Improving Deep Learning For Airbnb Search

TL;DR

This paper discusses advancements in deep learning for Airbnb search, focusing on architecture improvements, bias mitigation, and cold start solutions to enhance ranking performance.

Contribution

It introduces a new neural network architecture, a novel bias handling method, and strategies for cold start, advancing deep learning application in search ranking.

Findings

New ranking neural network architecture developed

Significant improvement in bias handling for challenging inventory

Enhanced cold start treatment for new listings

Abstract

The application of deep learning to search ranking was one of the most impactful product improvements at Airbnb. But what comes next after you launch a deep learning model? In this paper we describe the journey beyond, discussing what we refer to as the ABCs of improving search: A for architecture, B for bias and C for cold start. For architecture, we describe a new ranking neural network, focusing on the process that evolved our existing DNN beyond a fully connected two layer network. On handling positional bias in ranking, we describe a novel approach that led to one of the most significant improvements in tackling inventory that the DNN historically found challenging. To solve cold start, we describe our perspective on the problem and changes we made to improve the treatment of new listings on the platform. We hope ranking teams transitioning to deep learning will find this a practical case study of how to iterate on DNNs.