支持向量机和人工神经网络在期权价格预测中的比较研究

Comparative Study of Support Vector Machine and Artificial Neural Network in Option Price Prediction

期权定价已成为金融市场的重要组成部分之一。由于市场是动态的,准确预测期权价格非常困难。因此,设计和发展了各种机器学习技术来预测期权价格未来趋势。比较了支持向量机(SVM)模型和人工神经网络(ANN)模型在期权价格预测中的有效性。在测试和训练阶段,2种模型都使用公开可用的基准数据集SPY option price-2015进行测试。2种模型均采用主成分分析(PCA)转换后的数据,以达到更好的预测精度。另一方面,为了避免过拟合问题,将整个数据集划分为训练集(70%)和测试集(30%)2组。将支持向量机模型与基于均方根误差(RMSE)的神经网络模型的结果进行了比较。实验结果表明:神经网络模型优于支持向量机模型,预测的期权价格与相应的实际期权价格吻合良好。

Option pricing has become an important part of the financial market.Because the market is dynamic, it is very difficult to accurately predict the option price.Therefore, various machine learning techniques are designed and developed to deal with the problem of predicting the future trend of option price.This paper compares the effectiveness of support vector machine(SVM) model and artificial neural network(ANN) model in option price prediction.In the testing and training phase, both models are tested with the publicly available benchmark data set, spy option price-2015.Both models use the data converted by principal component analysis(PCA) to achieve better prediction accuracy.On the other hand, in order to avoid the over fitting problem, the whole data set is divided into two groups: training set(70%) and test set(30%).The results of support vector machine model and neural network model based on root mean square error(RMSE) are compared.The experimental results show that the neural network model is better than the support vector machine model in that its predicted option price is in good agreement with the corresponding actual option price.