Lim, YS;
Gorse, D;
(2020)
Deep Recurrent Modelling of Stationary Bitcoin Price Formation Using the Order Flow.
In: Rutkowski, L and Scherer, R and Korytkowski, M and Pedrycz, W and Tadeusiewicz, R and Zurada, JM, (eds.)
ICAISC: International Conference on Artificial Intelligence and Soft Computing.
(pp. pp. 170-179).
Springer: Zakopane, Poland.
Preview |
Text
DeepRecurrentModellingOfStationaryPriceFormationUsingTheOrderFlow.pdf - Accepted Version Download (554kB) | Preview |
Abstract
In this paper we present a deep recurrent model based on the order flow for the stationary modelling of the directional movements of high-frequency prices. The formation of prices seen on the price chart of a stock or currency at any timescale are driven by the order flow, which is the microsecond streams of orders arriving at the exchange. In our experiments, we use high-frequency Bitcoin data to train our models. We train a deep recurrent neural network on the order flow to model the directional price movement given a sequence of order flow. We show that without any retraining, the model is temporally stable even as Bitcoin trading shifts into an extremely volatile ”bubble trouble” period. The significance of the result is shown by benchmarking against existing state-of-the-art models for modelling price formation using deep learning. As such the secondary contribution of this paper is also a comparative study between the stationarity of existing deep models in literature.
| Type: | Proceedings paper |
|---|---|
| Title: | Deep Recurrent Modelling of Stationary Bitcoin Price Formation Using the Order Flow |
| Event: | 19th International Conference, ICAISC 2020 |
| ISBN-13: | 9783030614003 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1007/978-3-030-61401-0_17 |
| Publisher version: | https://doi.org/10.1007/978-3-030-61401-0_17 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10116731 |
Loading...
Loading...Loading...| 1. |  United States | 9 |
| 2. |  China | 3 |
| 3. |  Hong Kong | 2 |
| 4. |  Brazil | 1 |
| 5. |  Angola | 1 |
| 6. |  South Africa | 1 |
| 7. |  Germany | 1 |
| 8. |  Netherlands | 1 |
| 9. |  Belgium | 1 |
| 10. |  Canada | 1 |
Archive Staff Only
 |
View Item |
