© 2019 Strange Loop
Video games define our era both in terms of market share, cultural impact and complexity of the medium. Nowadays players generate extremely rich datasets that record each and every in-game action, social interaction, ad view or purchase. Because of the constant and continued relationship between player and game, which can last for years, such player behavioral data constitutes a unique sample of information on human behavior. Yokozuna Data, a Keywords Studio headquartered in Tokyo, is leading the data science revolution in the video game industry, developing next-generation machine learning software to operationally predict the behavior of individual players. Models based on convolutional neural networks and conditional inference survival ensembles can reveal information such as the moment and game level at which a certain player will leave the game, how much they will spend until then, when they will make their next battle or which virtual item they are likely to select. This allows game developers to take preventive actions aimed at maximizing player engagement and to create an optimal, personalized game experience. I will review how these techniques can be used to create customized game events and provide individual recommendations on in-game items and actions. As I will discuss, the ability of these methods to deal with really big datasets (petabytes of data) and to adapt to different kinds of games and players makes them suitable for use in operational environment.
África Periáñez is the founder and CEO of Yokozuna Data, a Keywords Studio based in Tokyo. She leads a team of data scientists and data engineers who develop a state-of-the-art machine learning platform that predicts individual player behavior. The goal of África is to democratize game data science and push back the frontiers of this field. Using cutting-edge machine learning techniques, she aims to obtain a thorough understanding of players' behavior and to accurately predict their actions in order to contribute to the development of data-driven, personalized games. She is a senior data scientist and researcher with 14+ years of experience and holds a PhD in Mathematics from the University of Reading (UK), a Master of Advanced Studies in String Theory Physics carried out at CERN (Switzerland), and an MSc in Theoretical Physics from the Autonomous University of Madrid (Spain). She has worked as a research scientist in renowned institutions such as CERN (under a Marie Curie individual fellowship), RIKEN in Japan (working with the K computer, one of the fastest supercomputers in the world), DWD in Germany (German Weather Service, working in satellite data assimilation), or the University of Reading in the UK. She is the co-author of multiple peer-reviewed articles and has been a speaker in numerous international conferences and regular seminars. She also has significant industry experience at SPSS Inc., IBM, Silicon Studio, and now Keywords Studios. Her work has been featured in different media, including Bloomberg,SINC, The Economic Timesor The Japan Times. Most recently she contributed to Quartz's "Future of Gaming", a chapter of their celebrated "What Happens Next" series.