If you are developing a deep academic paper or study, these specific publications are the primary sources for his methodologies: Paper Title Key Innovation Introduction of listing embeddings for Airbnb Applying Deep Learning To Airbnb Search Full-scale architecture for search ranking A Simple Deep Personalized Recommendation System Use of Deep Average Networks (DAN) for traveler preferences Five lessons from building a deep neural network Best practices for hybrid marketplace recommenders Notable Figures named Mihajlo
: He popularized applying the "Word2vec" concept to marketplaces, treating a user's click-stream as a "sentence" and individual listings as "words" to learn high-quality embeddings.
: A physicist whose "Pupin coils" revolutionized long-distance telephony through the theory of physical loading. mihajlo
Mihajlo Grbovic - Machine Learning and Data Science at Airbnb
: His models capture both short-term intent (current search session) and long-term preferences (past bookings) to re-rank search results in milliseconds. If you are developing a deep academic paper
In his papers, Grbovic outlines specific lessons for building production-grade deep learning systems:
: He integrates visual data (photos) and textual metadata into a single hybrid model, ensuring that recommendations are not just based on clicks, but on the actual content of the listing. Key Technical Contributions In his papers, Grbovic outlines specific lessons for
: Using sophisticated strategies to select "negative" examples (items a user saw but didn't click) to sharpen the model's ability to distinguish preferences.