I am a data scientist based in the San Francisco Bay Area. My 20 years of experience doing data science spans the range of the subject, from problem definition and data preparation, through modeling via machine learning, to results interpretation and presentation to all levels of audience.
If going through the whole website will take too long, see the work highlights for my most significant projects and results.
Areas of data science in which I have particular expertise include:
- End-to-end solution of business problems for customers
- Machine learning algorithms: gradient boosted decision tree, random forest, support vector machine, neural network, nearest neighbor, unsupervised, etc.
- Machine learning for large datasets (tools like H2O, etc., also previously Skytree)
- Communication of results and interpretations to all audiences
- Presentation and training of data science (Toastmasters Competent Communicator)
- Broad range of industries
- Python for general data science work
- Bridging customers, product management, and engineering to improve products and drive roadmaps
Besides technical data science work, I have provided training, outreach, blogs, videos, and other material to customers and the public. My previous experience in academia (astrophysics combined with data science) includes several publications in top research journals (over 1000 citations total), and most other aspects of academic research work, including grant funding, teaching & mentoring, and leading projects.
For more details of my data science work, experience, previous academic research, general data science content, and other topics, see the subpages on the navigation menu. This site is new and some pages are still missing some polish, but the core content is present.