Predicting Arbitrage-free American Option Prices Using Artificial Neural Network with Pseudo Inputs

Abstract

Machine learning models, which have recently been applied to evaluate financial variables, have a major difficulty to accomplish arbitrage-free valuation. We propose an American style option pricing method using multilayer artificial neural networks with arbitrage-free pseudo inputs. The proposed neural network model was trained with samples composed of market data and pseudo grid points generated by the calibrated parametric models. The trained model found arbitrage-free price or nearest price for each strike price and expiration date. We compared the proposed model with a conventional multilayer neural network model in terms of model prediction using S&P 100 American put options from 2012. The proposed model achieved better prediction performance than the conventional neural network model. In addition, prices obtained from the proposed method were much closer to the arbitrage-free prices from the parametric model.