Machine Learning for Financial Risk Management with Python

Chapter 7. Liquidity Modeling

When the music stops, in terms of liquidity, things will be complicated. But as long as the music is playing, you’ve got to get up and dance. We’re still dancing.

Chuck Prince (2007)

Liquidity is another important source of financial risk. However, it has been long neglected, and the finance industry has paid a huge price for modeling risk without considering liquidity.

The causes of liquidity risk are departures from the complete markets and symmetric information paradigm, which can lead to moral hazard and adverse selection. To the extent that such conditions persist, liquidity risk is endemic in the financial system and can cause a vicious link between funding and market liquidity, prompting systemic liquidity risk (Nikolaou 2009).

Tapping into the time lag between a changing value of the variable and its impact on the real market turns out to be a success criterion in modeling. For instance, interest rates, to some extent, diverge from real market dynamics from time to time, and it takes some time to settle. Together with this, uncertainty is the solely source of risk in traditional asset pricing models; however, it is far from reality. To fill the gap between financial models and real-market dynamics, the liquidity dimension stands out. A model with liquidity can better adjust itself to developments in the financial markets in that liquidity affects both the required returns of assets and also the level of uncertainty. Thus, liquidity is quite ...