High-frequency trading requires fast data processing without information lags for precise stock price forecasting. This high-paced stock price forecasting is usually based on vectors that need to be treated as sequential and time-independent signals due to the time irregularities that are inherent in high-frequency trading. A well-documented and tested method that considers these time-irregularities is a type of recurrent neural network, named long short-term memory neural network. This type of neural network is formed based on cells that perform sequential and stale calculations via gates and states without knowing whether their order, within the cell, is optimal. In this paper, we propose a revised and real-time adjusted long short-term memory cell that selects the best gate or state as its final output. Our cell is running under a shallow topology, has a minimal look-back period, and is trained online. This revised cell achieves lower forecasting error compared to other recurrent neural networks for online high-frequency trading forecasting tasks such as the limit order book mid-price prediction as it has been tested on two high-liquid US and two less-liquid Nordic stocks.

翻译：高频交易需要快速处理数据且无信息滞后，以实现精确的股票价格预测。这种高节奏的股票价格预测通常基于向量，这些向量需被视为序列化且与时间无关的信号，因为高频交易本身存在时间不规则性。一种经过充分文献记载与测试、并考虑了这些时间不规则性的方法是递归神经网络，即长短时记忆神经网络。这种神经网络由若干单元构成，这些单元通过门控与状态执行序列化且稳定的计算，但无法确定单元内部的计算顺序是否为最优。本文提出一种经过修订并可实时调整的长短时记忆单元，该单元选择最佳的门控或状态作为最终输出。我们的单元采用浅层拓扑结构，具有最小回望周期，并实现在线训练。与其他递归神经网络相比，这种修订后的单元在在线高频交易预测任务（如限价订单簿中间价格预测）中实现了更低的预测误差，这已通过两只高流动性美股和两只低流动性北欧股票进行了测试。