I currently manage the Data Science and Analytics team at Live Oak Bank.
On the management side, I'm interested in things like metric trees and systems thinking to organize a company's data projects.
On the data science side, I'm interested in simple models and analyses that solve concrete business problems.
An implementation of convergent cross mapping with the familiar api of scikit-learn.
Published in the Journal of Open Source Software, skedm is an implementation of empirical dynamic modeling with the familiar api of scikit-learn.
An interface to the National Data Buoy Center.
A docker based project layout for deploying scikit-learn models as an API endpoint.
The Royal Society
We adjust spatial forecasting to handle discrete data and apply a nonlinear forecasting technique to explore nonlinear determinism in spatial configurations of coral and algal taxa from Palmyra Atoll, a pristine reef in the central Pacific Ocean. PDF
The Journal of Open Source Software
This python package implements nonlinear time series analysis techniques, also referred to as empirical dynamic modeling. It is based on many of the workflows and routines within TISEAN (Hegger and Schreiber 1999) and (Ye et al. 2017).
Chaos: An Interdisciplinary Journal of Nonlinear Science
Methods in nonlinear time series forecasting and genetic programming applied to these data corroborate that coastal morphology at these scales is predominately driven by nonlinear internal dynamics, which partially mask external forcing signatures. PDF
Master's Thesis
Here, we adjust spatial forecasting to handle discrete data and apply a nonlinear forecasting technique to explore the ubiquity of nonlinear determinism in irregular spatial configurations of coral and algal taxa from Palmyra Atoll, a relatively pristine reef in the central Pacific Ocean. PDF