• Data Science
  • PVP
  • SEO

Machine learning solution for internal link structure prioritises conversions for Expedia

About the client

Launched in 2001, Expedia.com is part of the world’s largest travel group, Expedia Group. Expedia.com has tens of millions of pages and can be used to book airline tickets, hotel reservations, car rentals, cruises and vacation packages.

The scale of Expedia’s online inventory provides major challenges for the teams managing the site and before In Marketing We Trust stepped in with a tailored solution there were inefficient, time-consuming updates taking place every six months to correct the thousands of broken internal links that were continually building up. With an enterprise of this magnitude the client required a customised technical solution to increase SEO performance and reduce link-fixing workload on internal teams.


Reduce the heavy lifting for Expedia’s content and SEO executives by preventing site users being taken to non-existent pages

Deliver a tailored long-term solution to a large-scale issue of internal link errors

The challenge facing the client in this instance could at first appear daunting, given that Expedia’s team are managing one of the biggest travel sites in the world. The Expedia website has tens of millions of pages with a high variety of page structure templates.

Before In Marketing We Trust took control of the situation there were more than 50,000 links pointing to 404 pages. Directing users and search engines to landing pages that were unavailable or did not exist was damaging from the perspective of UX, conversion rates and SEO performance.

Relieve the burden on multiple teams at Expedia

Internal links needed to point to the correct content or in some cases unnecessary links would simply have to be removed. Expedia had multiple teams working on the website and with huge amounts of frequently changing inventory it was difficult for the site’s editors and managers to stay on top of internal link audits. 

In addition, there was an enormous amount of authority flowing to Expedia.com which needed to be distributed more effectively. Updates to fix internal links were taking too much time and client-side bandwidth, so an efficiently designed technical solution was required.


Building customised solutions for enterprise-scale digital properties reduces stress on site managers and produces improvements in SEO performance


In Marketing We Trust’s technical SEO expertise produced the required response for Expedia

The specialists from In Marketing We Trust’s technical SEO team, led by Chief Innovation Officer Frederic Chanut, designed a dynamic, automated solution to provide ongoing updates to the internal architecture of the Expedia site. 

We combined our knowledge of search engines, with expertise in data science and development to create a bespoke software solution. 

Building a customised Web Crawler and developing a specific recommendation engine for Expedia would fix the internal link structure for their massive website of tens of millions of indexed pages. The solution would ensure all internal links point to canonical pages, avoiding 404 errors and reducing 301 redirects.


How we got there

Expedia already had an existing internal link structure widget which was providing some level of internal linking, however, the links were being rapidly outdated by changes in the site caused by ongoing business activity.

We upgraded our own customised web crawler to rapidly and efficiently crawl the Expedia site to identify broken or underperforming links. We also built an automated logic engine which identified the best action to take with a broken link – to change its target, remove it, or to flag it for human attention.

The next step on this project was to specifically connect crawl rate with sales numbers. To achieve this we analysed the conversion outcomes of landing pages and influenced the internal link structure to prioritise pages which produced more conversions. This was done whilst maintaining the breadth of internal links necessary to ensure that crawlers could still find everything on the site and that internal links maintained high levels of relevancy.

In Marketing We Trust provided Expedia with a customised Web Crawler and developed a recommendation engine using some of our existing machine learning solutions. This produced an algorithm capable of suggesting the most accurate replacement for an error page and turned a painstaking manual process into an automated one.


Understanding the challenge faced by the client has led to investment in a bespoke technical solution to reduce workload and improve SEO results


A methodical and pragmatic approach has produced a long-term solution to a complex problem

The work of In Marketing We Trust’s experienced technical SEO team on this project resulted in the removal of thousands of links pointing to 404s and thousands of additional unnecessary links also being removed. A new, far cleaner architecture has been put in place. 


links pointing to 404 page errors removed


of unnecessary links removed


new architecture designed with approximately 99% cleanliness

Better Conversion

algorithm built to prioritise better conversion outcomes

An integration with the client’s legacy system includes manual overrides and crucially the customised solution we have created for Expedia is directly tied to the key business metric of increasing sales.

The internal link structure is now progressively kept up to date, with fix recommendations being issued every 24 hours. This has brought the number of bad internal links down from tens of thousands to less than a thousand at any given time, and has considerably improved the valid-to-invalid Googlebot crawl ratio, meaning that the site is updated faster and is seeing improved organic results on search engines.

In Marketing We Trust have been working closely with Expedia for more than eight years providing the travel giant with tailored digital and SEO solutions. Expedia knew they could count on our expertise to fix what was becoming a burdensome task fixing internal links. Using our existing Machine Learning solutions, we developed an algorithm to turn a painstaking manual process into an automated one to replace error pages.

The impact of this project for Expedia’s SEO efforts has been significant. In addition to removing thousands of 404 pages and insignificant links, the project has contributed to the development of the website architecture, as well as increasing the prominence of high converting landing pages. We continue to work closely with Expedia to this day.