失效链接处理 |
2018 airbnb real-time rec using Embedding for serach ranking PDF 下载
本站整理下载:
相关截图:
主要内容:
1 INTRODUCTION
During last decade Search architectures, which were typically based
on classic Information Retrieval, have seen an increased presence
of Machine Learning in its various components [2], especially in
Search Ranking which often has challenging objectives depending
on the type of content that is being searched over. The main reason
behind this trend is the rise in the amount of search data that can
be collected and analyzed. The large amounts of collected data
open up possibilities for using Machine Learning to personalize
search results for a particular user based on previous searches and
recommend similar content to recently consumed one.
The objective of any search algorithm can vary depending on the
platform at hand. While some platforms aim at increasing website
engagement (e.g. clicks and time spent on news articles that are being searched), others aim at maximizing conversions (e.g. purchases
of goods or services that are being searched over), and in the case
of two sided marketplaces we often need to optimize the search
results for both sides of the marketplace, i.e. sellers and buyers. The
two sided marketplaces have emerged as a viable business model
in many real world applications. In particular, we have moved from
the social network paradigm to a network with two distinct types of
participants representing supply and demand. Example industries
include accommodation (Airbnb), ride sharing (Uber, Lyft), online
shops (Etsy), etc. Arguably, content discovery and search ranking
for these types of marketplaces need to satisfy both supply and
demand sides of the ecosystem in order to grow and prosper.
In the case of Airbnb, there is a clear need to optimize search
results for both hosts and guests, meaning that given an input query
with location and trip dates we need to rank high listings whose
location, price, style, reviews, etc. are appealing to the guest and,
at the same time, are a good match in terms of host preferences for
trip duration and lead days. Furthermore, we need to detect listings
that would likely reject the guest due to bad reviews, pets, length
of stay, group size or any other factor, and rank these listings lower.
To achieve this we resort to using Learning to Rank. Specifically, we
formulate the problem as pairwise regression with positive utilities
for bookings and negative utilities for rejections, which we optimize
using a modified version of Lambda Rank [4] model that jointly
optimizes ranking for both sides of the marketplace.
Since guests typically conduct multiple searches before booking,
i.e. click on more than one listing and contact more than one host
during their search session, we can use these in-session signals, i.e.
clicks, host contacts, etc. for Real-time Personalization where the
aim is to show to the guest more of the listings similar to the ones we
think they liked since staring the search session. At the same time
we can use the negative signal, e.g. skips of high ranked listings, to
show to the guest less of the listings similar to the ones we think
Applied Data Science Track Paper KDD 2018, August 19-23, 2018, London, United Kingdom 311
they did not like. To be able to calculate similarities between listings
that guest interacted with and candidate listings that need to be
ranked we propose to use listing embeddings, low-dimensional
vector representations learned from search sessions. We leverage
these similarities to create personalization features for our Search
Ranking Model and to power our Similar Listing Recommendations,
|