Online users have high expectations for search: they want it to be fast, personalised and, above all, relevant. High search relevance is particularly important for websites ranking location-based search results, as each result must be easy to travel to.
Whether your website ranks properties, jobs or hotels, understanding your users’ search intent is important. It means you can deliver the best results at the top of the page, which leads to higher conversion rates, low bounce rates and a great user experience.
However, building a relevant search can be a complex process, and many websites struggle to display optimise results pages that match the searcher’s intent. In this post, you’ll learn how to increase the relevance of your website search using travel time data.
What is search relevance?
Search relevance refers to how accurately a website or app’s search results match a search query. Every time a user searches for information on your website, the results should match their query.
Achieving this requires an understanding of the searcher’s intent. For example, if we wanted to search for hotels in London that are reachable within 30 minutes of our starting location by public transport, the results displayed should be a list of all of the hotels that match our initial search:
Why is search relevance important?
Search relevance is crucial to providing a great user experience. Studies show that as many as 68% of users would not return to a site that provided a poor search experience.
For many websites, the search function will be the first element that users will use. This is particularly the case for websites with location-based search, where users are often searching for locations or points of interest that are nearby or easy to get to. If your users see results they can’t travel to, they’ll bounce.
Search relevance vs. ranking
While search relevance is all about whether a search result matches a search query, search ranking refers to the order in which these results are displayed. Searchers expect to have the most relevant results at the top of the results page. Ranking can also be personalised to better match a user’s preferences.
Because there are often many variables at play, search relevance and ranking can be difficult to fine-tune. Matching results to a query is a balancing act because decisions involve multiple considerations.
For example, when choosing a hotel for a city break we may consider reviews, hotel star rating, proximity to the airport, the local neighbourhood and hotel facilities.
Machine learning is often used to understand how to deliver the best performing results page - this process is called feature engineering. It means that results aren't ranked purely on price or on reviews, it's a delicate balance between all features.
The secret to delivering relevant location search results
Display location search results by journey time
For websites that provide location-based search, using travel time data as a feature within your search relevance algorithm significantly improves the relevance of search results.
Filtering search results based on travel times returns twice as many relevant results as a distance-based search. This is because displaying results by distance doesn't accurately show which locations are reachable. Distance ignores real-life transport networks, local geography and congestion.
In contrast, travel time data helps searchers understand how easily they can reach a location by different modes of transport.
It eliminates irrelevant results for locations that take too long to reach, whilst ensuring that you're always showing the most relevant results at the top of the search results page.
In the following image, we can see where’s reachable within 20 km from a starting location in London. However, this distance radius assumes people can travel as the crow flies in a straight line:
To compare, here are all the areas that we could reach within 1 hour by public transport:
74% of people would rather search for locations by time instead of distance
Increasingly, searchers expect to be shown travel times when searching for locations. In a study conducted by TravelTime, 74% of people said they would prefer to search for locations by travel time rather than distance.
In many ways this is unsurprising: as individuals, we easily understand time without having to run any calculations.
With distance, we have to calculate how long it will take us to make the journey - which, with transport networks that vary in speed and availability, isn't always straightforward. Because of this, websites that offer results that take travel times into account offer a high relevance for users.
The TravelTime API lets your website visitors search for locations by travel time and preferred mode of transport. This gives your users the ability to decide how far they’re willing to travel from their start location.
In turn, this increases conversions because they’ll no longer see places that are nearby but hard to access. Instead, they can see results that may be further away by distance, but still easy to get to.
See how TravelTime helps improve search relevance below:
What types of websites can use travel time data to improve search relevance?
Travel time data can improve the search relevance of any website or app where journey time is an important factor for users, including:
- Job boards: Display relevant jobs based on a user's commute time
- Property: Help users find homes based on travel time to points of interest
- Retail: List nearby stores by travel time to drive more footfall
- Hotels: Show relevant hotels based on journey times to points of interest
5 great examples of location search relevance
1. Totaljobs displays results by commute time (and increases conversions by 10%)
Totaljobs, one of the UK’s leading job boards, transformed its job search functionality by integrating travel time data into its search relevance algorithm. While most job sites only give users the option to search by distance, Totaljobs recognised that distance alone isn’t a useful reflection of a location’s accessibility.
By giving users the ability to search for jobs by commute time, Totaljobs has seen a 10% increase in website conversions.
2. Zoopla allows users to find properties within their desired travel times
Within 10 months of using travel time data within its search functionality, Zoopla, one of the UK’s largest property websites, saw a 300% increase in website conversions – measured as users booking viewing appointments. This can be attributed to the tool providing more relevant results.
“Our travel time tool has achieved an impressive 300% increase in conversions,” said Matt Cohan, Chief Product Office at Zoopla. “We believe that because the results are more relevant the quality of leads we pass to our members is higher.”
3. Alpaca lets users find properties based on journey times to points of interest
As the largest global network of housing renting groups, Alpaca smartly connects renters with real estate agents and property managers. By integrating the TravelTime API into its search recommendation algorithm, Alpaca can display the most relevant property listings to its users based on their proximity to points of interest that users have specified.
Sebastian Illing, Co-Founder, said: “We’ve found that our users really like the POI functionality. Whereas before we thought that factors like amenities would be most important for our users, we’ve found that the POI has a much higher usage from our users. Over 40% of our users currently use it.”
4. Zen Educate suggests jobs based on candidates' commute preferences
Zen Educate is an online staffing platform that allows schools to connect directly with teachers and supply staff. The platform uses the TravelTime API to match teachers to the most relevant teaching jobs based on how accessible a potential school is.
Using straight-line distance wouldn’t give teachers an accurate view of how easily they can travel to a school. However, by integrating travel time data into its search recommendations, teachers can choose their travel time and transport preferences, increasing the relevance of the opportunities that they are shown.
5. Foxtons enhances its property search with travel time isochrones
Estate agency, Foxtons, allows users to search for properties based on commute times. Users can enter their work address on the website and the travel time search tool identifies the best locations to live based on commute times and mode of transport. It also uses isochrones to help users visualise where’s reachable within their preferred time limit.
Improve your search relevance with the TravelTime API
Optimising search relevance requires an understanding of a user's intent in order to display results that match their query.
For location-based search, where the returned results are locations, you can improve search relevance by using travel time data as a feature within your search relevance algorithm.
This will filter and display results based on how reachable they are by a user's chosen mode of transport. By doing this, you'll give your users a better understanding of the locations they can actually reach within a given time, as well as increase your conversion rates.