Determining Computer Opponent’s Actions in Strategy Game Using K-Nearest Neighbour Algorithm

Main Article Content

Michael Freddy
Teady Matius Surya Mulyana


Advances in computer technology allow various devices to complete complex computing, especially in the entertainment industry and the biggest example is games. Strategy game is the type of game that most often gets an Artificial Intelligence or AI system implemented to imitate human behaviour when playing games. Many game AI systems are predictable so players get bored quickly, so adaptive and simple AI is needed to make it easier for game developers. K-Nearest Neighbour is a classification algorithm with supervised learning, this algorithm will be used in this study. The research method tests the level of accuracy in determining the class by providing a sample of data which is divided into training data and test data. The measure of the level of accuracy is calculated using the confusion matrix after the test table is obtained. The results of the study concluded that the K-Nearest Neighbour algorithm can determine computer opponents fairly well. More data samples are needed as data training to increase the level of classification accuracy.


Download data is not yet available.

Article Details

How to Cite
M. . Freddy and T. M. S. Mulyana, “Determining Computer Opponent’s Actions in Strategy Game Using K-Nearest Neighbour Algorithm”, JuTISI, vol. 8, no. 3, pp. 537 –, Dec. 2022.