Analysis of stock index with a generalized BN-S model: an approach based on machine learning and fuzzy parameters

Abstract

We use the superposition of the Lévy processes to optimize the classic BN-S model. Considering the frequent fluctuations of price parameters difficult to accurately estimate in the model, we preprocess the price data based on fuzzy theory. The price of S&P500 stock index options in the past ten years are analyzed, and the deterministic fluctuations are captured by machine learning methods. The results show that the new model in a fuzzy environment solves the long-term dependence problem of the classic model with fewer parameter changes, and effectively analyzes the random dynamic characteristics of stock index option price time series.