<![CDATA[Balancing updates (buffs and nerfs) are essential in Multiplayer Online Battle Arena games because minor parameter changes can shift the competitive metagame and reduce hero diversity. Unlike previous studies on Dota 2 that focus on match outcome prediction, this study introduces and evaluates hero-centric balance recommendations against official patch actions across patch transitions. To address this gap, this work contributes a patch-to-patch (Version 7.39-7.40b) external validation protocol that compares recommendations from patch t with developer actions in patch t+1 using patch notes. Professional match records were gathered from public sources and sorted by hero and patch into combat, economic, and impact categories. This study proposed a data-driven pipeline to classify each Dota 2 hero as overpowered, underpowered, or balanced from professional match telemetry and to translate these classes into balance recommendations (Nerf, Buff, or Balance). Labels derive from win-rate and pick-rate distributions using statistical control limits (μ ± kσ, k = 0.3) to ensure transparent, repeatable labeling. A Random Forest classifier was trained using grid-searched hyperparameters and evaluated using stratified 6-fold cross-validation with macro-averaged F1 to address class imbalance. Internal evaluation achieved 0.94 accuracy and 0.84 macro-F1. For external validation, patch t recommendations were compared to official balance actions in patch t+1 during six successive transitions; accuracy ranged from 0.436 to 0.672 (mean 0.559), with the best result on 7.39b to 7.39c (84/125). These results indicated that professional telemetry could support interpretable balance monitoring and provide early signals for buff/nerf candidate review.]]>
