On Move Pattern Trends in a Large Go Games Corpus

TL;DR

This paper analyzes a large Go game corpus to extract move patterns, identify features linked to player attributes, and develop classifiers, with applications in ranking, study, and AI tuning.

Contribution

It introduces a method for summarizing move patterns in large Go datasets and links these features to player strength and style, enhancing analysis and AI development.

Findings

Significant correlations between move features and player strength.

Effective classifiers for player attributes.

Potential applications in ranking and AI tuning.

Abstract

We process a large corpus of game records of the board game of Go and propose a way of extracting summary information on played moves. We then apply several basic data-mining methods on the summary information to identify the most differentiating features within the summary information, and discuss their correspondence with traditional Go knowledge. We show statistically significant mappings of the features to player attributes such as playing strength or informally perceived "playing style" (e.g. territoriality or aggressivity), describe accurate classifiers for these attributes, and propose applications including seeding real-work ranks of internet players, aiding in Go study and tuning of Go-playing programs, or contribution to Go-theoretical discussion on the scope of "playing style".