying the Effects of Performance on Mobile App Retention. teoksessa Proceedings of the 2019 World Wide Web Conference (WWW '19) International World Wide Web Conferences Steering Committee. https://doi.org/10.1145/3308558.3313428
@inproceedings{07ef6408c7384ae18863de736c34b4e1,
title = "Tortoise or Hare? Quantifying the Effects of Performance on Mobile App Retention",
abstract = "We contribute by quantifying the effect of network latency and battery consumption on mobile app performance and retention, i.e., user’s decisions to continue or stop using apps. We perform our analysis by fusing two large-scale crowdsensed datasets collected by piggybacking on information captured by mobile apps. We find that app performance has an impact in its retention rate. Our results demonstrate that high energy consumption and high latency decrease the likelihood of retaining an app. Conversely, we show that reducing latency or energy consumption does not guarantee higher likelihood of retention as long as they are within reasonable standards of performance. However, we also demonstrate that what is considered reasonable depends on what users have been accustomed to, with device and network characteristics, and app category playing a role. As our second contribution, we develop a model for predicting retention based on performance metrics. We demonstrate the benefits of our model through empirical benchmarks which show that our model not only predicts retention accurately, but generalizes well across application categories, locations and other factors moderating the effect of performance.",
keywords = "113 Computer and information sciences, performance evaluation, crowdsensing, data fusion, mobile computing, apps retention, mobile networks, energy consumption",
author = "{Zuniga Corrales}, {Wladimir Agustin} and {Flores Macario}, {Huber Raul} and Eemil Lagerspetz and Tarkoma, {Sasu Arimo Olavi} and Jukka Manner and Pan Hui and Nurmi, {Petteri Tapio}",
year = "2019",
month = "5",
doi = "10.1145/3308558.3313428",
language = "English",
booktitle = "Proceedings of the 2019 World Wide Web Conference (WWW '19)",
publisher = "International World Wide Web Conferences Steering Committee",
address = "Switzerland",

}

Zuniga Corrales, WA, Flores Macario, HR, Lagerspetz, E, Tarkoma, SAO, Manner, J, Hui, P & Nurmi, PT 2019, Tortoise or Hare? Quantifying the Effects of Performance on Mobile App Retention. julkaisussa Proceedings of the 2019 World Wide Web Conference (WWW '19). International World Wide Web Conferences Steering Committee, International World Wide Web Conference on World Wide Web (WWW 2019), San Francisco, Yhdysvallat (USA), 13/05/2019. https://doi.org/10.1145/3308558.3313428

Tortoise or Hare? Quantifying the Effects of Performance on Mobile App Retention. / Zuniga Corrales, Wladimir Agustin; Flores Macario, Huber Raul; Lagerspetz, Eemil; Tarkoma, Sasu Arimo Olavi; Manner, Jukka; Hui, Pan; Nurmi, Petteri Tapio.

Proceedings of the 2019 World Wide Web Conference (WWW '19). International World Wide Web Conferences Steering Committee, 2019.

Tutkimustuotos: Artikkeli kirjassa/raportissa/konferenssijulkaisussaKonferenssiartikkeliTieteellinenvertaisarvioitu

TY - GEN

T1 - Tortoise or Hare? Quantifying the Effects of Performance on Mobile App Retention

AU - Zuniga Corrales, Wladimir Agustin

AU - Flores Macario, Huber Raul

AU - Lagerspetz, Eemil

AU - Tarkoma, Sasu Arimo Olavi

AU - Manner, Jukka

AU - Hui, Pan

AU - Nurmi, Petteri Tapio

PY - 2019/5

Y1 - 2019/5

N2 - We contribute by quantifying the effect of network latency and battery consumption on mobile app performance and retention, i.e., user’s decisions to continue or stop using apps. We perform our analysis by fusing two large-scale crowdsensed datasets collected by piggybacking on information captured by mobile apps. We find that app performance has an impact in its retention rate. Our results demonstrate that high energy consumption and high latency decrease the likelihood of retaining an app. Conversely, we show that reducing latency or energy consumption does not guarantee higher likelihood of retention as long as they are within reasonable standards of performance. However, we also demonstrate that what is considered reasonable depends on what users have been accustomed to, with device and network characteristics, and app category playing a role. As our second contribution, we develop a model for predicting retention based on performance metrics. We demonstrate the benefits of our model through empirical benchmarks which show that our model not only predicts retention accurately, but generalizes well across application categories, locations and other factors moderating the effect of performance.

AB - We contribute by quantifying the effect of network latency and battery consumption on mobile app performance and retention, i.e., user’s decisions to continue or stop using apps. We perform our analysis by fusing two large-scale crowdsensed datasets collected by piggybacking on information captured by mobile apps. We find that app performance has an impact in its retention rate. Our results demonstrate that high energy consumption and high latency decrease the likelihood of retaining an app. Conversely, we show that reducing latency or energy consumption does not guarantee higher likelihood of retention as long as they are within reasonable standards of performance. However, we also demonstrate that what is considered reasonable depends on what users have been accustomed to, with device and network characteristics, and app category playing a role. As our second contribution, we develop a model for predicting retention based on performance metrics. We demonstrate the benefits of our model through empirical benchmarks which show that our model not only predicts retention accurately, but generalizes well across application categories, locations and other factors moderating the effect of performance.

KW - 113 Computer and information sciences

KW - performance evaluation

KW - crowdsensing

KW - data fusion

KW - mobile computing

KW - apps retention

KW - mobile networks

KW - energy consumption

U2 - 10.1145/3308558.3313428

DO - 10.1145/3308558.3313428

M3 - Conference contribution

BT - Proceedings of the 2019 World Wide Web Conference (WWW '19)

PB - International World Wide Web Conferences Steering Committee

ER -

Zuniga Corrales WA, Flores Macario HR, Lagerspetz E, Tarkoma SAO, Manner J, Hui P et al. Tortoise or Hare? Quantifying the Effects of Performance on Mobile App Retention. julkaisussa Proceedings of the 2019 World Wide Web Conference (WWW '19). International World Wide Web Conferences Steering Committee. 2019 https://doi.org/10.1145/3308558.3313428