Online Hybrid Neural Network for Stock Price Prediction: A Case Study of High-Frequency Stock Trading in the Chinese Market

Time-series data, which exhibit a low signal-to-noise ratio, non-stationarity, and non-linearity, are commonly seen in high-frequency stock trading, where the objective is to increase the likelihood of profit by taking advantage of tiny discrepancies in prices and trading on them quickly and in huge quantities. For this purpose, it is essential to apply a trading method that is capable of fast and accurate prediction from such time-series data. In this paper, we developed an online time series forecasting method for high-frequency trading (HFT) by integrating three neural network deep learning models, i.e., long short-term memory (LSTM), gated recurrent unit (GRU), and transformer; and we abbreviate the new method to online LGT or O-LGT. The key innovation underlying our method is its efficient storage management, which enables super-fast computing. Specifically, when computing the forecast for the immediate future, we only use the output calculated from the previous trading data (rather than the previous trading data themselves) together with the current trading data. Thus, the computing only involves updating the current data into the process. We evaluated the performance of O-LGT by analyzing high-frequency limit order book (LOB) data from the Chinese market. It shows that, in most cases, our model achieves a similar speed with a much higher accuracy than the conventional fast supervised learning models for HFT. However, with a slight sacrifice in accuracy, O-LGT is approximately 12 to 64 times faster than the existing high-accuracy neural network models for LOB data from the Chinese market.

[1]  Sang Won Yoon,et al.  Prediction of stock price direction using a hybrid GA-XGBoost algorithm with a three-stage feature engineering process , 2021, Expert Syst. Appl..

[2]  Zihao Zhang,et al.  Multi-Horizon Forecasting for Limit Order Books: Novel Deep Learning Approaches and Hardware Acceleration using Intelligent Processing Units , 2021, ArXiv.

[3]  Jiadong Guo,et al.  Hierarchical Multi-Scale Gaussian Transformer for Stock Movement Prediction , 2020, IJCAI.

[4]  Herbert Kimura,et al.  Literature review: Machine learning techniques applied to financial market prediction , 2019, Expert Syst. Appl..

[5]  Leopoldo Catania,et al.  Dynamic Discrete Mixtures for High-Frequency Prices , 2019, Journal of Business & Economic Statistics.

[6]  Stefan Zohren,et al.  DeepLOB: Deep Convolutional Neural Networks for Limit Order Books , 2018, IEEE Transactions on Signal Processing.

[7]  Matthew Baron,et al.  Risk and Return in High-Frequency Trading , 2017, Journal of Financial and Quantitative Analysis.

[8]  M. Gabbouj,et al.  Tensor representation in high-frequency financial data for price change prediction , 2017, 2017 IEEE Symposium Series on Computational Intelligence (SSCI).

[9]  Alexandros Iosifidis,et al.  Forecasting Stock Prices from the Limit Order Book Using Convolutional Neural Networks , 2017, 2017 IEEE 19th Conference on Business Informatics (CBI).

[10]  G. Dionne,et al.  Asymmetric Effects of the Limit Order Book on Price Dynamics , 2016, Journal of Empirical Finance.

[11]  Yuan Zhang,et al.  Modelling high-frequency limit order book dynamics with support vector machines , 2015 .

[12]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[13]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[14]  Saptarsi Goswami,et al.  STUDY OF EFFECTIVENESS OF TIME SERIES M ODELI NG (ARIMA) INFORECASTING STOCK PRICES , 2014 .

[15]  Stacy Williams,et al.  Limit order books , 2010, 1012.0349.

[16]  S. Hochreiter,et al.  Long Short-Term Memory , 1997, Neural Computation.

[17]  J. Goodnight.  A Tutorial on the SWEEP Operator , 1979 .

[18]  A. Beaton.  THE USE OF SPECIAL MATRIX OPERATORS IN STATISTICAL CALCULUS , 1964 .

[19]  Changjun Zhou,et al.  Stock Prediction Based on Genetic Algorithm Feature Selection and Long Short-Term Memory Neural Network , 2021, IEEE Access.