Posts Tagged ‘social games’

Sony Online Entertainment leverages Sonamine Predictive Player Scores

Wednesday, January 2nd, 2013 by Nick

Happy new year everyone!

There is a lot of industry interest in using data analytics in games.  Looking at the gamasutra or linkedin job board today, I see that Ubisoft, 2K games, MachineZone, Ngmoco, Microsoft, Z2live, Activision etc are all looking for data analysts.  Especially after it was revealed that the Democrats used a predictive scoring algorithm to allocate scare volunteer resources to get-out-the-vote, interest in using predictive analytics has never been higher, or more hyped.

But really, how do you actually use predictive scores in a day-to-day productionized manner to increase revenues and retention?  Well, one of Sonamine’s customer is Sony Online Entertainment, an industry leading MMO developer.  They have successfully integrated Sonamine predictive player scores into a full fledged player relationship management program that encompasses different player touch points, a communications calendar and different offers.  SOE presented their story at GDC Online in Austin.  (skip to link at bottom to get presentation).  Here are some of their lessons:

  • Develop a player relationship management program, with calendar of communications and offers.
  • Have a system that allows targeting to different sub-segments of players with appropriate messages.
  • Use Sonamine predictive scores to create different player segments.
  • Take the long view, it is a journey.
  • Do not underestimate the resources needed to pull this off.

Fill in a short form and download the Sony GDC presentation here.

Hardcore Classification-Identifying Play Styles in Social Games Using Network Analysis

Thursday, July 14th, 2011 by Nick

With ever growing social network platforms like Facebook and Google+, you might wander whether or not social network analysis can be used in games that do not have the same scale as these platforms.  After all, many social, online, MMO and mobile games are somewhat social in nature: they have chats, messages, friend lists and even synchronous quests within the game.

This study by social game researchers Kirman and Lawson quite definitively show that the social network WITHIN a social game is very similar to the social networks in the platforms.  The in-game network displays the same scale free property of social networks.  The degree distribution shows a “power law” distribution (see diagram below).

pd

What’s even more fascinating is that Kirman and Lawson were able to categorize the players into three group based on their impact to the overall game network.  Hardcore players when removed led to a disintegration of the player network.   Disintegration was defined as the largest connect network left being smaller than the disconnected players.  In other words, when you remove the hardcore players, what is left are more disconnected players than a connected group.

So what?

As game designers and community managers, we usually look for the players that spend the most time playing the game.  This paper shows an alternative where the players are the ones which are central to the in-game player network.  Marketers should also take note of these hardcore players, even if any of them are not revenue generating players.

Shameless plug – Check out Sonamine Predictive Player Segments – InfluenceSoon to see how we can identify these hardcore players for you.

Details
The data for this analysis was collected from a social game called Familiars over a two month period in 2008 with 157 players.  The authors used pretty standard social network analysis techniques such as identifying the degree distribution, clustering coefficient and path lengths.  The major caveat of this study is the smaller player base that was analyzed.  The key method to identify hardcore gamers was to first selectively identify players with the highest degree centrality, and then remove them one-by-one from the in-game network.

Reference (link to paper)

Ben Kirman and Shaun Lawson.  Hardcore Classification: Identifying Play Styles in Social Games Using Network Analysis.  S. Natkin and J. Dupire (Eds.): ICEC 5709, pp. 246–251, 2009. IFIP International Federation for Information Processing 2009