Raising Retail Productivity through Data Pooling: A Mobile Phone App Intervention

How to cite

Shenoy, Ajay; Park, David; Parra, Brenda Samaniego de la; Riley, Emma. 2025. "Raising Retail Productivity through Data Pooling: A Mobile Phone App Intervention." AEA RCT Registry. AEARCTR-0016469. https://doi.org/10.1257/rct.16469-4.0

Download: BibTeX · RIS — for reference managers without a browser translator. Zotero and most others pick up this page's citation metadata directly.

Ajay Shenoy* , David Park , Brenda Samaniego de la Parra , Emma Riley

* Primary investigator

Registry ID
AEARCTR-0016469
DOI
https://doi.org/10.1257/rct.16469-4.0
First registered
Last updated
Status
In development
Trial dates
2026-02-05 – 2026-08-09
Countries
Private
JEL codes
O12; D22; L26; O33
Registry record
http://www.socialscienceregistry.org/trials/16469

Abstract

This study examines whether limited access to high‑quality demand and supplier information constrains the growth of small retailers in developing countries and whether an AI‑driven mobile application that pools sales data across shops can overcome this barrier. It will further test what the returns are to increasing the size of the data pool. One thousand Lusaka‑based retail shops will be randomly assigned in equal proportion to (i) an inventory‑management app only (control); (ii) the app plus lower-priced supplier recommendations generated from data pooled across a relatively small number of similar shops; or iii) the app plus lower-priced supplier recommendations generated from data pooled across a relatively large number of similar shops; or (iv) the app plus product recommendations generated from data on similar shops. Further, within the arm assigned to receive product recommendations, half the stores will receive a buy-back offer to mitigate against the risk of adopting new products that do not sell well. We will followup with the shops 3 times during and immediately after the intervention, and again 3 months later, in order to collect detailed data on adoption of the recommended products and suppliers, weekly sales, and business income. Results will inform policies aimed at supporting SME productivity through digital data‑sharing platforms.

Intervention

Intervention Components:
1. Inventory‑management mobile application (basic logging & analytics)
2. AI-generated supplier recommendations
3. AI‑generated product recommendations

Experimental design

An individually randomised controlled trial with 1,000 shops divided equally across three arms.
Treatment Arms:
T0 (Control) – App only
T1 – App + supplier recommendations from a smaller pool of comparable shops
T2 – App + supplier recommendations from a larger pool of comparable shops
T3 - App + product recommendations from comparable shops

Cross‑Randomisation: Within T3, we will randomise whether stores also receive a buy-back offer, protecting them against the risk of the recommended product not selling well.

All shops receive in‑person onboarding and three weeks of usage incentives to ensure high app engagement.

Design details

Randomization method
Computer randomisation in Stata, using reproducible seed.
Randomization unit
Individual firms
Clusters
1000 firms
Observations
1000 firms
Arms
T0 = 250 firms; T1 = 250 firms; T2 = 250 firms; T3 = 250 firms
Primary outcomes
We will specify our primary and secondary outcomes in a pre-analysis plan, which will be lodged before followup data collection begins. We plan to capture data on the following: Adoption of the recommended product Purchases from the recommended supplier Sales & gross margin of recommended and existing products Total sales revenue Total business income / profit Changes in suppliers or supplier search behaviour Number of customers (footfall) Number of distinct products stocked & inventory turnover Introduction of other new products

Cited by

No citation data available for this registration yet.

Keywords