Researchers develop tool to predict what gamers want

Researchers from North Carolina State University have developed a new method that can predict the behavior of players in online role-playing games with an accuracy up to 80 percent. The tool could be used by the game industry to develop new game content, or to help steer players to the parts of a game they will enjoy most, based on their gaming style. The team developed the data-driven predictive method by analyzing the behavior of 14,000 players in the massively multiplayer online role-playing game (MMORPG) World of Warcraft (WoW).

"We are able to predict what a player in a game will do based on his or her previous behavior, with up to 80 percent accuracy," says Brent Harrison, a Ph.D. student at NC State and co-author of a paper describing the research. "In a game like World of Warcraft, which is constantly developing new content, this could help guide content design decisions."

The researchers developed the new method by evaluating the task-based achievement badges that players earn in WoW. These achievements are awarded whenever a player accomplishes a specific goal or series of goals. The team collected data on the order in which gamers earned their achievement badges and then identified the degree to which each individual achievement was correlated to every other achievement. The researchers used that data to identify groups of achievements - called cliques - that were closely related. Those cliques could then be used to predict future behavior. It was also discovered that highly correlated achievements - or part of the same clique - do not necessarily have any obvious connection to the outside observer.

If a gaming company wants to improve a game, it has to make sure players will like the changes. This research can help with that decision, as it points to what kind of storylines and mechanics players like about the game already. The research could also apply to any setting where users are making a series of decisions. Since this is a data-driven modeling approach, it could be done on a large scale with minimum input from game designers.

The researchers' work will be presented in a paper titled "Using Sequential Observations to Model and Predict Player Behavior" at the Foundations of Digital Games Conference (June 29, 2011 to July 1, 2011) in Bordeaux, France.