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.

On Spotify, multiple recommender systems enable personalized user experiences across a wide range of product features. These systems are owned by different teams and serve different goals, but all of these systems need to explore and learn about new content as it appears on the platform. In this work, we describe ongoing efforts at Spotify to develop an efficient solution to this problem, by centralizing content exploration and providing signals to existing, decentralized recommendation systems (a.k.a. exploitation systems). We take a creator-centric perspective, and argue that this approach can dramatically reduce the time it takes for new content to reach its full potential.

Podcasts are a popular medium for rapid dissemination of information, entertainment, and casual conversations. Content aggregators are taking an increased interest in recommending podcasts to listeners to help them build larger audiences. With many podcasts released every day, many podcasts that would be of interest to listeners remain underserved by these recommendation systems. In this paper, we study variables related to podcast appeal to listeners selected at random in a large online study, in a production setting, involving more than five million recommendations. We present the results of two observational studies, which suggests that underserved podcast have the potential to grow their audiences. To mitigate the rich-get-richer effect, we propose leveraging semantic information, via means of knowledge graphs, to recommend underserved podcasts to listeners. Finally, we conduct empirical experiments that show our method is effective at recommending underserved podcasts, in comparison to baseline methods that rely on listening behavior.

Traditional collaborative filtering (CF) methods suffer from sparse or even cold-start problems, especially for new established recommenders. However, since there are now quite a few recommender systems already existing in good working order, their data should be valuable to the new-start recommenders. This paper proposes shared collaborative filtering approach to leverage the data from other parties (contributor party) to improve own (beneficiary party's) CF performance, and at the same time the privacy of other parties cannot be compromised. Item neighborhood list is chosen as the shared data from the contributor party with considering differential privacy. And an innovative algorithm called neighborhood boosting is proposed to make the beneficiary party leverage the shared data. MovieLens and Netflix data sets are considered as two parties to simulate and evaluate the proposed shared CF approach. The experiment results validate the positive effects of shared CF for increasing the recommendation accuracy of the beneficiary party. Especially when the beneficiary party's data is quite sparse, the performance can be increased by around 10%. The experiments also show that shared CF even outperforms the methods that incorporate the detailed original rating scores of the contributor party without considering the privacy issues. The proposed shared CF approach obtains a win-win situation for both performance and privacy.