EDEdoardo D'AMico

Edoardo D'AMico

*This is an algorithmically generated author record based on publicly available information.

Edoardo D'AMico has a total of 59 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A Unified Model for Personalization: Language-Steerable Generative Recommendation, Search, and User Understanding

    by Marco De Nadai, Edoardo D'AMico, Max Lefarov, Alexandre Tamborrino, Divita Vohra, Mark VanMiddlesworth, Shawn Lin, Jacqueline Wood, Jan Stypka, Eliza Klyce, et al.

    Large language models (LLMs) are increasingly applied to recommendation, retrieval, and reasoning, yet deploying a single end-to-end model that can jointly support these behaviors over large, heterogeneous catalogs remains challenging. Such systems must generate unambiguous references to real items, handle multiple entity types, and operate under strict latency and reliability constraints requirements that are difficult to satisfy with text-only generation. While tool-augmented recommender systems address parts of this problem, they introduce orchestration complexity and limit end-to-end optimization. We view this setting as an instance of a broader research problem: how to adapt LLMs to reason jointly over multiple-domain entities, user behavior, and language in a fully self-contained manner. To this end, we introduce NEO, a framework that adapts a pre-trained decoder-only LLM into a tool-free, catalog-grounded generator. NEO represents items using semantic identifiers (SIDs) and trains a single model to interleave natural language and typed item identifiers within a shared sequence. Natural-language prompts control the task, target entity type, and output format (IDs, text, or mixed), while constrained decoding guarantees catalog-valid item generation without restricting free-form text. We refer to this instruction-conditioned controllability as language-steerability. Inspired by multimodal alignment, we treat SIDs as a distinct modality and study design choices for integrating discrete entity representations into LLMs via staged alignment and instruction tuning. We evaluate NEO at scale on a real-world catalog of over 10M items across multiple media types and discovery tasks, including recommendation, search, and user understanding. In offline experiments, NEO consistently outperforms strong task-specific baselines and exhibits positive cross-task transfer, demonstrating a practical path toward consolidating large-scale discovery capabilities into a single language-steerable generative model.

  • Open Access

    From Habits to Discovery: Deploying LLMs for Personalized Generative Recommendations at Spotify

    by Edoardo D'AMico, Marco De Nadai, Praveen Chandar, Divita Vohra, Shawn Lin, Max Lefarov, Paul Gigioli, Gustavo Penha, Ilya Kopysitsky, Ivo Joel Senese, et al.

    Podcast listening is often grounded in a set of favorite shows, while listener intent can evolve over time. This combination of stable preferences and changing intent motivates recommendation approaches that support both familiarity and exploration. Traditional recommender systems typically emphasize long-term interaction patterns, and are less explicitly designed to incorporate rich contextual signals or flexible, intent-aware discovery objectives. In this setting, models that can jointly reason over semantics, context, and user state offer a promising direction. Large Language Models (LLMs) provide strong semantic reasoning and contextual conditioning for discovery-oriented recommendation, but deploying them in production introduces challenges in catalog grounding, user-level personalization, and latency-critical serving. We address these challenges with GLIDE, a production-scale generative recommender for podcast discovery at Spotify. GLIDE formulates recommendation as an instruction-following task over a discretized catalog using Semantic IDs, enabling grounded generation over a large inventory. The model conditions on recent listening history and lightweight user context, while injecting long-term user embeddings as soft prompts to capture stable preferences under strict inference constraints. We evaluate GLIDE using offline retrieval metrics, human judgments, and LLM-based evaluation, and validate its impact through large-scale online A/B testing. Across experiments involving millions of users, GLIDE increases non-habitual podcast streaming on Spotify home surface by up to 5.4% and new-show discovery by up to 14.3%, while meeting production cost and latency constraints.


