Selecting explanatory factors of voting decisions by means of fsQCA and ANN

This investigation applies fuzzy-set qualitative comparative analysis (fsQCA) and an artificial neural networks method (ANN) with the aim of addressing the determinants of votes regarding managerial proposals presented in corporate meetings. The data refer to companies in the United States banking industry and they cover the period from 2003 to 2013. The results show that the variables that contribute to explain the voting support have changed over time. Thus, during the 2003–2006 sub-period the number of funds voting appears as the most clearly outstanding variable. On the contrary, in the 2007–2009 sub-period there is a heterogeneous set of explanatory features that includes the total volume of assets, the leverage ratio and the return on assets ratio, among others, as the most remarkable factors. Finally, in the 2010–2013 sub-period, there are no specific features or combinations that contribute to voting support, indicating that the explanatory factors are yet to be consolidated after the financial downturn.