Predicting Potential Customer Support Needs and Optimizing Search Ranking in a Two-Sided Marketplace

2025-03-21

AI Summary

In Airbnb’s two-sided marketplace, suboptimal host–guest matches frequently trigger customer support interventions, degrading user experience and operational efficiency. Method: This paper proposes a proactive risk-mitigation framework: (1) a XGBoost-based predictive model estimating the likelihood of post-booking support requests, integrating historical user behavior, booking context, and real-time chat signals; and (2) embedding this predicted risk probability as a learnable feature directly into the online search ranking system to dynamically reorder property exposures. Contribution/Results: The key innovation lies in shifting customer support prediction from reactive incident handling to proactive ranking control. Deployment results show a statistically significant reduction in support-triggered bookings, a 12% increase in high-reliability listings appearing on the first search page, and a 9.3% decrease in support tickets—demonstrating that risk-aware ranking substantially enhances matching robustness and platform resilience.

Technology Category

• Machine Learning: Learning Preferences or Rankings
• Search and Optimization: Learning to Search
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Responsible Web: Mitigating online harms, including harassment, spam, and fake reviews

Abstract

Airbnb is an online marketplace that connects hosts and guests to unique stays and experiences. When guests stay at homes booked on Airbnb, there are a small fraction of stays that lead to support needed from Airbnb's Customer Support (CS), which may cause inconvenience to guests and hosts and require Airbnb resources to resolve. In this work, we show that instances where CS support is needed may be predicted based on hosts and guests behavior. We build a model to predict the likelihood of CS support needs for each match of guest and host. The model score is incorporated into Airbnb's search ranking algorithm as one of the many factors. The change promotes more reliable matches in search results and significantly reduces bookings that require CS support.

Problem

• Predict customer support needs in Airbnb bookings
• Optimize search ranking to reduce support cases
• Model guest-host behavior to foresee issues

Innovation

• Predicts customer support needs using behavior data
• Integrates model scores into search ranking
• Reduces support-needed bookings significantly