As we come to the end of this course, we hope we have been able to gain more knowledge about the game data science process to help us start exploring, analyzing, and extracting actionable insights from game data. In this chapter, we’ll summarize the different parts of the game data science process we introduced in the introduction chapter. We’ll then share some notes and words of hard-earned experience when embarking on using the methods discussed in this course. Furthermore, we’ll discuss the topic of ethics, as it’s an important topic when we deal with player data. We’ll then introduce some issues that we didn’t address in this course, including how to deal with distributed big data, how to build bots from game data, how to use probabilistic models, and what are the overall applications of game data science within the production process.

In conclusion, this course should only be the beginning of our journey. There will always be new algorithms and methods developed that we can try with our game data. Always be on the lookout for these new methodologies. Hopefully, the course gave enough of a foundation to allow us to explore and understand more advanced techniques proposed and discussed within the games industry and academic research.

Summary of the game data science process

The course focuses on several stages of game data science discussed in the Introduction chapter. As we start with any data, remember data preprocessing (discussed in preprocessing) is an important first step to cleaning and preparing our data for analysis. It is a tedious process but an important one.

Get hands-on with 1200+ tech skills courses.