1,139 Hits in 3.5 sec

Predicting player churn in the wild

Fabian Hadiji, Rafet Sifa, Anders Drachen, Christian Thurau, Kristian Kersting, Christian Bauckhage
2014 2014 IEEE Conference on Computational Intelligence and Games  
One of the key challenges is modeling and predicting player churn. This paper presents the first cross-game study of churn prediction in Free-to-Play games.  ...  The presented classifiers are applied on a dataset covering five free-to-play games resulting in high accuracy churn prediction.  ...  the wild.  ... 
doi:10.1109/cig.2014.6932876 dblp:conf/cig/HadijiSDTKB14 fatcat:tj5aecwzmzaz7dvny77lgafc3a

GAIM: Game Action Information Mining Framework for Multiplayer Online Card Games (Rummy as Case Study) [chapter]

Sharanya Eswaran, Vikram Vimal, Deepanshi Seth, Tridib Mukherjee
2020 Lecture Notes in Computer Science  
In particular, we focus on multi-player, skill-based card games, and use Rummy as a case study.  ...  We introduce GAIM, a deep-learning analytical framework that enables benchmarking and profiling of players, from the perspective of how the players react to the game state and evolution of games.  ...  To understand why DA improved churn prediction, we look into a player who churned and was correctly predicted by HQE-enhanced model, but not baseline churn model.  ... 
doi:10.1007/978-3-030-47436-2_33 fatcat:mpx4y56vtzfoxc7flinblntf6q

The Playtime Principle: Large-scale cross-games interest modeling

Rafet Sifa, Christian Bauckhage, Anders Drachen
2014 2014 IEEE Conference on Computational Intelligence and Games  
Predicting behavior is necessary to describe player engagement and prevent future player churn.  ...  One of the key challenges in game analytics is the development of methods for characterizing and predicting player behavior as it evolves over time.  ...  ACKNOWLEDGMENTS The work reported in this paper was carried out within the Fraunhofer / University of Southampton research project SoFWIReD. The authors gratefully acknowledge this support.  ... 
doi:10.1109/cig.2014.6932906 dblp:conf/cig/SifaBD14 fatcat:hajo7gpfmnh3tjs7vltd5anqqe

Data-Driven Game Development: Ethical Considerations [article]

Magy Seif El-Nasr, Erica Kleinman
2020 arXiv   pre-print
Previous work in player modeling as well as work in the fields of AI and machine learning have demonstrated several ways in which algorithmic decision-making can be flawed due to data or algorithmic bias  ...  In recent years, the games industry has made a major move towards data-driven development, using data analytics and player modeling to inform design decisions.  ...  [30] developed a set of classifiers that can be used to predict churn in "freemium" (free to play, pay for bonuses) games. Additionally, Peterson et al.  ... 
arXiv:2006.10808v1 fatcat:ejn4ei4hznhizj5wiuutpsk73y

AI in (and for) Games [article]

Kostas Karpouzis, George Tsatiris
2021 arXiv   pre-print
This relation is two-fold: on one hand, AI/ML researchers can generate large, in-the-wild datasets of human affective activity, player behaviour (i.e. actions within the game world), commercial behaviour  ...  and responsive non-player characters (NPCs) or predict and respond player behaviour across a wide variety of player cultures.  ...  Acknowledgements This work has been partly funded by the iRead project which has received funding from the European Union's Horizon 2020 Research and Innovation programme under Grant Agreement No. 731724  ... 
arXiv:2105.03123v1 fatcat:gxy4lhmlhjhclmnax2rwyctbum

Page 63 of Youth's Companion Vol. 78, Issue 5 [page]

1904 Youth's Companion  
The milk of buffaloes that are not “sacred’”’ is churned in the front part 7 of the huts in which the people live.  ...  Bourse is taking like wild-fire.— Boston Globe.  ... 

On Quitting: Performance and Practice in Online Game Play [article]

Tushar Agarwal, Keith A. Burghardt, Kristina Lerman
2017 arXiv   pre-print
Finally, we train an epsilon-machine, a type of hidden Markov model, and find a plausible mechanism of game play that can predict player performance and quitting the game.  ...  We find significant heterogeneity in the improvement of player performance, given by score, and address this by dividing players into similar skill levels and segmenting each player's activity into sessions  ...  Acknowledgments This work was supported in part by NSF (#SMA-1360058), ARO (#W911NF-15-1-0142), and the USC Viterbi-India and ISI summer internship programs.  ... 
arXiv:1703.04696v1 fatcat:cwdczlqfdvakdiozfaoeh4dze4

A Comparison of Methods for Player Clustering via Behavioral Telemetry [article]

