Speaker "Jeff Palmucci" Details Back



Classification Using Crowdsourced Data at Scale


Tripadvisor has on average 340 unique monthly visitors and 350 million reviews and opinions. We classify our millions of locations into hundreds of different categories using review text, votes collected from our users, and machine learning techniques. This talk will cover some interesting issues that arise when building large numbers of models using crowdsourced data and the solutions we have developed.


As a serial entrepreneur, Jeff has started several companies. He was VP of Software Development for Optimax Systems, a developer of scheduling systems for manufacturing operations acquired by i2 Technologies. As a Founder and CTO of programmatic hedge fund Percipio Capital Management, he helped lead the company to an acquisition by Link Ventures. Jeff is currently leading the Machine Learning group at Tripadvisor, which does various machine learning projects across the company including natural language processing, review fraud detection, personalization, information retrieval, and machine vision. When Jeff is not writing code, he enjoys going to innumerable rock concerts as a professional photographer.