kryptos
kryptos copied to clipboard
Structural Breaks
Goals
As a machine learning developer, I want to use machine learning to determine structural breaks (whenever an observation is drawn from a distribution that happens to be very different from the distributions that have been observed in the past), so that I can better detect change in time-series data.
Inspiration

Most quantitative models are "fit to fail". -Marcos Lopez de Prado
Source: (New frontiers: Marcos Lopez de Prado on Machine Learning for finance, 2018)