Anders Drachen, Christian Thurau, Rafet Sifa, Christian Bauckhage
2014 arXiv   pre-print
installed game clients of the entire population of players.  ...  The analysis of user behavior in digital games has been aided by the introduction of user telemetry in game development, which provides unprecedented access to quantitative data on user behavior from the  ...  Within the past few years, behavior analysis in digital games has moved from the laboratory to the wild thanks to telemetry tracking, and rapidly become a widely applied factor in game development.  ... 
arXiv:1407.3950v1 fatcat:en2uncct3rehjklclggv7zhpzu

"And then they died": Using Action Sequences for Data Driven,Context Aware Gameplay Analysis [article]

Erica Kleinman, Sabbir Ahmad, Zhaoqing Teng, Andy Bryant, Truong-Huy D. Nguyen, Casper Harteveld, Magy Seif El-Nasr
2020 arXiv   pre-print
While effective in extracting information regarding player action, much of the context regarding when and how those actions occurred is lost.  ...  We present the methodology along with a case study demonstrating how it can be used to analyze behavioral patterns of teamwork in the popular multiplayer game Defense of the Ancients 2 (DotA 2).  ...  They are then able to analyze these clusters in order to classify player types and predict churn rates [50] .  ... 
arXiv:2006.10823v1 fatcat:aidrizomnrberktgjqteylgv4e

The Proficiency-Congruency Dilemma: Virtual Team Design and Performance in Multiplayer Online Games [article]

Jooyeon Kim, Brian C. Keegan, Sungjoon Park, Alice Oh
2015 arXiv   pre-print
When designing a team, players must negotiate a proficiency-congruency dilemma between selecting roles that best match their experience and roles that best complement the existing roles on the team.  ...  We also conduct focus groups with novice and elite players to understand how players' team design practices vary with expertise.  ...  more ideal "model organisms" for team effectiveness research in the "wild" outside of laboratories [17, 84] .  ... 
arXiv:1512.08321v1 fatcat:cuxtmzcgvnebtjav5hodgfw5pu

Page 24 of Collier's: The National Weekly Vol. 45, Issue 4 [page]

1910 Collier's: The National Weekly  
what is most needed is a change of the character of exhortation to the players in the dressing-room, [t should be impressed aipon ever)  ...  Give me a dynamo and a few pounds of wire; and [ll run the washing-machine and the churn-handle and the house-sweeper and the fanning mill and the grindstone and the silo machine and the rORI< mule-deer  ... 

Not All the Bots Are Created Equal: The Ordering Turing Test for the Labeling of Bots in MMORPGs

Stefano De Paoli
2017 Social Media + Society  
This article contributes to the research on bots in Social Media.  ...  Data for the research comes from scientific literature on Machine Learning proposed for the identification of bots and from game forums and other player produced paratexts from the case study of the game  ...  The wild is a PvP area. The Aubury Shop instead is located in a safe area.  ... 
doi:10.1177/2056305117741851 fatcat:ocnovzu3k5hvhk4j5sktfb6774

Behavior evolution in Tomb Raider Underworld

Rafet Sifa, Anders Drachen, Christian Bauckhage, Christian Thurau, Alessandro Canossa
2013 2013 IEEE Conference on Computational Inteligence in Games (CIG)  
In this paper, the focus is on examining the behavior of 62,000 players from the major commercial game Tomb Raider: Underworld, as it unfolds from the beginning of the game and throughout the seven main  ...  This makes dimensionality-reduction methods such as clustering and classification useful for discovering and defining patterns in player behavior.  ...  The work presented here would not be possible without the collaboration of these colleagues.  ... 
doi:10.1109/cig.2013.6633637 dblp:conf/cig/SifaDBTC13 fatcat:cwiru6fclfeq3mcjff3olaiu5u

The Big Three: A Methodology to Increase Data Science ROI by Answering the Questions Companies Care About [article]

Daniel K. Griffin
2020 arXiv   pre-print
The applications of data science seem to be nearly endless in today's modern landscape, with each company jockeying for position in the new data and insights economy.  ...  Companies may be achieving only a third of the value they could be getting from data science in industry applications.  ...  This is typically referred to as predicting churn, or churn risk prediction. It is closely related to sales and demand forecasting mentioned in the prediction and pattern mining section.  ... 
arXiv:2002.07069v1 fatcat:if3das3tpbeuba33gmsnmvulrm

Network Science Predicts Who Dies Next in Game of Thrones [article]

Milan Janosov
2021 arXiv   pre-print
As an example, this short project was carried out in 2017 and was followed by some media attention, with the following goal: to bring network science and predictive modeling together on the subject of  ...  the popular TV and book series, Game of Thrones, and predict which key characters are likely to meet their ends.  ...  In this network, every major character is represented by a network node, while there is a link between two players if they co-occurred in the same scene.  ... 
arXiv:2110.09856v1 fatcat:w7udszioojgrbkmulk5ct2dwt4
« Previous Showing results 1 — 15 out of 1,139 results