Reducing SNAP Payment Errors through Predictive Modeling: A Randomized Trial

Last registered on August 10, 2026
View Trial History

Pre-Trial

Trial Information

General Information

Title
Reducing SNAP Payment Errors through Predictive Modeling: A Randomized Trial
RCT ID
AEARCTR-0019325
Initial registration date
August 07, 2026

Initial registration date is when the trial was registered.

It corresponds to when the registration was submitted to the Registry to be reviewed for publication.

First published
August 10, 2026, 4:53 PM EDT

First published corresponds to when the trial was first made public on the Registry after being reviewed.

Locations

There is information in this trial unavailable to the public. Use the button below to request access.

Request Information

Primary Investigator

Name
Anthony Lollo
Affiliation
Yale
Contact Primary Investigator

Other Primary Investigator(s)

PI Name
Jacob Wallace
PI Affiliation
Yale
Contact Investigator

Additional Trial Information

Status
In development
Start date
2026-08-14
End date
2027-03-31
Keywords
Welfare
Additional Keywords
JEL code(s)
Secondary IDs
Prior work
This trial does not extend or rely on any prior RCTs.
Abstract
This study is a two-arm randomized controlled trial that tests whether a predictive model—which incorporates a wide variety of case features—is better able to identify cases at risk for SNAP payment errors than a current rules-based process that primarily selects cases for review based on benefit amount. Over a 4-month period we will randomize approximately 2,500 cases in a 1:1 ratio to: (1) control (business-as-usual case selection process, N=1,250), or (2) treatment (predictive model case selection, N=1,250). After cases are selected by either process, they will go through a standardized Quality Assurance (QA) review in which all information related to income and expenses is reviewed. During this process, errors are corrected which may result in changes to the initial benefit determination. We think cases selected for review by the predictive model will be more likely to have underlying payment errors and will have larger errors. As a result, there will be a larger extent of benefit changes resulting from QA reviews for the cases selected by the predictive model.
External Link(s)

Registration Citation

Citation
Lollo, Anthony and Jacob Wallace. 2026. "Reducing SNAP Payment Errors through Predictive Modeling: A Randomized Trial ." AEA RCT Registry. August 10. https://doi.org/10.1257/rct.19325-1.0
Sponsors & Partners
Experimental Details

Interventions

Intervention(s)
Arm 1: Control
Cases are selected for review using the state’s pre-existing manual “ABC” selection criteria. This selection process prioritizes reviews based on benefit amount, with priority given to cases with benefits > $400, then cases receiving between $200 and $399, and the lowest priority for review given to cases receiving < $200 in benefits. In addition to this benefit prioritization, reviewers are given discretion to select cases if any information pertaining to the top 6 error elements is “questionable or error prone”.

Arm 2: Treatment
Cases will be selected for review based on the model output from predictive models. The models are cross-validated XGboost classifiers that use historic federal SNAP payment error data and state case review data to identify the case characteristics most likely to predict whether a case has a payment error and whether the state’s current review process can fix those errors. Cases will be selected for review based on a composite scoring function which incorporates predictions of both models. Using this composite scoring function, the top 60 cases will be selected for review each week.

Intervention Start Date
2026-08-14
Intervention End Date
2026-12-31

Primary Outcomes

Primary Outcomes (end points)
The total dollar amount of benefits changed per case as a result of the state’s QA review process
Primary Outcomes (explanation)
Calculated as the absolute difference in $ between the benefit allotment at the time of review and the benefit allotment determined as the result of the QA review per case.

Secondary Outcomes

Secondary Outcomes (end points)
Share of cases with any change in benefits after the QA review, Share of cases with any benefit change at or above the federal SNAP PER error threshold (e.g., $58 in FY2026), Total dollar amount of benefits changed per case at or above the federal SNAP PER error threshold (e.g., $58 in FY2026).
Secondary Outcomes (explanation)

Experimental Design

Experimental Design
This study is a two-arm, randomized controlled trial designed to evaluate the effectiveness of different strategies for selecting cases for QA review within Connecticut’s SNAP program. Each week, cases are assigned to each arm in roughly equal proportions (1:1)
Experimental Design Details
Not available
Randomization Method
1. Eligibility Determination: At the beginning of each week, the list of newly certified or recertified cases are identified based on SNAP eligibility and enrollment data within CT eligibility systems.

2. Random Number Generation: Cases are assigned a pseudorandom number using a pseudorandom number generator.

3. Rank and Allocation: Households are sorted by random number. Separately for newly certified cases and for recertified cases, the first half of cases are assigned to Arm 1 (Control), and the second half of cases are assigned to Arm 2 (Treatment).
Randomization Unit
SNAP household (i.e. case)
Was the treatment clustered?
No

Experiment Characteristics

Sample size: planned number of clusters
2500 SNAP households
Sample size: planned number of observations
2500 SNAP households
Sample size (or number of clusters) by treatment arms
1250 SNAP households reviewed in each treatment arm
Minimum detectable effect size for main outcomes (accounting for sample design and clustering)
The study is powered to detect differences in average benefit corrections of $12 (50% relative change) for treatment vs. control or 3.8 percentage points in the share of cases that have any benefit error (30% relative change).
Supporting Documents and Materials
IRB

Institutional Review Boards (IRBs)

IRB Name
Yale Human Research Protection Program Institutional Review Boards
IRB Approval Date
2026-06-08
IRB Approval Number
2000042696
Analysis Plan

There is information in this trial unavailable to the public. Use the button below to request access.

Request Information