Improving Micro-Finance Productivity through Data Analysis

Ryan David Taylor

Abstract

After nearly three months of gathering, creating, organizing, and analyzing data from social entrepreneurship programs in Peru and Ghana, correlations have been found within the data which may be used in the pursuit to eliminate poverty around the globe. These correlations were found through completing both linear relationship analyses and multi-variable regression analyses. The most statistically significant factors when looking at correlational relationships with number of missed and late payments were APR, loan duration, loan date (year fraction), gender or principle loan participant, and participation in incentive programs. The most poignant of these variables in terms of statistical significance was participation in incentive programs. This information, assuming the continued cooperation of social entrepreneurship and economic development firms, will be used to initiate controlled research studies in which it might be determined whether the factors of correlational significance also hold causational value. If so, programs may be developed as a result of the studies that will help improve social entrepreneurship programs and eventually eradicate cases of deep poverty.