A Study on the Factors Influencing Rank Prediction in PlayerUnknown’s Battlegrounds

Abstract

This study analyzes the key factors influencing player rank prediction in PlayerUnknown’s Battlegrounds (PUBG), using machine learning models to evaluate in-game performance. By examining variables such as “walkDistance”, “boosts”, and “weaponsAcquired”, the study identifies these as critical predictors, with “walkDistance” emerging as the most significant across all match types. Utilizing models including random forest (RF), gradient descent (GD), extreme gradient boosting (XGBoost), and feedforward neural network (FNN), the analysis reveals performance variation by match type: XGBoost achieves the highest accuracy in solo matches (88.07%), GD performs best in duo matches (84.75%), and RF records the highest accuracy in squad matches (78.21%). These findings provide valuable insights for game developers in balancing gameplay and offer personalized strategic recommendations for players. Future research may enhance predictive performance by incorporating additional variables and exploring alternative models applicable to PUBG and similar battle royale games.