Are you a Hunter or Camper? A phase-based framework for real-time survival prediction in battle royale using FightScore and ActiveScore

The battle royale genre game’s primary goal is survival. Similarly, the goal of the PlayerUnknown’s Battlegrounds (PUBG), a representative battle royale game, is to be the last man standing in a shrinking zone. Thus, game strategy for survival is the most important part in winning. The game play progress is divided into distinct game phases with Aggressiveness and Activeness as key attributes. Players change their strategy by the game phase. To capture this dynamic, we propose introducing scores. In this study, we analyze phase-specific survival strategies in PUBG from the perspectives of Aggressiveness and Activeness, and predicts player survival in real-time. Using in-game features that reflect Aggressiveness and Activeness, we calculate scores, “FightScore” and “ActiveScore” , to cluster players into four strategic types: Hunter, Sniper, Traveler, and Camper. Unlike existing methods that rely on post-game statistics, we use phase-specific data to derive strategies to predict survival and optimize strategies for the subsequent phases. We evaluate the effectiveness of three machine learning models, Random Forest, Logistic Regression, and XGBoost, to predict survival and win. We focus on the relationship between phase-specific strategy and survival in PUBG, which can be informative for players, e-sports analysts, and broadcasters.