Adaptive Recommendation Quotas Adaptive Recommendation Quotas for Gig Economy Platforms

Last registered on January 23, 2026
View Trial History

Pre-Trial

Trial Information

General Information

Title
Adaptive Recommendation Quotas Adaptive Recommendation Quotas for Gig Economy Platforms
RCT ID
AEARCTR-0017620
Initial registration date
January 11, 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
January 23, 2026, 7:31 AM EST

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
Suguru Otani
Affiliation
Graduate School of Economics, The University of Tokyo, Market Design Center
Contact Primary Investigator

Other Primary Investigator(s)

PI Name
Shunya Noda
PI Affiliation
Graduate School of Economics, The University of Tokyo
Contact Investigator
PI Name
Kazuki Sekiya
PI Affiliation
Graduate School of Economics, The University of Tokyo
Contact Investigator
PI Name
Yuki Komatsu
PI Affiliation
Department of Economics, The University of Tokyo
Contact Investigator
PI Name
Yuki Fujii
PI Affiliation
Timee, Inc.
Contact Investigator
PI Name
Shunsuke Ozeki
PI Affiliation
Timee, Inc.
Contact Investigator

Additional Trial Information

Status
In development
Start date
2026-01-12
End date
2026-05-31
Keywords
Labor
Additional Keywords
gig work, platform design, recommendation algorithm
JEL code(s)
Secondary IDs
Prior work
This trial does not extend or rely on any prior RCTs.
Abstract
This paper studies recommender systems as mechanisms for allocating exposure of items to users, and asks how we can design exposure allocation to achieve more efficient and more equitable matching outcomes. We analyze this problem in the context of Timee, Japan's largest spot-work platform, where workers favorite job templates to receive notifications when offerings are posted. In this environment, we show that conventional recommender systems optimized for conversion metrics such as clicks or favoriting probabilities generate misdirected concentration: they over-recommend job templates that are popular among workers but have limited labor demand and may not lead to employment opportunities. To address this problem, we propose quota-based exposure control mechanisms, including an adaptive quota rule that responds to posting activity and unfilled capacity, as well as a fully parallelizable \emph{Thresholded Exposure Control} (TEC) algorithm suitable for large-scale deployment. In simulations calibrated to 2024 Hokkaido data, job fulfillment rates increase from 57.0\% under a greedy recommender to 63.7\% with static quotas and to 70.6\% with TEC.
External Link(s)

Registration Citation

Citation
Fujii, Yuki et al. 2026. "Adaptive Recommendation Quotas Adaptive Recommendation Quotas for Gig Economy Platforms." AEA RCT Registry. January 23. https://doi.org/10.1257/rct.17620-1.0
Sponsors & Partners

Partner

Name
Timee, Inc.
Type
private_company
URL
https://corp.timee.co.jp/
Experimental Details

Interventions

Intervention(s)
We experimentally evaluate a recommender algorithm that adaptively allocates exposure across job templates on Japan’s largest spot-work platform, Timee. The treatment prefecture (Aomori) received the proposed Thresholded Exposure Control (TEC) recommender as default in the “template recommendation” tab, while the control prefecture (Iwate) continued using the baseline Greedy recommender optimized for favoriting probabilities. The intervention ran from January 12 to February 11, 2026.
Intervention Start Date
2026-01-12
Intervention End Date
2026-02-11

Primary Outcomes

Primary Outcomes (end points)
Average recommended workers per template (daily, prefecture × day).
Subscribers per template (unique workers who favorited the template).
Fulfillment rate — confirmed matches divided by posted offering capacity within each prefecture per day.
Impression-level choice about favorite and application via favorite lists.
Primary Outcomes (explanation)
Average recommended workers per template = mean number of unique users exposed to each firm template per day.
Subscribers per template = count of unique workers who add a template to their favorite list on that day.
Fulfillment rate = number of filled offerings / total posted offering capacity within a prefecture on that day.
All outcomes are aggregated to the prefecture × day level and measured consistently across treatment and control regions.
Impression-level choice captures user's binary action about whether he selects the displayed offer in his favorite list or apply for it.

Secondary Outcomes

Secondary Outcomes (end points)
Secondary Outcomes (explanation)

Experimental Design

Experimental Design
This is a cluster-randomized controlled trial with prefectures as clusters. Prior to deployment, we randomly assigned Aomori and Iwate 1:1 to treatment (TEC) and control (Greedy) using a reproducible script with a fixed seed; the assignment log (timestamp, seed, and code) is archived. We run a prefecture-level, two-arm cluster RCT on Timee to evaluate an exposure-aware recommender. Aomori is assigned to treatment (TEC recommender as default in the template-recommendation tab); Iwate serves as control (status-quo greedy recommender). Outcomes are observed daily at the prefecture level and mirror the simulation targets: (i) average recommended workers per template, (ii) subscribers per template, and (iii) fulfillment rate (confirmed offerings / posted capacity). Effects are estimated via difference-in-differences with prefecture and date fixed effects; the prefecture-level rollout is chosen to mitigate interference in a shared marketplace. Also, we examine the effects on impression-level choice.
Experimental Design Details
Not available
Randomization Method
Simple random assignment (1:1) at the prefecture (cluster) level, implemented via reproducible code with a fixed random seed and archived assignment record.
Randomization Unit
Prefecture (cluster).
Was the treatment clustered?
Yes

Experiment Characteristics

Sample size: planned number of clusters
2 (1 treatment, 1 control).
Sample size: planned number of observations
1500 active users for treatment (Aomori prefecture) based on the number of active users on the channel (1544) in November 2025. 1500 active users for control (Iwate prefecture) based on the number of active users on the channel (1502) in November 2025.
Sample size (or number of clusters) by treatment arms
1 prefecture for treatment
1 prefecture for control
Minimum detectable effect size for main outcomes (accounting for sample design and clustering)
Supporting Documents and Materials

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

Request Information
IRB

Institutional Review Boards (IRBs)

IRB Name
The Office for Life Science Research Ethics and Safety at the University of Tokyo
IRB Approval Date
2025-11-07
IRB Approval Number
E25ALS0256
Analysis Plan