TripAdvisor has begun using machine learning to automatically select the ‘best’ photos to portray a hotel listed on its site. The review site says primary, or ‘hero’, images can often be lower quality when hotel managers don’t choose their own … Continue reading
TripAdvisor using machine learning to choose ‘best’ hotel pictures
TripAdvisor has begun using machine learning to automatically select the ‘best’ photos to portray a hotel listed on its site.
The review site says primary, or ‘hero’, images can often be lower quality when hotel managers don’t choose their own favourite.
“While many of these traveller photos in the gallery are undoubtedly helpful to travellers, they are not always the most representative photos of the business, nor are they the photos that an owner would choose to show off the best of their property,” the company said.
“The primary photo is the best way for a property to make a strong first impression to travellers – an image that draws potential guests to a property’s listing means they are more likely to choose that place to stay.”
Its new auto-select feature for primary photos for accommodations uses machine learning to evaluate and select the best available primary photo, taking into account both professional and traveller photos.
It analyses factors which user testing has shown to influence the impact of photos on engagement, from image resolution, orientation and sharpness, to whether there are people in the photo.
Trip Advisor claims its machine learning technology has been shown to select photos which drive higher levels of engagement from travellers.
Accommodation owners have always been able to select their primary photo and can choose from their own submitted photos or those taken by travellers. Despite the new tool, owners can still choose their own photo.
“We know that good photos are a key part in attracting new guests,” said Martin Verdon-Roe, vice president, B2B hotel product and marketing at TripAdvisor.
“According to research, 79% of TripAdvisor travellers said that photos were important when choosing to book an accommodation and in more recent live site testing with partners we can see that optimised photo selection has been shown to increase user click through rates.
“This exciting new feature capitalises on our strength in machine learning with insights from millions of professional and traveller photos across TripAdvisor to help properties make the best first impression to our global travellers.”