Applying wrapper-based variable selection techniques to predict MFIs profitability: evidence from Peru. Issue 1 (2nd January 2021)

• Record Type: Journal Article
• Authors: Pietrapiana, Fabio; Feria-Dominguez, José Manuel; Troncoso, Alicia
• Is Part Of: Journal of development effectiveness. Volume 13:Issue 1(2021)
• Page Start: 84
• Page End: 99
• Publication Date: 2021-01-02
• Subjects: Microfinance Institutions (MFIs) -- return on Assets (ROA) -- wrapper Techniques -- random Forest (RF) -- k Nearest Neighbours (KNN) -- m5 -- peru; Economic development -- Periodicals; Developing countries -- Economic conditions -- Periodicals; Economic development; Economic history; Developing countries; Periodicals; 338.91724
• DOI: 10.1080/19439342.2021.1884119
• Languages: English
• ISSNs: 1943-9342

Abstract

ABSTRACT: 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 algorithms 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.