Axial-LOB: High-Frequency Trading with Axial Attention
This work addresses the challenge of high-frequency trading prediction for financial markets, offering a novel method that improves accuracy while reducing computational complexity.
The paper tackled the problem of predicting stock price movements from limit order book data by proposing Axial-LOB, a fully-attentional deep learning architecture that achieves state-of-the-art directional classification performance across all tested prediction horizons.
Previous attempts to predict stock price from limit order book (LOB) data are mostly based on deep convolutional neural networks. Although convolutions offer efficiency by restricting their operations to local interactions, it is at the cost of potentially missing out on the detection of long-range dependencies. Recent studies address this problem by employing additional recurrent or attention layers that increase computational complexity. In this work, we propose Axial-LOB, a novel fully-attentional deep learning architecture for predicting price movements of stocks from LOB data. By utilizing gated position-sensitive axial attention layers our architecture is able to construct feature maps that incorporate global interactions, while significantly reducing the size of the parameter space. Unlike previous works, Axial-LOB does not rely on hand-crafted convolutional kernels and hence has stable performance under input permutations and the capacity to incorporate additional LOB features. The effectiveness of Axial-LOB is demonstrated on a large benchmark dataset, containing time series representations of millions of high-frequency trading events, where our model establishes a new state of the art, achieving an excellent directional classification performance at all tested prediction horizons.