Parametric models and non-parametric machine learning models for predicting option prices: Empirical comparison study over KOSPI 200 Index options

作者：

Highlights：

• Empirical comparison study over 10 years of KOSPI 200 Index were given.

• Machine learning methods significantly outperform parametric methods.

• Gaussian process model delivers the most outstanding performance in prediction.

摘要

•Empirical comparison study over 10 years of KOSPI 200 Index were given.•Machine learning methods significantly outperform parametric methods.•Gaussian process model delivers the most outstanding performance in prediction.

论文关键词：Option pricing,Gaussian processes,Support vector machines,Artificial neural network,Black–Scholes model,Heston model,Merton model

论文评审过程：Available online 25 February 2014.

论文官网地址：https://doi.org/10.1016/j.eswa.2014.01.032