Is data mining the new tool for gamers seeking pre-launch secrets?
Despite great data analytics capabilities, gaming companies are facing an interesting data mining challenge from an unexpected end – their audience.
Titanfall, one of the most anticipated games of 2014, launched its Beta version on February 15 and in less than two days users have discovered lot more than intended by combing through its raw data files. The revealed information includes 14 maps, split-screen option and new game modes. Titanfall is scheduled to release for Xbox One, PC and Xbox 360 on March 14th 2013.
While this is certainly not the first time when curious gamers have mined game data to claim the fame by revealing the new features of yet-to-launch game versions, the speed with which it occurred this time is scintillating. Such data mining is getting diverse responses. Some are highly excited to know more about the forthcoming game and use this to plan their activities around launch day. Others refer to it using the plain old term - "hacking" - and abhor it for killing the surprise.
The phenomenon of gamers data-mining the game data is particularly interesting given the massive resources gaming companies are investing into mining users' data. For example, last year, with more than 2 billion gamers worldwide, Electronic Arts generated 50 TB of data per day. Game data mining is used for a variety of purposes (beyond the very obvious one - targeted marketing!):
- Find weak spots in a games' design
- Figure out how players spend their time when playing
- Predict when players will stop playing
- Discover which assets are not getting used
- Personalize i.e. make games that adapt to the player
However, with the increasing trend of smart players hacking into the game software data, Gaming companies need to be very cautious about the raw data accompanied in their game installations. Well, except for the cases where such data is left purposely to be data-mined by enthusiastic hackers, leading to some free pre-launch viral marketing.
Anmol Rajpurohit is an intern and blogger at KDnuggets, and a visiting student researcher at UCLA REMAP. He is a B.Tech. graduate in Computer Science from India and is keenly interested in research and development work in the field of Computer Networks, Information Retrieval and Knowledge Management (Data Mining, Web Mining, etc.).