Learn how we helped online travel company Traveloka build a universal search engine capable of returning results in multiple product categories.
Traveloka is an online travel company that provides a one-stop platform for a range of ticketing services, including flights, accommodation, and attractions. As one of Southeast Asia’s “unicorn” startups valued at over $1 billion, Traveloka is constantly searching for ways to improve their user experience. As part of this initiative, Traveloka has invested heavily in a number of artificial intelligence and machine learning projects.
With an expanding list of 19 core product offerings, improving search capabilities was key to their continued growth. To do this, Traveloka built a search function to make it easy for users to browse the full range of products from a single search bar.
1. How to automatically deskew (straighten) a text image using OpenCV
2. Explanation of YOLO V4 a one stage detector
3. 5 Best Artificial Intelligence Online Courses for Beginners in 2020
4. A Non Mathematical guide to the mathematics behind Machine Learning
We spoke with Deb Goswami, who is directly responsible for Traveloka’s ongoing research, design, and implementation. Deb oversees the machine learning team at Traveloka, whose sole purpose is to implement machine learning solutions. As Deb began to look into data annotation solutions, he found Lionbridge.
“Lionbridge initially stood out because of their capabilities in the regional language space, but we were also impressed by their flexible approach to data annotation. It was clear from early on that they were committed to providing us with a high level of support and eager to align with our project requirements.”
Dr Deb Goswami, Data Science Lead at Traveloka
Getting enough people to collect and annotate data was a large obstacle for the team at Traveloka. Lionbridge developed a comprehensive solution to classify thousands of search queries according to an extensive system of product and sub-product categories.
With Lionbridge’s support, Traveloka’s machine learning team was able to focus on the search engine’s core development work. As a result, Traveloka quickly launched the product with confidence that it was trained using high-quality data and backed by extensive linguistic capabilities.
“From our previous experience, we know how difficult it is to build out effective data annotation teams from scratch. We were extremely pleased with Lionbridge’s ability to scale without compromising on quality or speed, particularly when it came to acting on our feedback. Our partnership has produced some great results and we’re looking forward to more successful releases in the near future.”
Dr. Deb Goswami
Traveloka’s new universal search function allows users to effortlessly search 76 unique product combinations with a single click. With further releases still to come, Traveloka’s algorithm will continue to improve ease-of-use for both their web and app users. You can try out Traveloka’s new search function by downloading the app here.
Want to learn more? Download the full case study.