Big Loans to Small Businesses: Predicting Winners and Losers in an Entrepreneurial Lending Experiment

Working Paper
Published on 1 May 2022

A previous version of this paper was published 20 September 2021.


We experimentally study the impact of substantially larger enterprise loans in Egypt. Larger loans generate small average impacts, but machine learning using psychometric data reveals that ”top-performers” (those with the highest predicted treatment effects) substantially increase profits, while profits drop for poor-performers. The large differences imply that lender credit allocation decisions matter for aggregate income, yet we find that existing practice leads to substantial misallocation. We argue that some entrepreneurs are over-optimistic and squander the opportunities presented by larger loans by taking on too much risk, and show the promise of allocations based on entrepreneurial type relative to firm characteristics.


Gharad Bryan

London School of Economics

Dean Karlan

Northwestern University

Adam Osman

University of Illinois at Urbana Champaign