Unit:
Specialty Financial Analysis and PolicyLibrary of the Faculty of Economics and of the Faculty of Business Administration
Supervisors info:
Georgios Dotsis, Associate Professor in Finance, Department of Economics, National and Kapodistrian University of Athens
Original Title:
Implied Volatility Sign Prediction Using Machine Learning
Translated title:
Implied Volatility Sign Prediction Using Machine Learning
Summary:
This thesis employs machine learning algorithms in order to forecast the future sign of the market implied volatility. More precisely, a dataset of 16 macroeconomic and financial indicators is being used to anticipate the VIX, VXO, VXN, VDAX, and V2TX's following month's sign. For this subject, a number of classification models are employed and evaluated, in order to find the best performing model on each index. The study's conclusion is that by picking and developing a number of indicators and appropriately altering these indicators to assist the models' performance, the sign of implied volatility can be forecasted using machine learning models.
Main subject category:
Social, Political and Economic sciences
Keywords:
Implied Volatility, Machine Learning, Forecasting, Classification Models