改进地图的搜索排名

How Airbnb is adapting ranking for our map interface.

Airbnb如何为我们的地图界面调整排名。

Malay Haldar, Hongwei Zhang, Kedar Bellare Sherry Chen

Search is the core mechanism that connects guests with Hosts at Airbnb. Results from a guest’s search for listings are displayed through two interfaces: (1) as a list of rectangular cards that contain the listing image, price, rating, and other details on it, referred to as list-results and (2) as oval pins on a map showing the listing price, called map-results. Since its inception, the core of the ranking algorithm that powered both these interfaces was the same — ordering listings by their booking probabilities and selecting the top listings for display.

搜索是将客人与Airbnb房东连接起来的核心机制。客人搜索房源的结果通过两种界面显示：(1) 作为包含房源图片、价格、评分和其他详细信息的矩形卡片列表，称为列表结果，(2) 作为地图上的椭圆形图钉显示房源价格，称为地图结果。自成立以来，驱动这两种界面的排名算法核心都是相同的——按预订概率对房源进行排序并选择顶部房源进行展示。

But some of the basic assumptions underlying ranking, built for a world where search results are presented as lists, simply break down for maps.

但一些基于搜索结果以列表形式呈现的基本排序假设，在地图上就不再适用了。

What Is Different About Maps?

地图有什么不同？

The central concept that drives ranking for list-results is that user attention decays starting from the top of the list, going down towards the bottom. A plot of rank vs click-through rates in Figure 1 illustrates this concept. X-axis represents the rank of listings in search results. Y-axis represents the click-through rate (CTR) for listings at the particular rank.

驱动列表结果排名的核心概念是用户注意力衰减，从列表顶部开始，向下延伸到底部。图1中的排名与点击率的关系图说明了这一概念。X轴代表搜索结果中房源的排名。Y轴代表特定排名房源的点击率（CTR）。

Figure 1: Click-through rates by listing search rank

图1：按房源搜索排名的点击率

To maximize the connections between guests and Hosts, the ranking algorithm sorts listings by their booking probabilities based on a number of factors and sequentially assigns their position in the list-results. This often means that the larger a listing’s booking probability, the more attention it receives from searchers.

为了最大化客人与房东之间的连接，排名算法根据多个因素对房源的预订概率进行排序，并依次分配它们在列表结果中的位置。这通...