Are microfinance institutions' financial performance gender driven? Evidence from Argentina

Abstract

This paper studies the determinants of financial performance (return on assets, ROA)of 18 Argentine Microfinance Institutions (MFIs) from 2002 to 2018. We apply therandom forest algorithm to predict the ROA of the Argentine MFIs, introducing twosocial variables to capture the depth of the outreach such as the female ratio and theaverage size of the loan portfolio divided by the GDP per capita. We also considerfive other main explanatory variables, such as the size, efficiency, quality of loan port-folio, solvency, and productivity ratio, as well as macroeconomic variables. Althoughour results indicate that the quality of the loan portfolio and efficiency are the mostimportant variables in predicting ROA, we find that social variables are also impor-tant; in particular, the female ratio, which is the third relevant predictor of ROA. Incontrast, macroeconomic variables and the financial crisis turn out to be insignificantin our analysis.