Estimation of game addiction in children plays a major role in the mental and physical development of the child. Therefore, Various scales are used to examine game addiction of children and various input parameters (Age, Gender, Daily play time, etc.) are employed in scales. The purpose of this study is to project a system that estimates whether the child is addicted to the game when looking at the input parameters. Artificial Neural Networks (ANN) and Multiple Linear Regression (MLR) techniques were used to design this system. In order to measure the predictive performance of the developed models, the Root Mean Squared Error (RMSE), and Correlation Coefficient (R) criteria were examined respectively and it was observed that the model developed by ANN predicted CGA with high accuracy.