Board Composition and Workplace Diversity : A Machine Learning Approach

We examine the predictive value of board gender diversity on workplace diversity and the relative importance of various board and firm characteristics in predicting diversity. With a novel machine learning approach, we measure three workplace diversity variables using a social media data set of approximately 250,000 employee reviews. Our results show that board composition is an important predictor of workplace diversity, and board gender diversity is the most important predictor of the gender equality and inclusiveness dimensions of corporate diversity culture. However, board gender diversity is not found to have significance in predicting age diversity in a company, and overall, firm characteristics are found to be more critical in explaining age diversity. Furthermore, we find that workplace diversity is an important predictor of firm value, indicating a possible channel on how board gender diversity affects firm performance