Predicting Individual Brand Value Using a Random Forest Model: A Data-Driven Approach to Organizational Influence

Individual brand value has become a strategic asset in contemporary organizations, yet existing research has predominantly relied on linear models to explain its formation. Such approaches assume additive and proportional effects, potentially oversimplifying the complex and contingent nature of brand development. This study introduces a Random Forest framework to examine how organizational structure, market positioning, and social–cultural context jointly shape individual brand value. Using survey data from 318 participants, the predictive performance of the Random Forest model is compared with that of a traditional multiple linear regression model. The results show that the Random Forest model achieves substantially higher explanatory power (R² = 0.72) than the linear benchmark (R² = 0.54), indicating that non-linear relationships and higher-order interactions play a central role in brand formation. Permutation-based importance analysis reveals a hierarchical pattern in which market positioning variables, particularly visibility and differentiation, exert the strongest influence, followed by organizational structure and social–cultural context. These findings suggest that individual brand value is not the linear accumulation of internal attributes but an emergent outcome of externally visible differentiation, conditionally enabled by organizational arrangements and socially interpreted within cultural environments. Methodologically, the study demonstrates how machine learning can complement theory-driven models by uncovering structural regularities that remain invisible under linear assumptions. The results call for a pluralistic analytical approach capable of aligning empirical methods with the complexity of organizational life.