Using Deep Learning for price prediction by exploiting stationary limit order book features
This work addresses the problem of price prediction for quantitative finance, but it is incremental as it builds on existing deep learning methods with a new feature construction approach.
The authors tackled the challenge of applying deep learning to non-stationary financial data by proposing a new method to construct stationary features, enabling effective prediction of mid price movements in limit order books. They developed a novel combined CNN-LSTM model that outperformed individual models in tested prediction horizons.
The recent surge in Deep Learning (DL) research of the past decade has successfully provided solutions to many difficult problems. The field of quantitative analysis has been slowly adapting the new methods to its problems, but due to problems such as the non-stationary nature of financial data, significant challenges must be overcome before DL is fully utilized. In this work a new method to construct stationary features, that allows DL models to be applied effectively, is proposed. These features are thoroughly tested on the task of predicting mid price movements of the Limit Order Book. Several DL models are evaluated, such as recurrent Long Short Term Memory (LSTM) networks and Convolutional Neural Networks (CNN). Finally a novel model that combines the ability of CNNs to extract useful features and the ability of LSTMs' to analyze time series, is proposed and evaluated. The combined model is able to outperform the individual LSTM and CNN models in the prediction horizons that are tested.