Manager - Data Science
Over the past 20 years, TripAdvisor has developed an industry-leading content moderation process to maintain the integrity of the more than 780 million reviews and opinions hosted on the platform.
In 2018, TripAdvisor received 155 million content submissions from users. Of those, 66 million were reviews. 100% of reviews submitted to TripAdvisor pass through an advanced moderation process, which uses state-of-the-art analysis technology to identify potential problem comments. In 2018, 2.7 million of the reviews submitted were further screened by a highly trained content moderation team.
TripAdvisor Content team is responsible to assess whether content submissions meet established guidelines whether they are reviews, forum posts or business listings. Our work impacts millions of users every day. Our team is autonomous and cross-functional, working with the operations, business, outsourced vendors, product team, and other engineering groups on brand new functionality across our web sites.
We are looking for an experienced data scientist with broad knowledge of machine learning techniques to design and implement machine learning solutions for our moderation process. You’ll have an amazing amount of data as raw material for your projects, including over 780 million collected reviews and opinions, 5 terabytes of log data per day, and 300,000 photos and videos per day. You must be comfortable communicating your approaches to technical and non-technical managers across the company.
You will also manage a team of analysts responsible for Content and Moderation data and will be accountable for the analytic output of the team as well as their strategic direction.
- Process massive amounts of structured and unstructured data using Spark/SQL/Hive.
- Build advanced supervised and unsupervised machine learning models - e.g. XGBoost, neural networks (auto-encoders, feedforward networks, recurrent/convolutional networks, etc.), bandit/Bayesian algorithms, time-series modeling, and more.
- Research new machine learning solutions to complex business problems.
- Write production code in Python.
- Carry out A/B test experiments.
- Communicate findings to non-technical audience.
- Manage a team of Data Analysts supporting TripAdvisor Content Operations team.
- Own and manage pipeline and prioritization for the Reporting & Analytics function.
- Support the planning and forecasting process for internal and third party operations team for accurate and efficient staffing model based on TripAdvisor user generated content trends.
• Ph.D. or Master’s degree in in Computer Science, Engineering, Statistics, or related field.
• 2+ years of management experience and at least 5 years of industry experience.
• Understanding and experience in implementing machine learning in a business environment.
• Excellent communication skills.
• Pragmatic approach to business problems.
• Strong background in machine learning and statistics (with experience applying it to the real world)
• Strong foundation on data warehouse and SQL queries
• Experience with Tableau, BigQuery and other industry platforms.
• Experience with online business
• Experience with big data technologies (e.g. Hive, Spark)