: 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.
Grbovic's research addresses the "cold-start" problem—recommending new items or assisting new users with no history—by using to explore heterogeneous data like text, images, and user behavior.
Mihajlo Grbovic is a prominent scientist in machine learning, and a "deep paper" on his work focuses on his pioneering research into and deep learning for search ranking . His most influential work stems from his tenure as a Science Lead at Airbnb , where he revolutionized how marketplaces connect users to items using latent representations. Core Research Focus: Real-Time Personalization
Mihajlo Grbovic - Machine Learning and Data Science at Airbnb
: Preferring modular, staged training over end-to-end training to ensure stability in large-scale systems.
In his papers, Grbovic outlines specific lessons for building production-grade deep learning systems:
: A physicist whose "Pupin coils" revolutionized long-distance telephony through the theory of physical loading.
: 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.
Grbovic's research addresses the "cold-start" problem—recommending new items or assisting new users with no history—by using to explore heterogeneous data like text, images, and user behavior. mihajlo
Mihajlo Grbovic is a prominent scientist in machine learning, and a "deep paper" on his work focuses on his pioneering research into and deep learning for search ranking . His most influential work stems from his tenure as a Science Lead at Airbnb , where he revolutionized how marketplaces connect users to items using latent representations. Core Research Focus: Real-Time Personalization : He popularized applying the "Word2vec" concept to
Mihajlo Grbovic - Machine Learning and Data Science at Airbnb His most influential work stems from his tenure
: Preferring modular, staged training over end-to-end training to ensure stability in large-scale systems.
In his papers, Grbovic outlines specific lessons for building production-grade deep learning systems:
: A physicist whose "Pupin coils" revolutionized long-distance telephony through the theory of physical loading.