Evaluating Go Game Records for Prediction of Player Attributes

TL;DR

This paper introduces a method to analyze Go game records by extracting move evaluations to predict player attributes like strength and style, aiding in player assessment and AI tuning.

Contribution

It presents a novel approach to extract and aggregate move evaluations from game records for predicting player attributes using machine learning.

Findings

Accurately predicts player strength and style

Effective for Go study and AI tuning

Potential for ranking internet players

Abstract

We propose a way of extracting and aggregating per-move evaluations from sets of Go game records. The evaluations capture different aspects of the games such as played patterns or statistic of sente/gote sequences. Using machine learning algorithms, the evaluations can be utilized to predict different relevant target variables. We apply this methodology to predict the strength and playing style of the player (e.g. territoriality or aggressivity) with good accuracy. We propose a number of possible applications including aiding in Go study, seeding real-work ranks of internet players or tuning of Go-playing programs.