Archives Articles

Going Material

Kedar Sarmalkar posted August 17, 2015
Google introduced material design in IO 2014 and finally established some strong android design guidelines. Here I'm going to describe some of things I had to do to convert the existing non-material TripAdvisor Flights screens to material design. Some of the steps were super easy and straight forward and some required a bit of troubleshooting and tweaking to get things right. Change the target SDK We had already done this…
Full Article

Making an Android Wear App

Dharmin Majmudar posted August 10, 2015
TripAdvisor helps you in multiple ways to plan your perfect trip right from finding places you would enjoy, getting trusted reviews from fellow travelers about that place, finding great restaurants that would enhance your trip and finally booking a relaxing hotel to end your perfect day. Once you are actually on your trip you would want to explore what's nearby, and what better way to lookup something quickly than turning…
Full Article

Lowering the Noise Floor

Thomas Alexander posted July 31, 2015
Automated UI testing is difficult, especially in a company that moves as fast as TripAdvisor. It seems that every week we have new features and UIs rolling out the door. Unfortunately, with all this development, there is bound to be some bugs that escape our tests. TripAdvisor currently serves 37 points of sale, with over 8 million locations, so comprehensive manual testing is frequently not an option. To aid us…
Full Article

Yes, I’m Lazy

Chris Colebourn posted July 24, 2015
The faster a web page loads the more likely people will use it. 80% of the time spent by a user waiting for a page to render is outside the server. The time is divided between downloading components, parsing, rendering content and executing scripts. For most pages, downloading is the largest component. Downloading content has two parts. The number of HTTP requests that need to be made and the total…
Full Article

Using Apache Spark for Massively Parallel NLP

Jeff Palmucci posted July 17, 2015
Here at TripAdvisor we have a lot of reviews, several hundred million according to the last announcement. I work with machine learning, and one thing we love in machine learning is putting lots of data to use. I've been working on an interesting problem lately and I'd like to tell you about it. In this post, I'll set up the problem and the underlying technology that makes it possible. I'll get…
Full Article

Which of TripAdvisor’s reviews are actually helpful?

Gregory Amis posted July 10, 2015
At TripAdvisor, we use machine learning to assess whether a user’s review is substantive and helpful to other users. This article describes our motivations, technology, and results. Problem description TripAdvisor members submit nearly one million reviews every week. We want to publish only the reviews that are helpful to other travelers, but our moderation team can’t possibly read every submitted review. If we can programmatically score a review’s helpfulness, we…
Full Article

My Struggles with Map / Reduce

Louis Calisi posted July 3, 2015
I have a confession to make: I’ve been using Map / Reduce for the past 5 years. Up till recently I thought it was the only way to realistically process massive amounts of data in a reasonable amount of time. I’ve assumed streaming technologies were only relevant for simplistic applications where speed is prioritized over accuracy. I’ve been working on an amazing project for TripAdvisor and have come to the…
Full Article

Ordering Hotels on TripAdvisor as a Minimum Feedback Arc Set problem

Craig Schmidt posted June 26, 2015
Hello from the TripAdvisor Machine Learning Group This is the first in a series of blog posts from the Machine Learning Group at TripAdvisor. We get to work on lots of fun, interesting problems, and we thought you might like to hear about them. What order should we show our hotels? Take a Hotels page for a city on TripAdvisor, like this one for Boston.   How should we sort…
Full Article