Distributional treatment effects of content promotion: evidence from an ABEMA field experiment

2026-01-16

Japanese Economic Review

AI Summary

This study investigates the causal effect of top-of-homepage content promotion on user viewing duration, with particular attention to accurately estimating heterogeneous treatment effects under a highly skewed distribution of watch time. Leveraging a large-scale randomized controlled trial conducted on ABEMA, Japan’s leading video streaming platform, this work introduces distributional treatment effects methodology to the streaming context—moving beyond conventional average treatment effect analyses. The findings reveal that top-position promotion significantly increases overall viewing duration, with the most pronounced impact observed for short-form content. Such promotions not only extend immediate user engagement but also stimulate subsequent episode consumption, highlighting nuanced, subgroup-specific benefits of strategic content placement.

Technology Category

• Data Mining & Knowledge Management: Data Stream Mining
• Search and Optimization: Distributed Search
• Machine Learning: Learning Preferences or Rankings

Application Category

• User Modeling, Personalization and Recommendation: Personalized content ranking and presentation
• Web Mining and Content Analysis: Content-based information diffusion
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

We examine the impact of top-of-screen promotions on viewing time at ABEMA, a leading video streaming platform in Japan. To this end, we conduct a large-scale randomized controlled trial. Given the non-standard distribution of user viewing times, we estimate distributional treatment effects. Our estimation results document that spotlighting content through these promotions effectively boosts user engagement across diverse content types. Notably, promoting short content proves most effective in that it not only retains users but also motivates them to watch subsequent episodes.

Problem

• Distributional Treatment Effects
• Content Promotion
• User Engagement
• Viewing Time
• Streaming Platform

Innovation

• distributional treatment effects
• randomized controlled trial
• content promotion
• user engagement
• non-standard distribution