Neural Networks

Abstract

This chapter will introduce the use of Neural Networks (NN) in game data science. Due to the availability of game data and the increase in computational power, the use of NNs and deep networks is on the rise in data science in general, and specifically within the field of game data science. Complex deep networks are used as they can generalize to highly complex relationships over unseen data and, as a result, provide better performance than traditional models. Such networks have been used to serve many purposes within the game production cycle, including churn predicting, predicting and measuring customer lifetime value, recommending items, as well as discovering and forecasting player behavior patterns. Deep learning has shown good performance and results on these problems. This chapter will detail different types of algorithms used for both Feedforward Neural Networks (FNNs) as well as Convolutional Neural Networks (CNNs). It also includes several case studies and examples of game projects to show the utility of these methods for game design and development. This chapter was written in collaboration with Sabbir Ahmed, a PhD student at Northeastern University.