Style Transfer with Time Series: Generating Synthetic Financial Data
This addresses the challenge of model generalization in finance by generating synthetic data to overcome data scarcity, though it is incremental as it builds on existing generative methods applied to a specific domain.
The paper tackles the problem of training deep learning models for financial markets, which suffer from limited observations and overfitting, by proposing a generative model for financial time series that creates realistic synthetic data, enabling training on millions of simulated paths.
Training deep learning models that generalize well to live deployment is a challenging problem in the financial markets. The challenge arises because of high dimensionality, limited observations, changing data distributions, and a low signal-to-noise ratio. High dimensionality can be dealt with using robust feature selection or dimensionality reduction, but limited observations often result in a model that overfits due to the large parameter space of most deep neural networks. We propose a generative model for financial time series, which allows us to train deep learning models on millions of simulated paths. We show that our generative model is able to create realistic paths that embed the underlying structure of the markets in a way stochastic processes cannot.