Streaming media has become a popular medium for consumers of all ages, with people spending several hours a day streaming videos, games, music, audiobooks or podcasts across devices. Most global streaming services have introduced Generative Artificial Intelligence (GenAI) into their operations to personalize consumer experience, improve content, and further enhance the value proposition of streaming services. Despite the rapid growth, there is a need to bridge the gap between academic research and industry requirements and build connections between researchers and practitioners in the field. This workshop aims to provide a unique forum for practitioners and researchers interested in GenAI to get together, exchange ideas and get a pulse for the state of the art in research and burning issues in the industry.

With proliferation of personal computing devices and large number of logged-in experiences, search has evolved to a stage with many different product scenarios where personalization plays a crucial role for relevance quality and user satisfaction.The purpose of this workshop is have a forum where the latest research and advancements specifically on Personalization and Recommendations in Search (PaRiS) can be discussed in conjunction with KDD 2025.This will be the fourth instance of this workshop.We held three very successful instances of this workshop at the SIGIR 2024 [3], WebConf 2023 [2] and WSDM 2022.This year we will especially focus on applications of LLM and Generative AI to enable personalization and recommendations [1] in the context of search, for example, conversational assistants, while continuing to use this workshop to discuss other advances and applications in the context of personalized search and recommendations in the context of search.

Search and recommendation systems are essential in many services, and they are often developed separately, leading to complex maintenance and technical debt. In this paper, we present a unified deep learning model that efficiently handles key aspects of both tasks.

Long-lived recommender systems (RecSys) often encounter lengthy user-item interaction histories that span many years. To effectively learn long term user preferences, Large RecSys foundation models (FM) need to encode this information in pretraining. Usually, this is done by either generating a long enough sequence length to take all history sequences as input at the cost of large model input dimension or by dropping some parts of the user history to accommodate model size and latency requirements on the production serving side. In this paper, we introduce a sliding window training technique to incorporate long user history sequences during training time without increasing the model input dimension. We show the quantitative & qualitative improvements this technique brings to the RecSys FM in learning user long term preferences. We additionally show that the average quality of items in the catalog learnt in pretraining also improves.

We motivate the need for recommendation systems that can cater to the members’ in-the-moment intent by leveraging their interactions from the current session. We provide an overview of an end-to-end in-session adaptive recommendations system in the context of Netflix Search. We discuss the challenges and potential solutions when developing such a system at production scale.

Personalized recommendations on the Netflix Homepage are based on a user's viewing habits and the behavior of similar users. These recommendations, organized for efficient browsing, enable users to discover the next great video to watch and enjoy without additional input or an explicit expression of their intents or goals. The Netflix Search experience, on the other hand, allows users to take active control of discovering new videos by explicitly expressing their entertainment needs via search queries. In this talk, we discuss the importance of producing search results that go beyond traditional keyword-matches to effectively satisfy users' search needs in the Netflix entertainment setting. Motivated by users' various search intents, we highlight the necessity to improve Search by applying approaches that have historically powered the Homepage. Specifically, we discuss our approach to leverage recommendations in the context of Search and to effectively organize search results to provide a product experience that meaningfully adds value for our users.

We discuss salient challenges of building a search experience for a streaming media service such as Netflix. We provide an overview of the role of recommendations within the search context to aid content discovery and support searches for unavailable (out-of-catalog) entities. We also stress the importance of keystroke-level Instant Search experience, and the technical challenges associated with implementing it across different devices and languages for a global audience.

Today's popular web search engines expand the search process beyond crawled web pages to specialized corpora ("verticals") like images, videos, news, local, sports, finance, shopping etc., each with its own specialized search engine. Search federation deals with problems of the selection of search engines to query and merging of their results into a single result set. Despite a few recent advances, the problem is still very challenging. First, due to the heterogeneous nature of different verticals, how the system merges the vertical results with the web documents to serve the user's information need is still an open problem. Moreover, the scale of the search engine and the increasing number of vertical properties requires a solution which is efficient and scaleable. In this paper, we propose a unified framework for the search federation problem. We model the search federation as a contextual bandit problem. The system uses reward as a proxy for user satisfaction. Given a query, our system predicts the expected reward for each vertical, then organizes the search result page (SERP) in a way which maximizes the total reward. Instead of relying on human judges, our system leverages implicit user feedback to learn the model. The method is efficient to implement and can be applied to verticals of different nature. We have successfully deployed the system to three different markets, and it handles multiple verticals in each market. The system is now serving hundreds of millions of queries live each day, and has improved user metrics considerably.

Supervised learning algorithms usually require high quality labeled training set of large volume. It is often expensive to obtain such labeled examples in every domain of an application. Domain adaptation aims to help in such cases by utilizing data available in related domains. However transferring knowledge from one domain to another is often non trivial due to different data distributions among the domains. Moreover, it is usually very hard to measure and formulate these distribution differences. Hence we introduce a new concept of label-relation function to transfer knowledge among different domains without explicitly formulating the data distribution differences. A novel learning framework, Domain Transfer Risk Minimization (DTRM), is proposed based on this concept. DTRM simultaneously minimizes the empirical risk for the target and the regularized empirical risk for source domain. Under this framework, we further derive a generic algorithm called Domain Adaptation by Label Relation (DALR) that is applicable to various applications in both classification and regression settings. DALR iteratively updates the target hypothesis function and outputs for the source domain until it converges. We provide an in-depth theoretical analysis of DTRM and establish fundamental error bounds. We also experimentally evaluate DALR on the task of ranking search results using real-world data. Our experimental results show that the proposed algorithm effectively and robustly utilizes data from source domains under various conditions: different sizes for source domain data; different noise levels for source domain data, and different difficulty levels for target domain data.

Information generated by multiple authors working independently at different times when analyzed synergistically reveals more information than apparent. For example, a traditional search for connections between the trucking industry and Iraqi banks may not produce any documents mentioning both. However, a search that follows trails of associations across documents may suggest a connection between an auto parts manufacturer who exports to Iraq, and an Iraqi bank providing loans to buy cars. The work described here extends link analysis based on named entities and labeled relationships to general concepts and unnamed associations. Unapparent Information Revelation involves finding chains connecting concepts across documents: it uses a new representation formalism called Concept Chain Graphs.