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.
| Language | English |
|---|---|
| Title of host publication | Proceedings of the Australasian Computer Science Week Multiconference, ACSW 2018 |
| Place of Publication | New York |
| Publisher | Association for Computing Machinery |
| Pages | 1-9 |
| Number of pages | 9 |
| Volume | Part F134893 |
| ISBN (Electronic) | 9781450354363 |
| DOIs | |
| Publication status | Published - 29 Jan 2018 |
| Event | 2018 Australasian Computer Science Week Multiconference, ACSW 2018 - Brisbane, Australia Duration: 29 Jan 2018 → 2 Feb 2018 |
Conference
| Conference | 2018 Australasian Computer Science Week Multiconference, ACSW 2018 |
|---|---|
| Country | Australia |
| City | Brisbane |
| Period | 29/01/18 → 2/02/18 |
Fingerprint
Cite this
}
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 proceeding › Conference proceeding contribution › Research › peer-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 -