Sequence Analysis of Game Data

Abstract

This chapter is devoted to sequence game data analysis. It will first define what sequence data is and how it is represented, and then delve more deeply into how to develop models from such data. Sequence analysis has a lot of utility and is important as it conserves the sequence of player actions and can shed light on how players solved different problems within the different game levels. Further, sequence analysis can also be a great way to develop a more robust and accurate player model. The chapter will discuss such advantages in light of showcasing the use of sequential analysis for DOTA 2. Further, the chapter will also be a practical guide on how to develop models from sequence data using practical step-by-step labs. Please note that this chapter was written with Erica Kleinman (a PhD student at University of California at Santa Cruz).