Today we’re joined by William Fehlman, director of data science at USAA.
Subscribe: iTunes / Google Play / Spotify / RSS
We caught up with William a while back to discuss his work on topic modeling, which USAA uses in various scenarios, including chat channels with members via mobile and desktop interfaces. In our conversation, we discuss how he generates the datasets that are used for the various chat channels, and the various methodologies of topic modeling that have been explored for these use cases, including latent semantic indexing, latent Dirichlet allocation, and non-negative matrix factorization. We also explore how terms are represented via a document-term matrix, and how they are scored using coherence.
You are invited to join us for the very first TWIMLcon conference, which will focus on the tools, technologies, and practices necessary to scale the delivery of machine learning and AI in the enterprise. The event will be held October 1st & 2nd in San Francisco and early bird registration is open today at twimlcon.com.
Mentioned in the Interview
- Latent Semantic Indexing
- Latent Dirichlet Allocation
- Non-negative matrix factorization
- TWIML Events Page
- TWIML Meetup
- TWIML Newsletter
“More On That Later” by Lee Rosevere licensed under CC By 4.0