Stock options pricing via machine learning methods combined with firm characteristics

This paper proposes machine learning-based option pricing models that incorporate firm characteristics. We employ two semi-parametric models, one that uses machine learning to predict the implied volatility and the other to correct the pricing error of the Black-Scholes model and use 114 firm characteristics as well as option-related variables as the input features. Tested on the stock options in the US market, we find that both models outperform a parametric model even without firm characteristics, and firm characteristics significantly enhance the performance of these models. Idiosyncratic volatility, share price, market equity, illiquidity, and firm age are found to be the most important features