Abstract
The reasonable pricing of options can effectively help investors avoid risks and obtain benefits, which plays a very important role in the stability of the financial market. The traditional single option pricing model often fails to meet the ideal expectations due to its limited conditions. Combining an economic model with a deep learning model to establish a hybrid model provides a new method to improve the prediction accuracy of the pricing model. This includes the usage of real historical data of about 10,000 sets of CSI 300 ETF options from January to December 2020 for experimental analysis. Aiming at the prediction problem of CSI 300ETF option pricing, based on the importance of random forest features, the Convolutional Neural Network and Long Short-Term Memory model (CNN-LSTM) in deep learning is combined with a typical stochastic volatility Heston model and stochastic interests CIR model in parameter models. The dual hybrid pricing model of the call option and the put option of CSI 300ETF is established. The dual-hybrid model and the reference model are integrated with ridge regression to further improve the forecasting effect. The results show that the dual-hybrid pricing model proposed in this paper has high accuracy, and the prediction accuracy is tens to hundreds of times higher than the reference model; moreover, MSE can be as low as 0.0003. The article provides an alternative method for the pricing of financial derivatives.
Highlights
The reasonable pricing of options can effectively help investors avoid risks and obtain benefits, which plays a very important role in the stability of the financial market
The prediction effect of the deep neural network model is significantly better. The performance of both the single neural network model and the hybrid model is distinctly improved compared with the former. This shows from another level that there are some price-influencing factors in the option market that cannot be described by parameter models
The experimental results are presented in Table 7: It can be observed from the Table 7 that, in the ridge regression integration of the call and put option pricing models, the coefficient of the prediction result of the dual-mixed model is the largest, and the coefficient of the prediction result of the single parameter model is negative, showing a negative correlation with the dependent variable
Summary
Option is an important tool for investors to obtain benefits and avoid risks in financial derivatives, and option pricing has always been a hot research objective of scholars. (SVM), Decision Tree [25] (DT), Artificial Neural Network [26] (ANN), etc In this method, the model only needs to focus on the relationship between the features in the option data, without considering the complex economic principles and rigorous mathematical derivation, which provides a new modeling idea for option pricing. Financial option data often have high dimensional and nonlinear characteristics, which results in unsatisfactory classification effects, affecting the overall performance of its pricing model. Effective analysis of option pricing feature data can reduce the complexity of the pricing model and can greatly improve the prediction accuracy and stability of the model. Feature-processed data the model and effectively improves prediction accuracy, which is more suitable for input greatly reduces the running time of the model and effectively improves the option accuracy, pricing inwhich the real market. According to the actual tion market transaction data, three groups of sixteen candidate characteristic variables are option market transaction data, three groups of sixteen candidate characteristic variables listed, as shown in Table are listed, as shown in Table
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
