2016 Symposium Keynote

The game industry is, just like any other technology-focused sector, faced with a deluge of data about users. Tracked across hardware platforms and online, behavioral data from users of games, apps and software in general is easy to collect, provides detailed views of the behavior of the users, and can be obtained at a massive scale. 

 

However, behavioral data can be difficult to translate into results and subsequent action. Such data streams are typically volumous, have high variety (or dimensionality) and is almost always very volatile, i.e. have value only for a short time. The problems with volatile, volumous and varied behavioral data are notably challenging in digital games, where ultra-high frequency data are captured across hundreds of millions of players on a daily basis. 

 

The pivot in the game industry towards mobile platforms and new business models in recent years, which today roughly covers 40% of the international market, has been associated with an acute need to take advantage of behavioral metrics. This has led to an incredibly rapid development in the analytics practices in games, which today is on par with sectors such as finance and health.

 

In order to deliver the user experience and ensure engagement in games, behavioral profiling and predictive modelling has emerged as ways of managing complex behavioral datastreams. Profiling users allow for a condensation and modeling of a complex behavioral space, and enables action to be taken towards meeting the needs of the users as made apparent via the profiles. 

 

This availability of behavioral and attributional data is mirrored in many other sectors, including the health, finance and social sectors. 

 

In this presentation, profiling as a tool for user behavior analysis, with an emphasis on game development, will be introduced and described, and an overview presented of different approaches and techniques, equally applicable in games-, health-, social-, financial- and other sectors. The presentation will also introduce the concept of cradle-to-grave profiling, as a framework for maintaining and updating dynamic user profiles throughout a production cycle. 

 

Bio: 

Anders Drachen, Ph.D. is a veteran Data Scientist, Game Analytics consultant at The Pagonis Network, co-director at the Center for Applied Game Research at Aalborg University (Denmark). His work in the game industry as well as in data and game science is focused on game analytics, business intelligence for games, game data mining, game user experience, industry economics, business development and game user research. His research and professional work is carried out in collaboration with companies spanning the industry, from big publishers to indies. He is one of the most published experts worldwide on the topic of game analytics, user research, game data mining, and user profiling, having authored more than 100 publications on game analytics, user testing, and business intelligence in game development. He writes about analytics on andersdrachen.com. His writings can also be found on the pages of trade publications such as Game Developer Magazine and Gamasutra.com. His research has been covered by international media, including Wired and Forbes, and won awards at international research conferences.