Log In Sign Up

Evaluating data augmentation for financial time series classification

by   Elizabeth Fons, et al.

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 (≈30K samples), augmentation methods achieve up to 400% improvement in risk adjusted return performance; for a larger stock dataset (≈300K samples), results show up to 40% improvement.


page 1

page 2

page 3

page 4


Adaptive Weighting Scheme for Automatic Time-Series Data Augmentation

Data augmentation methods have been shown to be a fundamental technique ...

Forecasting Market Prices using DL with Data Augmentation and Meta-learning: ARIMA still wins!

Deep-learning techniques have been successfully used for time-series for...

Accuracy Improvement for Fully Convolutional Networks via Selective Augmentation

Deep learning methods have shown suitability for time series classificat...

Augmentation Backdoors

Data augmentation is used extensively to improve model generalisation. H...

Data Augmentation for Deep Candlestick Learner

To successfully build a deep learning model, it will need a large amount...

Prior knowledge distillation based on financial time series

One of the major characteristics of financial time series is that they c...

Code Repositories