Today, we’re joined by Stuart Reid, Chief Scientist at NMRQL Research. NMRQL, based in Stellenbosch, South Africa, is an investment management firm that uses machine learning algorithms to make adaptive, unbiased, scalable, and testable trading decisions for its funds. In our conversation, Stuart and I dig into the way NMRQL uses machine learning and deep learning models to support the firm’s investment decisions. In particular, we focus on techniques for modeling non-stationary time-series, of which financial markets are just one example. We start from first principles and look at stationary vs non-stationary time-series, discuss some of the challenges of building models using financial data, explore issues like model interpretability, and much more. This was a very insightful conversation, which I expect will be very useful not just for those in the fintech space. Check out the complete show notes for this episode at twimlai.com/talk/203.