Misperceptions and product choice: evidence from a randomised trial in Zambia

Do misperceptions deter small retailers from stocking profitable products?

Abstract

The authors apply unsupervised machine learning to the inventories of 2000 shops in Lusaka, Zambia, to identify clusters of similar retailers and flag a “target” product, one stocked by some but not all shops in a cluster.

This paper is part of the Private Enterprise Development in Low-Income Countries (PEDL) programme.

Citation

Bai J and others. ‘Misperceptions and product choice: evidence from a randomised trial in Zambia’ PEDL Working Paper, 2025

Misperceptions and product choice: evidence from a randomised trial in Zambia

Updates to this page

Published 24 October 2025