My academic research focused on theoretical machine learning and optimization, but theory is most useful insofar as it drives practical innovation. For eleven years I have applied this philosophy to the financial power markets in order to successfully adapt to the nuances of the most volatile markets in the world. More recently my efforts have been more holistic, building teams and products that transcend the organization and are marketed externally to add value to the company and the industry.
Solea Energy |
Vancouver, BC, Canada
|
Vice President of Research |
09/2021 to Present
|
I orchestrate a team of developers, researchers, and external academic collaborators to develop an analytics engine and software for the financial power markets. Our team has two mandates: first, we improve the risk-adjusted profitability of traders internally to promote our core business; second, we develop tools and products for a burgeoning branch of the business focused on algorithmic solutions to the efficient management of physical assets. As part of the leadership team at Solea I help drive our strategic decisions by identifying and validating growth areas with an eye to the opportunity cost of pursuing different options.
Boulder, CO
|
Director of Quantitative Strategies |
04/2020 to 09/2021
|
I create probabilistic demand and price forecasts of the power markets, the most volatile markets in the world. I conduct thorough risk analyses as the strategy, trader, team, and company levels to ensure that capital is efficiently deployed to maximize return per unit risk. I develop and deploy front-end mechanisms to help (human) traders create automated strategies powered by machine learning tools, track profit, analyze risk, and manage portfolios. I trade across multiple products in the largest RTOs in the USA.
Boulder, CO
|
Consulting Statistician |
02/2019 to 04/2020
|
I generate automated strategies for trading in the SPP, MISO, and PJM RTOs across multiple products.
Yes Energy |
Boulder, Colorado
|
Consulting Statistician |
08/2018 to 09/2019
|
I produced interpretable analytics to provide insights to the management team at Yes Energy and develop aspects of the quick signals product. The primary focuses of my work over this time were two-fold: First, to create algorithms to fuse data from the live power sensors into a single index in order to predict LMPs at Western Hub for ICE trading, and second working to develop short term (24 hour) load forecasts with five minute resolution, along with estimates of the uncertainty of the forecast.
eXion Energy |
Boulder, Colorado
|
Consulting Statistician |
01/2016 to 04/2018
|
I applied cutting-edge machine learning techniques to assist in understanding every aspect of the trading process. Projects I oversaw include:
- Forecasting day ahead and real time energy prices.
- Portfolio optimization according to pre-specified objective functions.
- Risk analysis at nodal and portfolio level.
- Fundamentally driven statistical models of congestion prices.
Using these tools, I constructed automated trading strategies for MISO, PJM, and SPP that were profitable in every quarter of operation.
Endurance Energy |
Boulder, Colorado
|
Trader |
09/2011 to 04/2015
|
Using econometric and machine learning techniques I traded virtual day-ahead futures for the electric power grid.
A Nonstationary Designer Space-Time Kernel |
|
Presented at the 2018 Neural Information Processing Systems (NeurIPS) conference, the largest Machine Learning and AI conference in the world. In this work we present a new method for modeling time series data that deals with uncertainty in a natural way.
Sampled Tikhonov Regularization for Large Linear Inverse Problems |
|
Published in Inverse Problems. In this work we present a method for an adaptive parameter to prevent overfitting in the big data domain.
Intraday Load Forecasts with Uncertainty |
|
Published in Energies Journal. In this work we describe a method for performing accurate short term load forecasts with rigorous estimates of the uncertainty.
A stochastic subspace approach to gradient-free optimization in high dimensions |
|
Submitted to Springer Journal Optimization and Applications. In this work we develop a method for optimizing extremely large scale problems for which access to the gradient is not feasible.
Zeroth order optimization with orthogonal random directions |
|
Under revisions at Mathematical Programming. In this work we analyze methods for optimization when the function, but not the derivative, can be queried
Colorado School of Mines |
09/2015 to 04/2020
|
Colorado School of Mines |
09/2015 to 05/2018
|
University of Colorado |
09/2006 to 05/2011
|
Visiting Researcher · University of Genova, under Lorenzo Rosasco |
04/2019 to 08/2019
|
I worked in the lab of Lorenzo Rosasco for the final summer of my PhD. While there I was also a TA for the Machine Learning Crash Course (MLCC) hosted by the LCSL (laboratory of computational and statistical learning), MALGA (machine learning Genova center).
Gene Golub Summer School · Inverse Problems: Systematic Integration of Data with Models under Uncertainty |
Summer/2018
|
Internationally competitive summer school taught by world class researchers to 50 PhD students from around the world.
Regularization in Machine Learning |
Summer/2017
|
Internationally competitive summer school taught by world class researchers to 40 PhD students from around the world.
Colorado School of Mines · Willy Hereman Endowed Scholarship |
05/2019
|
Awarded to an outstanding first generation graduate student.
Colorado School of Mines · Poate Fellowship |
12/2015
|
Awarded annually to one outstanding first-year graduate student in the Applied Mathematics and Statistics department.
American Statistical Association · Maurice Davies Award |
Summer/2018
|
Awarded annually to one outstanding statistics PhD student in the front range of Colorado and Wyoming.
|