Airbnb connects millions of guests and Hosts everyday. Most of these connections are forged through search, the results of which are determined by a neural network–based ranking algorithm. While this neural network is adept at selecting individual listings for guests, we recently improved the neural network to better select the overall collection of listings that make up a search result. In this post, we dive deeper into this recent breakthrough that enhances the diversity of listings in search results.

At Airbnb, we have been consciously designing and building products to be equally usable by all users. Making our mobile apps and websites more accessible not only aligns with our company’s mission of creating a world where people can belong anywhere, but also supports the civil rights of people with disabilities and complies with the law.

In this article, we highlight some of the efforts we have made to make the app more accessible, for example, labeling UI elements, grouping related content, supporting large font scale, providing heading and page names. The Airbnb app is one of the most popular travel apps with millions of users and supports many features. Making such a complex app more accessible is a huge endeavor that we are continuously working on.

在 2020 年 Hasura 的企业 GraphQL 会议上，Airbnb爱彼迎 展示了 Viaduct，一个面向数据的服务网格（Service Mesh） ，其为爱彼迎基于微服务的 SOA（Service-Oriented Architecture）的模块化带来了阶梯性的提升。我们将在这篇文章中介绍 Viaduct 背后的思想及大致运作原理。

How Airbnb is applying declarative design patterns to rapidly build fluid transition animations.

How Airbnb uses visual attributes to enhance the Guest and Host experience.

Leveraging text generation models to build more effective, scalable customer support products.

Online travel search hasn’t changed much in the last 25 years. The traveler enters her destination, dates, and the number of guests into a search interface, which dutifully returns a list of options that best meet the criteria. Eventually, Airbnb and other travel sites made improvements to allow for better filtering, ranking, personalization and, more recently, to display results slightly outside of the specified search parameters–for example, by accommodating flexible dates or by suggesting nearby locations. Taking a page from the travel agency model, these websites also built more “inspirational” browsing experiences that recommend popular destinations, showcasing these destinations with captivating imagery and inventory (think digital “catalog”).

分类系统是用于对信息进行分类和组织的知识组织系统。分类系统使用文字（而不是数字或符号）来描述事物，并使用层次结构来将事物进行分类。分类系统的结构反映了这些事物是如何相互关联的。例如，超赞房东是房东的一种类型，而房东是爱彼迎用户的一种类型。分类系统提供了重要的术语控制，使下游系统能够通过其定位信息以及分析一致的、结构化的数据。

爱彼迎在前端产品中使用分类系统来帮助房客和房东发现优质的住宿、体验、内容以及客户支持产品。爱彼迎也在后台工具中使用分类系统来结构化数据、组织内部信息以及支持机器学习应用程序。

Introduction of Airbnb interleaving experimentation framework, usage and approaches to address challenges in our unique business.

How Airbnb built a persistent, high availability and low latency key-value storage engine for accessing derived data from offline and streaming events.

This blog aims to introduce Airbnb’s experience upgrading Data Warehouse infrastructure to Spark and Iceberg.

In our first post we discussed the need for a near real time Safe Deploy system and some of the statistics that power its decisions. In this post we will cover the architecture and engineering choices behind the various components that Safe Deploys comprises.

Designing a near real-time experimentation system required making explicit tradeoffs among speed, precision, cost, and resiliency. An early decision was to limit near real-time results to only the first 24 hours of an experiment — enough time to catch any major issues and transition to using comprehensive results from the batch pipeline. The idea being once batch results were available, experimenters would no longer need real time results. The following sections describe the additional design decisions in each component of the Safe Deploys system.

在本系列文章的第一篇中，我们介绍了数据保护平台（Data Protection Platform，以下简称 DPP），是一个使我们能符合国际法律和安全需求的数据保护平台。我们强调了解我们的数据是保护数据的必要组成部分，可以通过跟踪个人和敏感数据在我们生态系统中的存储位置来实现。在本篇文章中，我们将讨论公司在查找个人和敏感数据的确切位置时经常面临的挑战。许多公司依靠工程师手动追踪个人数据和敏感数据在内部系统如何流转以及流向何处，但依靠手动数据分类会带来不少挑战：

1. 数据在不断迭代。这使工程师很难全面了解数据，及数据如何在公司的基础设施中流动。数据还会复制并存到不同的数据存储中，此外，随着产品的变化和新产品的出现，也会有新类型的数据产生。
2. 手动分类更容易出错。工程师可能会忘记该数据资产是否包含个人数据，或者有些数据是用户自由输入，工程师并不知道里面会包含什么。
3. 安全和个人隐私数据不断增加。对于新隐私法规和安全合规要求的新增数据元素，工程师须再次进行手动数据分类，造成了公司的高成本和低效率。
4. 在代码库和各种数据存储中可能会泄漏密钥。工程师常用密钥包括生产环境API 密钥、供应商密钥和数据库登录凭证等。代码库中泄漏密钥是一个常见的问题，通常由于工程师意外或无意识地提交代码且没有被审批人发现。密钥一旦检入（check in）生产环境，想要找到它们就变成大海捞针，不容易被发现。

为了应对这些挑战，我们构建了数据分类工具来检测数据存储、日志和源代码中的个人和敏感数据。一起来看下我们的数据分类工具架构。具体来说，我们将深入研究 Inspekt 的技术组件，即数据存储和日志数据分类系统，以及 Angmar -- Github 企业版上的代码库的密钥检测和防护系统。

智能客服产品全剖析（下篇）的设计干货分享来也！本文将在用户旅程地图的基础上阐述智能客服产品的交互框架和界面设计心得。

Every engineer knows that security is a never-ending problem. Until we delete all our code and move into a cottage in the woods, we have to accept that there is no such thing as 100% secure software. You could be doing everything perfectly, and a publicly known vulnerability (CVE) could emerge for the most updated version of a third party library in your infrastructure. Things are secure until they are not. Like with Sisyphus, the boulder will never reach the top of the hill.

Rather than eliminating vulnerabilities, the goal of a vulnerability management program should be to quickly and effectively detect and respond to the barrage of threats that surface every day. There are many scanners and vendor tools that purport to solve the problem. But with the scanners comes the problem of a never-ending flood of CVE reports, thus slowing down our ability to remediate in a timely manner.

How Airbnb securely manages permissions for our large team of employees, contractors, and call center staff.