Player retention in league of legends: a study using survival analysis

Simon Demediuk, Alexandra Murrin, David Bulger, Michael Hitchens, Anders Drachen, William L. Raffe, Marco Tamassia

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionResearchpeer-review

Abstract

Multi-player online esports games are designed for extended durations of play, requiring substantial experience to master. Furthermore, esports game revenues are increasingly driven by in-game purchases. For esports companies, the trends in players leaving their games therefore not only provide information about potential problems in the user experience, but also impacts revenue. Being able to predict when players are about to leave the game-churn prediction-is therefore an important solution for companies in the rapidly growing esports sector, as this allows them to take action to remedy churn problems. The objective of the work presented here is to understand the impact of specific behavioral characteristics on the likelihood of a player continuing to play the esports title League of Legends. Here, a solution to the problem is presented based on the application of survival analysis, using Mixed Effects Cox Regression, to predict player churn. Survival Analysis forms a useful approach for the churn prediction problem as it provides rates as well as an assessment of the characteristics of players who are at risk of leaving the game. Hazard rates are also presented for the leading indicators, with results showing that duration between matches played is a strong indicator of potential churn.

LanguageEnglish
Title of host publicationProceedings of the Australasian Computer Science Week Multiconference, ACSW 2018
Place of PublicationNew York
PublisherAssociation for Computing Machinery
Pages1-9
Number of pages9
VolumePart F134893
ISBN (Electronic)9781450354363
DOIs
Publication statusPublished - 29 Jan 2018
Event2018 Australasian Computer Science Week Multiconference, ACSW 2018 - Brisbane, Australia
Duration: 29 Jan 20182 Feb 2018

Conference

Conference2018 Australasian Computer Science Week Multiconference, ACSW 2018
CountryAustralia
CityBrisbane
Period29/01/182/02/18

Fingerprint

Industry
Hazards

Cite this

Demediuk, S., Murrin, A., Bulger, D., Hitchens, M., Drachen, A., Raffe, W. L., & Tamassia, M. (2018). Player retention in league of legends: a study using survival analysis. In Proceedings of the Australasian Computer Science Week Multiconference, ACSW 2018 (Vol. Part F134893, pp. 1-9). [3167937] New York: Association for Computing Machinery. https://doi.org/10.1145/3167918.3167937
Demediuk, Simon ; Murrin, Alexandra ; Bulger, David ; Hitchens, Michael ; Drachen, Anders ; Raffe, William L. ; Tamassia, Marco. / Player retention in league of legends : a study using survival analysis. Proceedings of the Australasian Computer Science Week Multiconference, ACSW 2018. Vol. Part F134893 New York : Association for Computing Machinery, 2018. pp. 1-9
@inproceedings{3696f9a7a62c4da0969abb2bc8ae12ab,
title = "Player retention in league of legends: a study using survival analysis",
abstract = "Multi-player online esports games are designed for extended durations of play, requiring substantial experience to master. Furthermore, esports game revenues are increasingly driven by in-game purchases. For esports companies, the trends in players leaving their games therefore not only provide information about potential problems in the user experience, but also impacts revenue. Being able to predict when players are about to leave the game-churn prediction-is therefore an important solution for companies in the rapidly growing esports sector, as this allows them to take action to remedy churn problems. The objective of the work presented here is to understand the impact of specific behavioral characteristics on the likelihood of a player continuing to play the esports title League of Legends. Here, a solution to the problem is presented based on the application of survival analysis, using Mixed Effects Cox Regression, to predict player churn. Survival Analysis forms a useful approach for the churn prediction problem as it provides rates as well as an assessment of the characteristics of players who are at risk of leaving the game. Hazard rates are also presented for the leading indicators, with results showing that duration between matches played is a strong indicator of potential churn.",
keywords = "Business intelligence, Churn, Churn prediction, Esports, Game analytics, League of Legends, Prediction",
author = "Simon Demediuk and Alexandra Murrin and David Bulger and Michael Hitchens and Anders Drachen and Raffe, {William L.} and Marco Tamassia",
year = "2018",
month = "1",
day = "29",
doi = "10.1145/3167918.3167937",
language = "English",
volume = "Part F134893",
pages = "1--9",
booktitle = "Proceedings of the Australasian Computer Science Week Multiconference, ACSW 2018",
publisher = "Association for Computing Machinery",

