Abstract | ||
---|---|---|
Predicting the price movements of stocks based on deep learning and high-frequency data has been studied intensively in recent years. Especially, limit order book which describes the supply-demand balance of the market is used as features of a neural network. However, these methods do not utilize the properties of market orders. On the other hand, this study encodes information of time and prices of orders into images. This encoding method can take advantage of these properties. Then, we apply machine learning methods, convolutional neural network (CNN) and logistic regression (LR), to order-based features to predict the direction of short-term price movements. The results show that the execution has the highest prediction power than the order and cancellation information. Moreover, the difference between CNN and LR are small and depends on kinds of stocks. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/CIFEr.2019.8759057 | 2019 IEEE Conference on Computational Intelligence for Financial Engineering & Economics (CIFEr) |
Keywords | Field | DocType |
Financial data,order book,convolutional neural network,high-frequency data | Order book,Convolutional neural network,Computer science,Artificial intelligence,Stock (geology),Deep learning,Artificial neural network,Logistic regression,Machine learning,Order (exchange),Encoding (memory) | Conference |
ISSN | ISBN | Citations |
2380-8454 | 978-1-7281-0034-0 | 0 |
PageRank | References | Authors |
0.34 | 4 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Atsuki Nakayama | 1 | 0 | 0.34 |
Kiyoshi Izumi | 2 | 127 | 37.12 |
Hiroki Sakaji | 3 | 30 | 17.97 |
Hiroyasu Matsushima | 4 | 6 | 4.72 |
Takashi Shimada | 5 | 0 | 1.01 |
Kenta Yamada | 6 | 0 | 0.34 |