The 2018 KDD conference is right around the corner — and we are looking forward to seeing you there. (That’s Knowledge Discovery and Data Mining, if you’re not familiar with it!) We are excited to have three Airbnb papers accepted for oral presentation at the Applied Data Science Track and one tech talk presentation. Our team will share our approach to solving interesting and challenging problems at Airbnb, including personalized real-time search ranking, dynamic pricing, paid growth, and online experimentation.

These are just a few examples of advanced technology of machine learning, artificial intelligence, and online experimentation we leverage at Airbnb to help create a world where everyone can belong everywhere.

We can’t wait to both share our work and learn from all of you in London next week. Don’t hesitate to come and say hi to our team — and remember, we’re hiring!

Our Papers

Search Ranking and Recommendations are fundamental problems of crucial interest to major Internet companies, including web search engines, content publishing websites and marketplaces. However, despite sharing some common characteristics a one-size-fits-all solution does not exist in this space. Given a large difference in content that needs to be ranked, personalized and recommended, each marketplace has a somewhat unique challenge. Correspondingly, at Airbnb, a short-term rental marketplace, search and recommendation problems are quite unique, being a two-sided marketplace in which one needs to optimize for host and guest preferences, in a world where a user rarely consumes the same item twice and one listing can accept only one guest for a certain set of dates.

In this paper we describe Listing and User Embedding techniques we developed and deployed for purposes of Real-time Personalization in Search Ranking and Similar Listing Recommendations, two channels that drive 99% of conversions. The embedding models were specifically tailored for Airbnb marketplace, and are able to capture guest’s short-term and long-term interests, delivering effective home listing recommendations. We conducted rigorous offline testing of the embedding models, followed by successful online tests before fully deploying them into production.

The summary of this paper was published in Airbnb’s Medium Blog.

Customized Regression Model for Airbnb Dynamic Pricing by Peng Ye (Airbnb); Julian Qian (Ant financial); Jieying Chen (Airbnb); Chen-Hung Wu (Airbnb); Yitong Zhou (Airbnb); Spencer De Mars (Impira); Frank Yang (Airbnb); Li Zhang (Airbnb)

This paper describes the pricing strategy model deployed at Airbnb, an online marketplace for sharing home and experience. The goal of price optimization is to help hosts who share their homes on Airbnb set the optimal price for their listings. In contrast to conventional pricing problems, where pricing strategies are applied to a large quantity of identical products, there are no “identical” products on Airbnb, because each listing on our platform offers unique values and experiences to our guests. The unique nature of Airbnb listings makes it very difficult to estimate an accurate demand curve that’s required to apply conventional revenue maximization pricing strategies.

Our pricing system consists of three components. First, a binary classification model predicts the booking probability of each listing-night. Second, a regression model predicts the optimal price for each listing-night, in which a customized loss function is used to guide the learning. Finally, we apply additional personalization logic on top of the output from the second model to generate the final price suggestions. In this paper, we focus on describing the regression model in the second stage of our pricing system. We also describe a novel set of metrics for offline evaluation. The proposed pricing strategy has been deployed in production to power the Price Tips and Smart Pricing tool on Airbnb. Online A/B testing results demonstrate the effectiveness of the proposed strategy model.

Online controlled experiments, or A/B testing, has been a standard framework adopted by most online product companies to measure the effect of any new change. Companies use various statistical methods including hypothesis testing and statistical inference to quantify the business impact of the changes and make product decisions. Nowadays, experimentation platforms can run as many as hundreds or even more experiments concurrently. When a group of experiments is conducted, usually the ones with significant successful results are chosen to be launched into the product. We are interested in learning the aggregated impact of the launched features. In this paper, we investigate a statistical selection bias in this process and propose a correction method of getting an unbiased estimator. Moreover, we give an implementation example at Airbnb’s ERF platform (Experiment Reporting Framework) and discuss the best practices to account for this bias.

Invited Tech Talk

Ganesh Venkataraman will be delivering an invited talk at Ad KDD workshop. The growth team at Airbnb is responsible for helping travelers find Airbnb, in part by participating in ad auctions on major search platforms such as Google and Bing. In this talk, we will describe how advertising efficiently on these platforms requires solving several information retrieval and machine learning problems, including query understanding, click value estimation, attribution and realtime pacing of our expenditure and bidding optimization.

The Airbnb Booth at KDD

Please feel free to stop by our booth (#11) to meet Airbnb engineers and data scientists who work on a variety of machine learning problems.

Airbnb Events at KDD

We will be hosting an invite only event on Tuesday night. Join us Tuesday at The Gun to meet more members of the team and hear music from Hidden Jazz experience hosts from Airbnb’s community in London. We’ll have food, drinks, music and great conversation!

We Are Hiring!

Learn more about Machine Learning opportunities at Airbnb at http://bit.ly/airbnbML