A Machine Learning Approach for Micro-Credit Scoring

In micro-lending markets, lack of recorded credit history is a significant impediment to assessing individual borrowers’ creditworthiness and therefore deciding fair interest rates. This research compares various machine learning algorithms on real data test their efficacy at classifying borrowers into categories. We demonstrate that off-the-shelf multi-class classifiers such as random forest can perform this task very well, using readily available about customers (such age, occupation, location). presents inexpensive reliable means institutions around the developing world with which assess in absence or central databases.