Problem
Research questions and friction points this paper is trying to address.
sequence modeling
sparse labels
search ranking
user behavior
production deployment
JourneyFormer: Encoding Airbnb Guest Journey with Sequence Modeling
🤖 AI Summary
This work addresses the challenges posed by long, exploratory user behavior sequences and sparse booking signals in Airbnb’s search ranking system by proposing a sequence modeling approach tailored for sparse conversion signals. Built upon the Transformer architecture, the method introduces customized ID embedding strategies, an event selection mechanism, and a label attribution scheme, complemented by efficient negative sampling and training-inference optimizations that substantially enhance model scalability and deployment efficiency. Evaluated through both offline metrics and online A/B tests, the proposed system demonstrates significant performance gains and has successfully driven improvements in key business metrics across two core product interfaces.
📝 Abstract
Sequence modeling has become increasingly popular in recommendation and ranking algorithms, owing to its capacity to model users' historical behaviors and infer user intentions. Despite its theoretical simplicity, the practical deployment of a sequence model in production is non-trivial due to complexity of the sequence and sparse labels. For example, in Airbnb, guest sequences are often long, exploratory and complex, and we focus on booking labels, which are sparse. As such, we are often required to make various design decisions regarding data and modeling to strike a balance between effectiveness and scalability. This work delved into these production challenges and deployed JourneyFormer, a sequence modeling solution for search ranking at Airbnb. We detail crucial design considerations, covering aspects such as guest event selection, ID embeddings, model architecture, and label attribution. Additionally, we describe several tailored strategies to accelerate model training and inference. JourneyFormer has been successfully deployed within Airbnb's production, where its effectiveness and impact have been evidenced not only by improved offline ranking metrics but also by significant gains in key business metrics through online A/B testing across 2 production surfaces.
Innovation
Methods, ideas, or system contributions that make the work stand out.
sequence modeling
search ranking
sparse labels
user journey
production deployment
🔎 Similar Papers
No similar papers found.
