Designing Recommendation Exposure and Favorite Lists: A Field Experiment in a Spot-Work Platform

2026-06-15

AI Summary

This study addresses the inefficiency in job recommendation systems under scenarios of scarce and transient opportunities, where popular job templates are overexposed while those with unmet hiring demand receive insufficient visibility. To tackle this imbalance, the authors propose a Threshold Eligibility Control (TEC) mechanism that dynamically adjusts template exposure based on real-time job posting activity and vacancy capacity, enabling scalable and parallelizable resource reallocation across large platforms. Validated through both simulation calibrated with real-world data and a regional randomized controlled trial, the approach increases per-round job application success rates from 57.6% to 70.0%, significantly boosting effective matches and exposure of active templates, reducing the proportion of low-exposure templates, and improving conversion from user clicks and saves to actual job matches.

Abstract

How should recommender systems be designed when recommendations shape access to scarce, short-lived opportunities? We study this question in a production setting: Timee, Japan's largest platform for spot work, where workers favorite job templates and receive notifications when firms post shifts from those templates. Maximizing predicted favoriting can generate misdirected concentration: recommendations accumulate on popular templates that create few viable job openings, while templates with unmet labor demand receive too little exposure. We design exposure-control mechanisms for favorite-list management, reallocating template exposure based on posting activity and unfilled capacity. The proposed recommender, thresholded eligibility control (TEC), is fully parallelizable and suitable for large-scale digital platforms. In simulations calibrated to Timee data, TEC raises the per-round job-finding rate from 57.6\% to 70.0\%. A prefecture-level randomized field experiment increases realized matches and exposure per active template, reduces the share of low-exposure templates, and improves impression-level favoriting and downstream matching.

Problem

• recommender systems
• exposure control
• spot-work platform
• job matching
• favorite lists

Innovation

• thresholded eligibility control
• exposure allocation
• recommender systems
• field experiment
• labor matching