An Audio-centric Multi-task Learning Framework for Streaming Ads Targeting on Spotify

TL;DR

This paper presents CAMoE, a multi-task learning framework that improves ad click-through rate prediction across audio, video, and display formats on Spotify by leveraging modality-aware techniques and deep feature interactions.

Contribution

The paper introduces CAMoE, a novel multi-task learning framework that effectively integrates multi-modal ad data for improved CTR prediction in streaming platforms.

Findings

Achieved a 14.5% increase in CTR for audio ads.

Improved multi-modal ad performance with near Pareto-optimal results.

Delivered significant CTR gains and cost reductions in large-scale deployment.

Abstract

Spotify, a large-scale multimedia platform, attracts over 675 million monthly active users who collectively consume millions of hours of music, podcasts, audiobooks, and video content. This diverse content consumption pattern introduces unique challenges for computational advertising, which must effectively integrate a variety of ad modalities, including audio, video, and display, within a single user experience. Traditional ad recommendation models, primarily designed for foregrounded experiences, often struggle to reconcile the platform's inherent audio-centrality with the demands of optimizing ad performance across multiple formats and modalities. To overcome these challenges, we introduce Cross-modal Adaptive Mixture-of-Experts (CAMoE), a novel framework for optimizing click-through rate (CTR) prediction in both audio-centric and multi-modal settings. CAMoE enhances traditional mixture-of-experts models by incorporating modality-aware task grouping, adaptive loss masking, and deep-cross networks (DCN) to capture complex feature interactions within a multi-modal ad ecosystem. Through extensive ablation studies, we demonstrate that this approach achieves near Pareto-optimal performance across audio, video, and display ad formats, significantly improving AUC-PR compared to conventional single-task and content-based multi-task learning baselines. When deployed at scale on Spotify's ad serving platform, CAMoE delivered substantial gains, yielding a 14.5% increase in CTR for audio ads, a 1.3% increase for video ads, and a 4.8% reduction in expected cost-per-click (eCPC) for audio slots.