NN de-Americanization: an efficient method to facilitate calibration of American-style options
提出神经网络去美式化方法，从上市美式期权价格快速生成伪欧式价格，用于校准衍生品模型，相比行业方法更准确处理波动率曲面形状和利率非零时的早期行权溢价。
Neural network (NN) de-Americanization produces fast and accurate pseudo-European option prices from listed American option prices, facilitating the calibration of derivative models. The industry approach binomial de-Americanization takes a flat volatility surface as input for each strike and expiration. In contrast, the NN de-Americanization method takes the detailed shape of the volatility surface as an input; this is critical for accurately evaluating the early exercise premium (EEP) when interest rates are not close to zero.