Extracting Customer Insights at Airbnb
Abstract: Airbnb has had over 100 Million guest arrivals over all time, and over 40 Million in 2015 alone. Naturally this exponential growth is a challenge to deal with from a customer service perspective. The first part of this talk will thus concentrate on how we can respond to and address customer issues in a shorter amount of time, while maintaining a high level of customer satisfaction. In addition, customer issues in aggregate can tell us a lot about potential product improvements and changes, and the second part of this talk will discuss how we extract and categorize these potential improvements from vast amounts of customer service tickets.
Avneesh is currently a Machine Learning Scientist at Airbnb, where he leads efforts on building a common, scalable machine learning infrastructure that enables data scientists and engineers to explore, train, and deploy models with minimal effort. He has concentrated on leveraging the vast amounts of text data on the site to enable the next generation of data products within the company. Avneesh completed his PhD in natural language processing from Carnegie Mellon University in 2015 (where his thesis focused on building contextually richer models for translating human languages), and his undergraduate degree in electrical engineering from Stanford University in 2007. In a prior life (before grad school), he was a structured equity products trader at Goldman Sachs.