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.
Trading Under Uncertainty: A Distribution-Based Strategy for Futures Markets Using FutureQuant Transformer
Department of Computer Science & Engineering（计算机科学与工程系）；Ohio State University（俄亥俄州立大学）；School of Computing and Data Science（计算与数据科学学院）；Hong Kong University（香港大学）；Tandon School of Engineering（坦顿工程学院）；New York University（纽约大学）；College of Science, Mathematics and Technology（科学、数学与技术学院）；Wenzhou Kean University（温州凯恩大学）；Faculty of Science and Technology（科学与技术学院）；Beijing Normal-Hong Kong Baptist University（北京师范大学-香港 Baptist大学）
University College London（伦敦大学学院）；UCL Centre for Blockchain Technologies（伦敦大学学院区块链技术中心）；London School of Economics（伦敦政治经济学院）；Systemic Risk Centre（系统风险中心）
