Machine Learning for Financial Risk Management with Python

Chapter 4. Machine Learning-Based Volatility Prediction

The most critical feature of the conditional return distribution is arguably its second moment structure, which is empirically the dominant time-varying characteristic of the distribution. This fact has spurred an enormous literature on the modeling and forecasting of return volatility.

Andersen et al. (2003)

“Some concepts are easy to understand but hard to define. This also holds true for volatility.” This could be a quote from someone living before Markowitz because the way he models volatility is very clear and intuitive. Markowitz proposed his celebrated portfolio theory in which he defined volatility as standard deviation so that from then onward, finance became more intertwined with mathematics.

Volatility is the backbone of finance in the sense that it not only provides an information signal to investors, but it also is an input to various financial models. What makes volatility so important? The answer stresses the importance of uncertainty, which is the main characteristic of the financial model.

Increased integration of financial markets has led to prolonged uncertainty in those markets, which in turn stresses the importance of volatility, the degree at which values of financial assets changes. Volatility used as a proxy of risk is among the most important variables in many fields, including asset pricing and risk management. Its strong presence and latency make it even compulsory to model. Volatility as a risk ...