Managing Risks in a Risk-On/Risk-Off Environment

January 30, 2023

Managing Risks in a Risk-On/Risk-Off Environment

Trading and Investing

A firefighter looks up at the remains of the South Tower. (September 13, 2001)

Today we are taking a look at a very timely paper by Cornell Professor Marcos Lopez de Prado.

According to Professor Lopez de Prado, “Every structure has natural frequencies.”

Furthermore, “Minor shocks in these frequencies can bring down any structure, e.g. a bridge.

On November 7, 1940, the Tacoma Narrows Bridge dramatically collapsed into Puget Sound. An example of elementary forced mechanical resonance.

An Investment Universe also has natural frequencies, characterized by its eigenvectors.

The transformation matrix A = preserves the direction of purple vectors parallel to v_λ=1 = [1 −1]^T and blue vectors parallel to v_λ=3 = [1 1]^T. The red vectors are not parallel to either eigenvector, so, their directions are changed by the transformation. The lengths of the purple vectors are unchanged after the transformation (due to their eigenvalue of 1), while blue vectors are three times the length of the original (due to their eigenvalue of 3).

A concentration of risks in the direction of any such eigenvector exposes a portfolio to the possibility of greater than expected losses (indeed, maximum risk for that portfolio size). Even if that portfolio is below the risk limits.

Graph showing mechanical resonance in a mechanical oscillatory system.

This is particularly dangerous in a risk-on/risk-off regime. Managing Risk is not only about limiting its amount. But also controlling how this amount becomes concentrated around the natural frequencies of the investment universe.”

And in conclusion, the Professor’s main points at the end of the day are:

Correlations are a function of the angle between two vectors [law of cosines]. This causes problems in portfolios of more than two holdings.
In addition, correlations and regression analysis can measure risk levels. However they fail to measure risk concentration.