Airbnb has developed and deployed JourneyFormer, a sequence modeling solution for its search ranking system. The model addresses challenges such as long and complex guest sequences, sparse booking labels, and the need for scalability. Key design decisions involved guest event selection, ID embeddings, and model architecture, alongside strategies for accelerated training and inference. JourneyFormer has been successfully integrated into Airbnb's production environment, demonstrating improvements in offline ranking metrics and significant gains in online business metrics across multiple surfaces. AI
IMPACT This deployment showcases practical applications of sequence modeling in e-commerce, potentially influencing how other platforms optimize user journeys and search.
RANK_REASON The item is a research paper detailing a sequence modeling solution developed and deployed by Airbnb. [lever_c_demoted from research: ic=1 ai=1.0]
- Airbnb
- alphaXiv
- arXiv
- CatalyzeX
- Connected Papers
- DagsHub
- Gotit.pub
- Hugging Face
- JourneyFormer
- Litmaps
- ScienceCast
- scite Smart Citations
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →