Smart Shopping Algorithm (SSA) to Improve Nutrition
How to cite
Finkelstein, Eric. 2019. "Smart Shopping Algorithm (SSA) to Improve Nutrition." AEA RCT Registry. AEARCTR-0004520. https://doi.org/10.1257/rct.4520-1.0
Download: BibTeX · RIS — for reference managers without a browser translator. Zotero and most others pick up this page's citation metadata directly.
* Primary investigator
Abstract
While there have been efforts to improve the availability and transparency of nutritional information in food products through the provision of Nutritional Fact Panels (NFPs), they might not be immediately useful to the casual shopper.
In most standard-format NFPs, the information provided can be overwhelming and underused by the consumer for various reasons including a lack of time, a lack of nutritional literacy, the lack of a comprehensive denomination, or the unavailability of other baseline information (such as Daily Recommended Intake for different nutrients). This is further confounded when consumers wish to compare between products to make healthier decisions.
The rise in the popularity of online grocery stores is an opportunity to test the effectiveness of comprehensive nutrition tools that can provide consumers with nutritional information in clearer formats that can be better acted upon, overcoming the traditional barriers to healthier food decision-making.
This study seeks to assess the effectiveness of a Smart Shopping Algorithm (SSA) as an add-on to standard web-based grocery stores. The SSA is a suite of features implemented into a web based grocery store with the aim of providing a more convenient and nutrition-focused way of shopping for groceries.
We propose to conduct a two arm cross-over randomized controlled trial (RCT) on an experimental fully functioning web-based grocery store “NUSMart” to assess the effectiveness the SSA. Participants will be randomized into one of two intervention sequences, SSA then control, or control then SSA. In each arm, participants will perform one grocery shopping trip in that version of NUSMart; participants will be required to complete two shops to complete the study. In each shop, the nutritional data of their finalized purchases will be collected.
We hypothesize that diet quality, as measured by weight average Nutri-Score, will be significantly higher in the SSA arm than the control arm. Post-study surveys will collect participants’ experience and feedback for potential future extensions of the SSA.
Intervention
A two-arm cross-over randomized controlled trial (RCT) will be conducted on a web-based grocery store “NUSMart” to assess the effectiveness of an implemented Smart Shopping Algorithm (SSA) on consumers’ diet quality.
The results of this analysis will be complemented with participants’ baseline questionnaire and post-study survey to examine the causal effect of the SSA on food purchase decisions.
Participants will be randomized into one of two intervention sequences: Control condition followed by Intervention condition(SSA), or Intervention condition followed by Control condition.
Participants will be instructed to perform two grocery shopping trips on NUSMart, purchasing a week’s worth of groceries each time.
Data of their finalized purchases will be collected for each shopping trip via their sales orders for subsequent analyses.
Experimental design
For this two-arm cross-over RCT, the experimental web-based grocery store “NUSMart” will be used. NUSMart was designed to mirror an actual web-based grocery store in look and feel. All products include pictures of the item, retail prices and product descriptions.
Participants will only be recruited if they are Singapore residents aged 21 years or older.
Participants will be randomized into one of two intervention sequences: Control condition followed by Intervention condition(SSA), or Intervention condition followed by Control condition.
Participants will be instructed to perform two grocery shopping trips on NUSMart, purchasing a week’s worth of groceries each time.
Data of their finalized purchases will be collected for each shopping trip via their sales orders for subsequent analyses.
Design details
Cited by
No citation data available for this registration yet.