Transforming Location Retrieval at Airbnb: A Journey from Heuristics to Reinforcement Learning

TL;DR

This paper details Airbnb's transition from heuristic methods to reinforcement learning for location retrieval, addressing unique challenges in geographic-based search to improve relevance and personalization.

Contribution

It introduces a novel machine learning framework for location retrieval at Airbnb, overcoming cold start, generalization, and bias issues where traditional methods fall short.

Findings

Reinforcement learning outperforms heuristics in location relevance.

The system effectively handles cold start and bias issues.

Machine learning enhances personalization in location retrieval.

Abstract

The Airbnb search system grapples with many unique challenges as it continues to evolve. We oversee a marketplace that is nuanced by geography, diversity of homes, and guests with a variety of preferences. Crafting an efficient search system that can accommodate diverse guest needs, while showcasing relevant homes lies at the heart of Airbnb's success. Airbnb search has many challenges that parallel other recommendation and search systems but it has a unique information retrieval problem, upstream of ranking, called location retrieval. It requires defining a topological map area that is relevant to the searched query for homes listing retrieval. The purpose of this paper is to demonstrate the methodology, challenges, and impact of building a machine learning based location retrieval product from the ground up. Despite the lack of suitable, prevalent machine learning based approaches, we tackle cold start, generalization, differentiation and algorithmic bias. We detail the efficacy of heuristics, statistics, machine learning, and reinforcement learning approaches to solve these challenges, particularly for systems that are often unexplored by current literature.