RT Journal Article
T1 Applying wrapper-based variable selection techniques to predict MFIs profitability: evidence from Peru
A1 Fabio Pietrapiana, 
A1 Feria Domínguez, José Manuel
A1 Troncoso, Alicia
K1 Microfinance Institutions (MFIs)
K1 Return on Assets (ROA)
K1 Wrapper Techniques
K1 Random Forest (RF)
K1 K-Nearest Neighbours (KNN)
K1 M5'
K1 Peru
AB In this paper, we analyse the main factors explaining the profitability (ROA) of Microfinance Institutions (MFIs) in Peru from 2011 to 2107. We apply three wrapper techniques to asample of 168 Peruvians MFIs and 69 attributes obtained from MIX Market database. After running the algo-rithms M5ʹ, knearest neighbours (KNN) and Random Forest, we find that the M5ʹ algorithm provides the best fit for predicting ROA. Particularly, the key variable of the regression tree is the percentage of expenses over assets and, depending on its value, it is followed by net income after taxes and before donations, or profit margins
PB Routledge Taylor&Francis
YR 2021
FD 2021-02-15
LK https://hdl.handle.net/10433/19451
UL https://hdl.handle.net/10433/19451
LA en
NO JOURNAL OF DEVELOPMENT EFFECTIVENESS, 2021, VOL. 13, NO. 1, 84–99
NO Departamento de Economía Financiera y Contabilidad
DS RIO
RD May 7, 2026