After looking over Scikit-Learns documention, I realized that there wasn’t a cross validation iterator for walk forward optimization.»
This is an excercpt from Paul Wilmott’s Frequently Asked Questions In Quantitative Finance:»
Almost all calculations in finance involve using log returns rather than % returns. There are a number of reasons why log returns are preferred. Estimating beta doesn’t seem like a special case.»
It’s extremely difficult to present an honest backtest because it’s close to impossible to distinguish one from an overfitted one … not unless the audience knows how to ask the right questions.»
I’ve spent the past week learning all I can about Kalman filters. The best description I found was:»
Several months ago, I saw this mural in Wynwood.
This is what a good portfolio looks like.
This is my new blog.»