Analyst
Current- Designing custom data products and models from a variety of large data sources and providing consulting support to the top global pharmaceutical companies
- Write Python scripts to access and update PostgreSQL and MongoDB (BSON) databases containing large amounts of both structured and unstructured data (over 120 data elements for 600,000 worldwide clinical trials from the.
- Apply web scraping and natural-language processing techniques to augment these databases with other key information (including over 10,000 FDA approvals)
- Use packages like Mercury and Seaborn to create dynamic data visualization and interrogation tools which support both clinical R&D and investment/M&A activity
- Perform data cleaning in order to create machine-learning models for forecasting the likelihood of clinical trial success, drug approval, and catalyst events for publicly-traded pharmaceutical and biotech stocks
- Assist the finance, business development and R&D arms of large pharmaceutical companies in loading, editing and analyzing their internal datasets to answer key business questions around the timing and risk of various.