Machine learning asset allocation

A QuantMinds Digital Week webinar presented by Marcos Lopez de Prado, CIO, True Positive Technologies Convex optimisation solutions tend to be unstable, to the point of entirely offsetting the benefits of optimisation. For example, in the context of financial applications, it is known that portfolios optimised in sample often underperform the naïve (equal weights) allocation out of sample. This instability can be traced back to two sources: (1) noise in the input variables; and (2) signal structure that m