  • Open Access

    Don't Get Bored: Enhancing Scalability and Diversity in Session-Based Slate Recommendation

    by Aayush Singha Roy, Edoardo D'AMico, Elias Tragos, Aonghus Lawlor, Neil Hurley

    Reinforcement learning (RL) has demonstrated great potential to improve slate-based recommender systems by optimizing long-term user engagement. However, addressing the combinatorial action space in slate recommendations remains challenging. Recent work decomposes slate Q-values into item-wise Q-values, improving the tractability of value-based methods to learn the model. But in scenarios with a large item pool and a resource-intensive value function like deep neural networks, the action selection process still incurs substantial computational costs. Slow training might be tolerable, but high costs during action selection could hinder real-time deployment. To address this issue, this paper introduces an actor method that reduces Q-function evaluations to a subset of items, significantly cutting inference time for practical deployment. The research suggests acquiring representations at both item and slate levels, strategically identifying a specific item subset for slate composition. The proposed methodologies are assessed over different simulated user engagement behaviors: users certain about preferences (“decisive” behavior) and those more exploratory or bored users, losing interest with repetitive content exposure (“explorative” behavior). Empirical evaluation shows that the proposed approach achieves comparable user engagement with a value-based policy across behaviors. Meanwhile, it notably enhances serving time while recommending diverse topic slates, thus demonstrating its potential effectiveness and efficiency in real-world applications.


  • Open Access

    Rs4rs: Semantically Find Recent Publications from Top Recommendation System-Related Venues

    by Tri Kurniawan Wijaya, Edoardo D'AMico, Gabor Fodor, Manuel V. Loureiro

    Rs4rs is a web application designed to perform semantic search on recent papers from top conferences and journals related to Recommender Systems. Current scholarly search engine tools like Google Scholar, Semantic Scholar, and ResearchGate often yield broad results that fail to target the most relevant high-quality publications. Moreover, manually visiting individual conference and journal websites is a time-consuming process that primarily supports only syntactic searches. Rs4rs addresses these issues by providing a user-friendly platform where researchers can input their topic of interest and receive a list of recent, relevant papers from top Recommender Systems venues. Utilizing semantic search techniques, Rs4rs ensures that the search results are not only precise and relevant but also comprehensive, capturing papers regardless of variations in wording. This tool significantly enhances research efficiency and accuracy, thereby benefitting the research community and public by facilitating access to high-quality, pertinent academic resources in the field of Recommender Systems. Rs4rs is available at https://rs4rs.com.


  • Open Access

    Scalable Deep Q-Learning for Session-Based Slate Recommendation

    by Aayush Singha Roy, Edoardo D'AMico, Elias Tragos, Aonghus Lawlor, Neil Hurley


  • Open Access

    Addressing Fast Changing Fashion Trends in Multi-Stage Recommender Systems

    by Aayush Singha Roy, Edoardo D'AMico, Aonghus Lawlor, Neil Hurley

    Fashion industry is driven by fashion cycles, in which a fashion item is launched, rises to mainstream appeal and becomes a trend, then diminishes and eventually becomes obsolete. These properties make it critical to incorporate temporal information when adapting a recommendation framework to be employed in the fashion domain. However, an industry standard real-world recommendation architecture entails numerous phases, including data preparation, establishing and training recommender models, filtering and fulfilling revenue-based user needs. The contributions of the presented work are twofold. We first formalise the multi-stage recommendation pipeline by including the time dimension intrinsically present in the fashion data. We then present a study to incorporate explicit fashion domain characteristics into the presented pipeline. Finally, we conduct comprehensive experimentation on a real-world web-scale fashion dataset released by H\&M, illustrating how including domain knowledge in the multi-stage framework can lead to significantly improvement on the final recommendation performance.


  • Item Graph Convolution Collaborative Filtering for Inductive Recommendations

    by Edoardo D’aMico, Khalil Muhammad, Elias Tragos, Barry Smyth, Neil Hurley, Aonghus Lawlor


  • Analyzing and improving stability of matrix factorization for recommender systems

    by Edoardo D’aMico, Giovanni Gabbolini, Cesare Bernardis, Paolo Cremonesi