|
Field
Last Published
|
Before
January 27, 2026 08:02 AM
|
After
February 07, 2026 12:03 AM
|
|
Field
Experimental Design (Public)
|
Before
This study is a two-arm cluster-randomized controlled trial with geographic areas as clusters.
Prior to rollout, one of two areas (Kanto vs. Kansai–Chubu) was randomly assigned to receive the ECDA recommendation algorithm, while the other continued using the existing algorithm.
The primary estimand is the intention-to-treat (ITT) effect of ECDA on pre-specified marketplace outcomes during the intervention window.
The experiment runs for two weeks and we track post-treatment activity to obtain post-engagement data. The primary outcome measures include:
- Total Number of Dates (efficiency metric)
- Unique Dating Users (equity metric)
- Proposer and Receiver Gini Index (inequality metric)
- User Engagement Activity (retention measure)
- Total Number of Effective Users (post engagement effectiveness)
The estimation identifies the impact of the ECDA algorithm by comparing pre- and post-intervention differences between treatment and control groups, with market-specific fixed effects controlling for baseline differences.
|
After
This study is a two-arm cluster-randomized controlled trial with geographic areas as clusters.
Prior to rollout, one of two areas (Kanto vs. Kansai–Tokai) was randomly assigned to receive the ECDA recommendation algorithm, while the other continued using the existing algorithm.
The primary estimand is the intention-to-treat (ITT) effect of ECDA on pre-specified marketplace outcomes during the intervention window.
The experiment runs for two weeks and we track post-treatment activity to obtain post-engagement data. The primary outcome measures include:
- Total Number of Dates (efficiency metric)
- Unique Dating Users (equity metric)
- Proposer and Receiver Gini Index (inequality metric)
- User Engagement Activity (retention measure)
- Total Number of Effective Users (post engagement effectiveness)
The estimation identifies the impact of the ECDA algorithm by comparing pre- and post-intervention differences between treatment and control groups, with market-specific fixed effects controlling for baseline differences.
|
|
Field
Randomization Method
|
Before
Simple random assignment (1:1) at the geographic area (cluster) level. Unit of randomization is the geographic market/area. Prior to the intervention start date, we randomly assigned treatment status across the two areas (Kanto vs. Kansai–Chubu) using a computer-generated random number. The randomization was implemented by a member of the research team using a computer-generated random number prior to the intervention. The unit of randomization is the geographic market (area). One area (1 cluster) was assigned to treatment (ECDA deployed) and the other area (1 cluster) to control (status quo algorithm). No within-area randomization is used due to interference/spillovers among users within the same market.
|
After
Simple random assignment (1:1) at the geographic area (cluster) level. Unit of randomization is the geographic market/area. Prior to the intervention start date, we randomly assigned treatment status across the two areas (Kanto vs. Kansai–Tokai) using a computer-generated random number. The randomization was implemented by a member of the research team using a computer-generated random number prior to the intervention. The unit of randomization is the geographic market (area). One area (1 cluster) was assigned to treatment (ECDA deployed) and the other area (1 cluster) to control (status quo algorithm). No within-area randomization is used due to interference/spillovers among users within the same market.
|
|
Field
Randomization Unit
|
Before
Areas (e.g., Kanto and Kansai-Chubu)
|
After
Areas (e.g., Kanto and Kansai-Tokai)
|
|
Field
Intervention (Hidden)
|
Before
The ECDA algorithm is designed to enhance matching efficiency while reducing concentration in highly active and attractive users. It does so by incorporating user preference intensity and platform constraints into the recommendation mechanism. Male users act as proposers in the system, while female users remain passive recipients of recommendations. The intervention runs for two months, during which the treatment group (Kanto area) receives ECDA-based recommendations, and control groups (Kansai-Chubu area) continue receiving recommendations based on the platform’s pre-existing system. We collect data on user engagement, total number of matches, unique dating users, total number of effective users, and inequality metrics such as the Gini Index for proposers and receivers.
|
After
The ECDA algorithm is designed to enhance matching efficiency while reducing concentration in highly active and attractive users. It does so by incorporating user preference intensity and platform constraints into the recommendation mechanism. Male users act as proposers in the system, while female users remain passive recipients of recommendations. The intervention runs for two months, during which the treatment group (Kanto area) receives ECDA-based recommendations, and control groups (Kansai-Tokai area) continue receiving recommendations based on the platform’s pre-existing system. We collect data on user engagement, total number of matches, unique dating users, total number of effective users, and inequality metrics such as the Gini Index for proposers and receivers.
|