A Quantitative Analysis of Economic Strategy and Its Influence on Final Ranking in Magic Chess Game Using Machine Learning

Abstract

Economic management is a fundamental strategic pillar in auto-battler games such as Magic Chess, but its quantitative impact on player performance has not been extensively studied. This research aims to empirically measure the predictive ability of economic variables on players' final rankings. We analyzed a dataset consisting of 57 match records from players at the ‘Grandmaster’ ranking level. Two modeling approaches, Multiple Linear Regression and Random Forest, were used to predict players' final rankings (values 1–8) based on three primary economic features: total gold spent, re-roll frequency, and average economic bonus. The results from the Linear Regression model showed a Mean Squared Error (MSE) of 0.5496. However, the most significant finding was the R-squared value, which was only 0.016. This extremely low R-squared value indicates that the economic variables analyzed could only explain 1.6% of the total variance in players' final rankings. The conclusion of this study is that economic metrics alone are insufficient to build a reliable model for accurately predicting final rankings. This strongly suggests that other strategic factors, such as synergy composition, item allocation, and tactical decisions on the game board, have a far more dominant influence in determining a player's success in high-level Magic Chess.