Organizational Culture and Financial Performance: A Machine Learning Approach*

Abstract

This study explores the relationship between organizational culture and firm performance by applying a machine learning-based text analysis to a large corpus of employee reviews. Inspired by an intuitive framework of Myers-Briggs Type Indicator personality dimensions, we propose a novel representation of organizational culture using Korean employee narratives from JobPlanet. Using doc2vec, we derive eight continuous culture scores and investigate their associations with firm valuation metrics. The findings suggest that specific culture dimensions, such as extroversion and judging, are significantly related to firm value. Robustness checks using alternative embeddings confirm that the results are not model-specific. We contribute to the growing literature on culture by providing scalable, language-aware methods for quantifying organizational traits in emerging markets.