Gustavo Penha

I am a research scientist at Spotify, with a PhD from TU Delft. My work spans information retrieval, recommender systems, natural language processing, and machine learning. I am passionate about building systems that connect people with content (and creators) by understanding their information needs and preferences. I am interested in the entire information-seeking process and in designing and evaluating systems that support it.

news

May 26, 2023	Defended my PhD on Conversational Search and Recommendation 🎓.
Apr 19, 2022	We won the best paper award with our ECIR’22 paper 🏆 🎉.
Aug 27, 2021	Finished my research internship at Amazon 📦: CHI’22 & CHIIR’22.

selected publications

ECIR industry track

Contextualizing Spotify’s Audiobook List Recommendations with Descriptive Shelves

Penha, Gustavo, Wang, Alice, Achenbach, Martin, Sheets, Kristen, Mantravadi, Sahitya, Galvez, Remi, Guetta-Jeanrenaud, Nico, Narayanan, Divya, Kalaydzhyan, Ofeliya, and Bouchard, Hugues

Abs PDF

In this paper, we propose a pipeline to generate contextualized list recommendations with descriptive shelves, in the domain of audiobooks. By creating several shelves for topics the user has an affinity to, e.g. “Uplifting Women’s Fiction”, we can help them explore their recommendations according to their interests and at the same time recommend a diverse set of items. To do so, we use Large Language Models (LLMs) to enrich each item’s metadata based on a taxonomy created for this domain. Then we create diverse descriptive shelves for each user. A/B tests show improvements in user engagement and audiobook discovery metrics, demonstrating benefits for users and content creators.
RecSys

Bridging Search and Recommendation in Generative Retrieval: Does One Task Help the Other?

Penha, Gustavo, Vardasbi, Ali, Palumbo, Enrico, Nadai, Marco, and Bouchard, Hugues

PDF Blog Slides
TheWebConf

Improving Content Retrievability in Search with Controllable Query Generation

Penha, Gustavo, Palumbo, Enrico, Aziz, Maryam, Wang, Alice, and Bouchard, Hugues

PDF Blog Slides

recent presentations

Slides for talk on generative search and recs at Spotify.