European option pricing based on the multi-layer forward BP neural network
Yuqi Wang, Zuoliang Xu · 2024
By applying the multi-layer forward BP neural network to European option pricing, the TensorFlow platform is used to build the network. The interpolation features combine with numerical methods and statistical methods are used to predict the training features reasonably, which improves the accuracy of the predicted option price. In this paper, we take the SSE 50 ETF option data to conduct numerical experiments and empirical analysis based on multi-layer forward BP neural network methods(four-layer, six-layer and eight-layer forward BP neural network). Furthermore, we compare the proposed muti-layer methods, the B-S method and the two-layer method, which verify the effectiveness of the model in this paper. In addition, we compare the four-layer, six-layer, and eight-layer forward BP neural network methods. The results illustrate that the four-layer and six-layer neural network methods are better than the other models, and the eight-layer neural network will occur the phenomenon of over-fitting.