Application of Stacking ensemble learning in option implied volatility

Abstract

The change of option implied volatility is the key problem of option risk early warning management. Based on Stacking ensemble learning in machine learning, this paper takes the implied volatility of SSE 50ETF call option as the object, and takes 30 indicators as the characteristics of implied volatility prediction. Random forest (RF), Adaptive Boosting (AdaBoost), Gradient Boosting Decision Tree (GBDT) and Extreme Gradient Boosting (XGBoost), which pertain to the tree-based algorithms, are stacked as base classifiers in the first layer. Combining with cross validation, the output of base classifier is used as the input training of meta classifiers Logistic Regression (LR), Support Vector Machines (SVM) and K-Nearest Neighbor (KNN). The results show that Stacking ensemble learning is better than tree-based algorithms in the prediction of the trend of implied volatility of call options, and the average prediction accuracy can reach 78.09%. At the same time, the Stacking ensemble learning is used for back testing, and the average cumulative return is 70%. The Stacking ensemble learning proposed in this paper improves the prediction performance of implied volatility of call options and provides a new method for investors' investment decision-making.