Prediction of Factors Influencing Social Performance of Indian MFIs using Machine Learning Approach - Study on SPI and ANN

Aug 4, 2026

Upload by Jiven

The study predicts how microfinance institutions’ (MFIs) internal, institution-specific factors influence the Social Performance Index (SPI) of Indian MFIs using machine learning. SPI is computed from a 10-year panel of 73 Indian MFIs using six operational and outreach-related dimensions, with data sourced from the MIX repository. A pooled OLS regression identifies significant drivers, while an Artificial Neural Network (ANN) model uses all independent variables to forecast SPI, showing improved predictive performance and policy implications for enhancing social impact.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages11

Reading Time28 min

AccessFree to download

Introduction

Microfinance as a social mission

Importance of social performance improvement

Research aim and contribution

Social performance index and factor analysis

ANN-based prediction approach

Prediction ofFactors Influencing Social Performance of Indian MFIs using Machine Learning Approach Ranjeeta Nayak1, Prof. (Dr.) Sasmita Samanta2 1(Ph.D Scholar, School of Humanities and Commerce, KIIT Deemed to be University, Bhubaneswar, 751024, India, Email: [ranjeetanayak25@gmail.com](ranjeetanayak25@gmail.com)) 2 (Professor, School of Humanities and Commerce, KIIT Deemed to be University, Bhubaneswar, 751024, India, Email: [drsasmita@kiit.ac.in](drsasmita@kiit.ac.in)) Abstract The aim of the current work is to predict the impact of MFI specific internal factors on the social performance of Indian microfinance institutions (MFIs) by using machine learning techniques. Social performance index (SPI) is designed by taking data of 73 Indian MFIs for 10 years with the help of an indexing technique where six different factors (operational self sufficiency, number of women borrowers, number of rural borrowers, gross loan portfolio, average loan balance per borrower / GNI per capita and cost per borrower) representing different dimensions of functioning of MFIs are considered. The data is taken from MIX data repository. Pooled OLS regression model is used for analyzing impact of various MFI specific factors on SPI. For predicting the SPI, Artificial Neural Networks (ANN) machine learning model is considered that takes all independent variables as input. The results of regression model indicate that size, legal status, outreach and service provisions significantly affect SPI. ANN analysis result indicates that social performance of MFIs gets determined by MFI specific internal factors. The experimental result indicates that the proposed ANN prediction model is providing better result for predicting the SPI. The findings suggest that MFIs can contribute for development of the society by adopting suitable policies keeping in view certain internal factors. Keywords: Social performance index (SPI), microfinance institutions (MFIs), Social performance management, Artificial Neural Networks (ANN), machine learning model, Prediction. I. INTRODUCTION The growing trend of microfinance industry at global, national as well regional level indicates the significance of microfinance services not only for socioeconomic growth of poor but also for economic development of nation. As social entities, MFIs1 always work for achieving a social mission which can be poverty eradication, women empowerment, educating people, financial empowerment etc. MFIs specifically target low income people to provide them verities of financial products and services with the intention of enabling them to establish their own ventures. These organizations not only aim at financial empowerment of poor but also try for improvement of standard of living. With this noble objective of serving the society, MFIs always need to design efficient techniques for managing their social performance. Social performance of MFIs means extent to which and efficiency with which, MFIs are capable of achieving their mission. It is challenging for these institutions to enhance their social impact (Lyon and Fernandez, 2012; Snigdha, Sasmita and Arpita, 2020) . MFIs need to efficiently convert their inputs into outputs in order to create significant social influence. Proper resources management is very crucial for this reason. 1 MFIs is the abbreviation used for Microfinance Institutions Social performance improves client participation, mutual trust and satisfaction. This results into higher repayment rate and lower transaction cost ensuring financial sustainability of MFIs in long-term. In case of emerging economy like India, there is even more important role played by social institutions like MFIs. Social development contributes towards economic development of the nation. MFIs can play crucial role in eradicating poverty, which will be helpful for social development. Absence of access to financial facility is the main cause for the poor being in poverty (Narwal and Y

FAQs

What does the study aim to predict and how is social performance measured?

It predicts the social performance of Indian MFIs, measured through a Social Performance Index (SPI) constructed from six dimensions using data across 10 years.

Which analytical methods are used to analyze and predict SPI?

The study uses pooled OLS regression to assess the impact of MFI-specific factors on SPI and an Artificial Neural Network (ANN) model to predict SPI from all independent variables.

What key factors are found to significantly affect SPI?

Regression results indicate that size, legal status, outreach, and service provisions significantly influence SPI.

Aug 4, 2026

Upload by Jiven