ABOUT
I got started in analytics over half a decade ago with a company I founded called Harefoot Logistics, which leveraged analytics on top of newly mandated electronic logging devices to help truckers improve ROI and drive routes closer to home.
I was able to sharpen my product sense at a SaaS startup called DOmedia where I was brought aboard to grow their "Airbnb for billboards" marketplace, BillboardsIn.com. We leveraged product & marketing a/b testing, machine learning and data visualization to drive the growth of billboardsIn from its humble beginnings to exceeding a million dollars in revenue after just one year. This success would not have been possible without meticulously testing the customer experience and optimizing each aspect of the funnel from marketing to operations to sales.
I continued my work on a/b testing, data visualization and machine learning at Root Insurance. I came aboard to work on pricing, but was soon promoted to telematics. I built visualizations and dashboards that helped Product and Data Science directors understand how new driving trends were impacting their models and provided insights into features that could improve performance. I also worked with the design team and engineers to create a/b tests and experiments aimed at increasing location permission enablement and maintaining user engagement with the application.
I've always had a passion for the markets and have enjoyed using my background to make investment decisions and build trading models. When the pandemic hit and the stock market briefly crashed, I decided that I wanted to focus on building market neutral strategies with stock options to ensure that my returns were detached from major market movements. There was only one problem, there were no open source python packages to backtest derivatives trading strategies like there was for backtesting stock trades. So I built one! My proprietary backtest package (documentation is public), runs on a serverless architecture in the AWS cloud, which enables excellent scalability and a lean cost structure. With this framework now in place, I'm able to focus on building out machine learning models to predict derivatives pricing components such as underlying returns and implied volatility.
