Evaluating data augmentation for financial time series classification
This work addresses the challenge of small, noisy financial data for traders and investors, but it is incremental as it applies existing augmentation methods to a new domain.
The paper tackles the problem of improving financial time series classification by evaluating data augmentation methods, showing that they significantly enhance risk-adjusted returns, with up to 400% improvement on a small dataset and 40% on a larger one.
Data augmentation methods in combination with deep neural networks have been used extensively in computer vision on classification tasks, achieving great success; however, their use in time series classification is still at an early stage. This is even more so in the field of financial prediction, where data tends to be small, noisy and non-stationary. In this paper we evaluate several augmentation methods applied to stocks datasets using two state-of-the-art deep learning models. The results show that several augmentation methods significantly improve financial performance when used in combination with a trading strategy. For a relatively small dataset ($\approx30K$ samples), augmentation methods achieve up to $400\%$ improvement in risk adjusted return performance; for a larger stock dataset ($\approx300K$ samples), results show up to $40\%$ improvement.