Travelers Insurance
Data Scientist
Apr 2024 – Present
- Trained and deployed a ResNet neural network to use aerial imagery to identify damage to Travelers-insured properties after severe wind events
- Used large language models (LLMs) to extract key information from, and transformer models for multi-label classification of, legal complaints associated with general liability claims
- Managed an intern, provided mentorship to data scientists, and chaired a committee to improve a leadership development program
Senior Associate Data Scientist
Jul 2022 – Apr 2024
- Led the migration of a business-critical modeling code base from SAS to Python and from on-prem to AWS. Technical requirements included the ability to handle over 100M auto policies while improving run-time.
- Evaluated the feasibility of using tree-based models trained on features derived from aerial imagery to improve price segmentation in an auto insurance product
Associate Data Scientist
Jun 2021 – Jul 2022
- Used double generalized linear models (DGLMs) to determine appropriate pricing factors for millions of personal insurance policies.
- Trained an ensemble model to identify cross-selling opportunities for existing customers as part of a data science competition, coming in 2nd place out of 30 teams.