New tool helps game designers predict player behavior

Posted by Kate Taylor

A team at North Carolina State University says it can tell what gamers are about to do next, allowing games designers to steer players to the parts of games they'll like most.

"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 PhD student Brent Harrison.

“In a game like World of Warcraft, which is constantly developing new content, this could help guide content design decisions."

It would also be possible, says assistant professor of computer science Dr David Roberts, be used to steer players to relevant content.

"Because it is a data-driven modeling approach, it could be done on a grand scale with minimum input from game designers," he says.

The team analyzed the behavior of 14,000 players in the massively multiplayer online role-playing game (MMORPG) World of Warcraft, evaluating the task-based 'achievement' badges that they earned.

They identified the degree to which each individual achievement was correlated to every other achievement, identifying clusters of linked achievements they called 'cliques', and which could be used to predict later actions.

For example, says the team, if a clique consists of seven achievements, and a player has earned four of them, they will probably earn the other three.

Interestingly, the achievements that form part of the same clique don't necessarily have any obvious connection. For example, an achievement dealing with a character’s prowess in unarmed combat is highly correlated to the achievement badge associated with world travel – even though there's no obvious link.