Topic Modeling for Customer Insights at USAA with William Fehlman - TWIML Talk #276

Published: June 20, 2019, 7:26 p.m.

b'Today we\\u2019re joined by William Fehlman, director of data science at USAA, to discuss: \\n\\n\\u2022 His work on topic modeling, which USAA uses in various scenarios, including member chat channels.\\n\\n\\u2022 How their datasets are generated.\\n\\n\\u2022 Explored methodologies of topic modeling, including latent semantic indexing, latent Dirichlet allocation, and non-negative matrix factorization.\\n\\n\\u2022 We also explore how terms are represented via a document-term matrix, and how they are scored based on coherence.'