Abstract
Game companies avoid sharing their game data with external researchers. Only a few research groups have been granted limited access to game data so far. The reluctance of these companies to make data publicly available limits the wide use and development of data mining techniques and artificial intelligence research specific to the game industry. In this work, we developed and implemented an international competition on game data mining using commercial game log data from one of the major game companies in South Korea: NCSOFT. Our approach enabled researchers to develop and apply state-of-the-art data mining techniques to game log data by making the data open. For the competition, data were collected from Blade & Soul, an action role-playing game, from NCSOFT. The data comprised approximately 100 GB of game logs from 10,000 players. The main aim of the competition was to predict whether a player would churn and when the player would churn during two periods between which the business model was changed to a free-to-play model from a monthly subscription. The results of the competition revealed that highly ranked competitors used deep learning, tree boosting, and linear regression.
Highlights
Game artificial intelligence (AI) competition platforms help researchers access well-defined benchmarking problems to evaluate different algorithms, test new approaches, and educate students [1]
Periáñez are with Game Data Science Department, Yokozuna Data, Silicon Studio, 1-21-3 Ebisu the research has concentrated on building AI players to play challenging games such as StarCraft and simulated car racing and fighting games; these competitions commonly rank AI players based on the results of numerous game plays, using, for example, final scores and win ratios
Participants’ performances were measured using the average of the F1 score and root mean squared logarithmic error (RMSLE) on the two test sets for Track 1 and Track 2, respectively [Eq (1) and (2), respectively]: F1
Summary
Game artificial intelligence (AI) competition platforms help researchers access well-defined benchmarking problems to evaluate different algorithms, test new approaches, and educate students [1]. Since the early 2000s, considerable effort has focused on designing and running new game AI competitions using mathematical, board, video, and physical games [2]. Periáñez are with Game Data Science Department, Yokozuna Data, Silicon Studio, 1-21-3 Ebisu the research has concentrated on building AI players to play challenging games such as StarCraft and simulated car racing and fighting games; these competitions commonly rank AI players based on the results of numerous game plays, using, for example, final scores and win ratios. There have been special competitions that target humanlikeness [3], general game playing [4], and the learning ability of AI players. There have been few competitions on content creation [5], game player modeling, or game data mining
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