}

Demediuk, S, Murrin, A, Bulger, D, Hitchens, M, Drachen, A, Raffe, WL & Tamassia, M 2018, Player retention in league of legends: a study using survival analysis. in Proceedings of the Australasian Computer Science Week Multiconference, ACSW 2018. vol. Part F134893, 3167937, Association for Computing Machinery, New York, pp. 1-9, 2018 Australasian Computer Science Week Multiconference, ACSW 2018, Brisbane, Australia, 29/01/18. https://doi.org/10.1145/3167918.3167937

Player retention in league of legends : a study using survival analysis. / Demediuk, Simon; Murrin, Alexandra; Bulger, David; Hitchens, Michael; Drachen, Anders; Raffe, William L.; Tamassia, Marco.

Proceedings of the Australasian Computer Science Week Multiconference, ACSW 2018. Vol. Part F134893 New York : Association for Computing Machinery, 2018. p. 1-9 3167937.

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionResearchpeer-review

TY - GEN

T1 - Player retention in league of legends

T2 - a study using survival analysis

AU - Demediuk,Simon

AU - Murrin,Alexandra

AU - Bulger,David

AU - Hitchens,Michael

AU - Drachen,Anders

AU - Raffe,William L.

AU - Tamassia,Marco

PY - 2018/1/29

Y1 - 2018/1/29

N2 - Multi-player online esports games are designed for extended durations of play, requiring substantial experience to master. Furthermore, esports game revenues are increasingly driven by in-game purchases. For esports companies, the trends in players leaving their games therefore not only provide information about potential problems in the user experience, but also impacts revenue. Being able to predict when players are about to leave the game-churn prediction-is therefore an important solution for companies in the rapidly growing esports sector, as this allows them to take action to remedy churn problems. The objective of the work presented here is to understand the impact of specific behavioral characteristics on the likelihood of a player continuing to play the esports title League of Legends. Here, a solution to the problem is presented based on the application of survival analysis, using Mixed Effects Cox Regression, to predict player churn. Survival Analysis forms a useful approach for the churn prediction problem as it provides rates as well as an assessment of the characteristics of players who are at risk of leaving the game. Hazard rates are also presented for the leading indicators, with results showing that duration between matches played is a strong indicator of potential churn.

AB - Multi-player online esports games are designed for extended durations of play, requiring substantial experience to master. Furthermore, esports game revenues are increasingly driven by in-game purchases. For esports companies, the trends in players leaving their games therefore not only provide information about potential problems in the user experience, but also impacts revenue. Being able to predict when players are about to leave the game-churn prediction-is therefore an important solution for companies in the rapidly growing esports sector, as this allows them to take action to remedy churn problems. The objective of the work presented here is to understand the impact of specific behavioral characteristics on the likelihood of a player continuing to play the esports title League of Legends. Here, a solution to the problem is presented based on the application of survival analysis, using Mixed Effects Cox Regression, to predict player churn. Survival Analysis forms a useful approach for the churn prediction problem as it provides rates as well as an assessment of the characteristics of players who are at risk of leaving the game. Hazard rates are also presented for the leading indicators, with results showing that duration between matches played is a strong indicator of potential churn.

KW - Business intelligence

KW - Churn

KW - Churn prediction

KW - Esports

KW - Game analytics

KW - League of Legends

KW - Prediction

UR - http://www.scopus.com/inward/record.url?scp=85044769193&partnerID=8YFLogxK

U2 - 10.1145/3167918.3167937

DO - 10.1145/3167918.3167937

M3 - Conference proceeding contribution

VL - Part F134893

SP - 1

EP - 9

BT - Proceedings of the Australasian Computer Science Week Multiconference, ACSW 2018

PB - Association for Computing Machinery

CY - New York

ER -

Demediuk S, Murrin A, Bulger D, Hitchens M, Drachen A, Raffe WL et al. Player retention in league of legends: a study using survival analysis. In Proceedings of the Australasian Computer Science Week Multiconference, ACSW 2018. Vol. Part F134893. New York: Association for Computing Machinery. 2018. p. 1-9. 3167937 https://doi.org/10.1145/3167918.3167937