Trainline sells train tickets and provides live train times and railway information through the website and mobile app. They noticed a significant loss of potential ticket purchases because many users try to book their next ride while riding through remote areas with weak internet coverage. Users churn due to long loading time, so we detected the bottlenecks and built a special booking form for weak-internet situations. It behaved exactly like the existing site but had an adjusted framework and library to load faster. The page load time was reduced to only 0.84 sec on the 3G network (12.7 times faster than before).

Expedia Group Inc. is a renowned online travel shopping platform covering over 200 travel sites worldwide and making over 600 billion AI predictions a year. They wanted to increase the number of clicks on suggested links in the footer of their website. For example, if a user searches "beach villa in Zadar", the result page shows beach villas in Zadar. Still, links in the footer suggest many other similar destinations. Expedia wanted them to be as relevant as they get since it enhances the odds that the links in the footer result in additional bookings. We created a custom-made solution based on data collection and AI for improving the quality of those links. It led to an increase of 100,000 daily visits per page.