Cold-Starting Podcast Ads and Promotions with Multi-Task Learning on Spotify

• URL: http://arxiv.org/abs/2601.02306v1
• Date: Mon, 05 Jan 2026 17:48:15 GMT
• Title: Cold-Starting Podcast Ads and Promotions with Multi-Task Learning on Spotify
• Authors: Shivam Verma, Hannes Karlbom, Yu Zhao, Nick Topping, Vivian Chen, Kieran Stanley, Bharath Rengarajan,
• Abstract summary: We present a unified multi-objective model for targeting both advertisements and promotions within the Spotify podcast ecosystem.<n>Online A/B tests show up to a 22% reduction in effective Cost-Per-Stream.<n>Our experience shows that a unified modeling strategy improves maintainability, cold-start performance, and coverage.
• Score: 2.204478225790133
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present a unified multi-objective model for targeting both advertisements and promotions within the Spotify podcast ecosystem. Our approach addresses key challenges in personalization and cold-start initialization, particularly for new advertising objectives. By leveraging transfer learning from large-scale ad and content interactions within a multi-task learning (MTL) framework, a single joint model can be fine-tuned or directly applied to new or low-data targeting tasks, including in-app promotions. This multi-objective design jointly optimizes podcast outcomes such as streams, clicks, and follows for both ads and promotions using a shared representation over user, content, context, and creative features, effectively supporting diverse business goals while improving user experience. Online A/B tests show up to a 22% reduction in effective Cost-Per-Stream (eCPS), particularly for less-streamed podcasts, and an 18-24% increase in podcast stream rates. Offline experiments and ablations highlight the contribution of ancillary objectives and feature groups to cold-start performance. Our experience shows that a unified modeling strategy improves maintainability, cold-start performance, and coverage, while breaking down historically siloed targeting pipelines. We discuss practical trade-offs of such joint models in a real-world advertising system.

Related papers

• Practice on Long Behavior Sequence Modeling in Tencent Advertising [75.65309022911994]
  Long-sequence modeling has become an indispensable frontier in recommendation systems for capturing users' long-term preferences.<n>We propose several practical approaches within the two-stage framework for long-sequence modeling.<n> Deployed in production on Tencent's large-scale advertising platforms, our innovations delivered significant performance gains.
  arXiv  Detail & Related papers  (2025-09-10T06:55:57Z)
• SUMMA: A Multimodal Large Language Model for Advertisement Summarization [15.514886325064792]
  We propose SUMMA, a model that processes video ads into summaries highlighting the content of highest commercial value.<n> SUMMA is developed via a two-stage training strategy-multimodal supervised fine-tuning followed by reinforcement learning.<n>Online experiments show a statistically significant 1.5% increase in advertising revenue.
  arXiv  Detail & Related papers  (2025-08-28T09:19:53Z)
• Multi-task Offline Reinforcement Learning for Online Advertising in Recommender Systems [54.709976343045824]
  Current offline reinforcement learning (RL) methods face substantial challenges when applied to sparse advertising scenarios.<n>We propose MTORL, a novel multi-task offline RL model that targets two key objectives.<n>We employ multi-task learning to decode actions and rewards, simultaneously addressing channel recommendation and budget allocation.
  arXiv  Detail & Related papers  (2025-06-29T05:05:13Z)
• An Audio-centric Multi-task Learning Framework for Streaming Ads Targeting on Spotify [0.0]
  Spotify attracts over 675 million monthly active users who collectively consume millions of hours of music, podcasts, audiobooks, and video content.<n>This diverse content consumption pattern introduces unique challenges for computational advertising.<n>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.
  arXiv  Detail & Related papers  (2025-06-23T15:11:43Z)
• CTR-Driven Advertising Image Generation with Multimodal Large Language Models [53.40005544344148]
  We explore the use of Multimodal Large Language Models (MLLMs) for generating advertising images by optimizing for Click-Through Rate (CTR) as the primary objective.<n>To further improve the CTR of generated images, we propose a novel reward model to fine-tune pre-trained MLLMs through Reinforcement Learning (RL)<n>Our method achieves state-of-the-art performance in both online and offline metrics.
  arXiv  Detail & Related papers  (2025-02-05T09:06:02Z)
• Contextual Bandits for Advertising Campaigns: A Diffusion-Model Independent Approach (Extended Version) [73.59962178534361]
  We study an influence problem in which little is assumed to be known about the diffusion network or about the model that determines how information may propagate. In this setting, an explore-exploit approach could be used to learn the key underlying diffusion parameters, while running the campaign. We describe and compare two methods of contextual multi-armed bandits, with upper-confidence bounds on the remaining potential of influencers.
  arXiv  Detail & Related papers  (2022-01-13T22:06:10Z)
• CAMTA: Causal Attention Model for Multi-touch Attribution [25.258282793367453]
  We propose CAMTA, a novel deep recurrent neural network architecture which is a casual attribution mechanism for user-personalised MTA. We demonstrate the superior performance of CAMTA with respect to prediction accuracy as compared to several baselines.
  arXiv  Detail & Related papers  (2020-12-21T15:05:00Z)
• Dynamic Knapsack Optimization Towards Efficient Multi-Channel Sequential Advertising [52.3825928886714]
  We formulate the sequential advertising strategy optimization as a dynamic knapsack problem. We propose a theoretically guaranteed bilevel optimization framework, which significantly reduces the solution space of the original optimization space. To improve the exploration efficiency of reinforcement learning, we also devise an effective action space reduction approach.
  arXiv  Detail & Related papers  (2020-06-29T18:50:35Z)
• MoTiAC: Multi-Objective Actor-Critics for Real-Time Bidding [47.555870679348416]
  We propose a Multi-ecTive Actor-Critics algorithm named MoTiAC for the problem of bidding optimization with various goals. Unlike previous RL models, the proposed MoTiAC can simultaneously fulfill multi-objective tasks in complicated bidding environments.
  arXiv  Detail & Related papers  (2020-02-18T07:16:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.