In this paper, we analyse the main factors explaining profitability (ROA) of Microfinance Institutions (MFIs) in Peru from 2011 to 2107. We apply three wrapper techniques asample 168 Peruvians MFIs and 69 attributes obtained MIX Market database. After running algorithms M5?, knearest neighbours (KNN) Random Forest, find that M5? algorithm provides best fit for predicting ROA. Particularly, key ...