A variable impact neural network analysis of dividend policies and share prices of transportation and related companies

► We investigate dividend policy, including its impact on share prices of transportation providers. ► We harness mutually supportive techniques namely generalized regression neural network and conventional regression. ► Our results using regressions reveal that for Europe and for the US and Canada the market-to-book-value has a significant negative association with dividend yields. ► Neural network analysis indicates a prominent role for growth opportunities for the US and Canada. ► Risk is rewarded especially in Europe.