TripAdvisor's Lessons Learned From Building A Chatbot


Episode Artwork
1.0x
0% played 00:00 00:00
Apr 06 2017 26 mins  

Imagine being able to instantly get recommendations for top restaurants, hotels, and attractions, no matter where you are in the world without having to talk to a human. It’s a great resource for travelers made possible by the TripAdvisor chatbot.

Chatbots are popping up everywhere. TripAdvisor as a company tries to stay on top of new technology, but it didn’t want to create a chatbot just for the sake of making one. After considering the strategy involved, the team, led by Jeff Chow, vice president of product, decided to dip its toes into the chatbot water with a way to deliver great recommendations where and when people need them. Creating the chatbot was a learning experience with principles that can be applied to a variety of verticals. The overall goal for the chatbot was to take TripAdvisor’s leading qualities and turn then into the ultimate travel assistant on the go—perfect for planning a trip, traveling, or sharing information with friends and family. With its software, TripAdvisor wanted to use machine learning to scale the data from its many interfaces so that it could be used in different customer interactions.

The team views the chatbot as guided discovery—the questions start big and then narrow down until the task is completed and the best recommendation can be given. In order to provide the best recommendation, the bot must understand what the traveller is really looking for—after all, a restaurant recommendation in Miami will be different based on if someone is traveling for work or pleasure. Chatbots have potential to be a powerful, personalized tool. Because they can remember things users say, it can get personal and hopefully soon learn soft signals and natural conversation. That way, even if a user doesn’t explicitly ask something, a chatbot could potentially know what to recommend based on their patterns or behavior. However, getting smarter over time is a unique challenge in travel, as people’s travel preferences can change greatly depending on the purpose of their travel, which means the bot needs to be adaptable to different travel needs.

TripAdvisor also learned that building a chatbot isn’t a one and done process—there is always room for continued growth and improvement. The company’s next focus is to increase engagement with its partner businesses to provide better recommendations to customers.

Jeff’s best advice from the TripAdvisor experience is for other companies to be strategic with their chatbots and technology. Don't create a chatbot just for the sake of doing it, but instead think of what it can do to move your business forward. When done correctly, chatbots can create great opportunities for an organization.