Incorporating prior financial domain knowledge into neural networks for implied volatility surface prediction
This work addresses the challenge of accurate implied volatility prediction for financial practitioners by integrating domain-specific constraints, though it is incremental in applying neural networks to this domain.
The paper tackled the problem of predicting implied volatility surfaces by incorporating financial domain knowledge into neural network design, resulting in a model that outperformed benchmarks on S&P 500 index data over 20 years and empirically satisfied key financial conditions.
In this paper we develop a novel neural network model for predicting implied volatility surface. Prior financial domain knowledge is taken into account. A new activation function that incorporates volatility smile is proposed, which is used for the hidden nodes that process the underlying asset price. In addition, financial conditions, such as the absence of arbitrage, the boundaries and the asymptotic slope, are embedded into the loss function. This is one of the very first studies which discuss a methodological framework that incorporates prior financial domain knowledge into neural network architecture design and model training. The proposed model outperforms the benchmarked models with the option data on the S&P 500 index over 20 years. More importantly, the domain knowledge is satisfied empirically, showing the model is consistent with the existing financial theories and conditions related to implied volatility surface.