Classifying Sequences of Market Profile using Deep Learning
DOI:
https://doi.org/10.26438/ijcse/v6i9.480485Keywords:
Market Profile, Machine Learning, ConvLSTMAbstract
Since its inception, market profile has been used by traders as a way to assess the market value of a stock. By reading market profile charts, it is possible for traders to assess who is driving the market (buyers or sellers) and make trades accordingly. The spatiotemporal feature of market profile can be used to train a deep learning model for classifying sequences of market profile. This is a novel idea and one that needs to be examined and experimented upon. LSTM networks are structures capable of remembering long term dependencies in time series data. Convolutional Neural Networks, on the other hand help in figuring out patterns in multidimensional data. A python library is built to generate market profile from time series data. Leveraging the power of LSTMs and CNNs, two models are proposed for the classification: FC-LSTM and ConvLSTM. The results show that the proposed models are able to catch patterns amongst profiles and FC-LSTM performs better than ConvLSTM on this task.
References
[1] Ratnesh Kumar Shukla, Ajay Agarwal, Anil Kumar Malviya, "An Introduction of Face Recognition and Face Detection for Blurred and Noisy Images", International Journal of Scientific Research in Computer Science and Engineering, Vol.6, Issue.3, pp.39-43, 2018.
[2] P. Rutravigneshwaran, "A Study of Intrusion Detection System using Efficient Data Mining Techniques", International Journal of Scientific Research in Network Security and Communication, Vol.5, Issue.6, pp.5-8, 2017
[3] K. Greff, R. K. Srivastava, J. Koutník, B. R. Steunebrink and J. Schmidhuber, "LSTM: A Search Space Odyssey," IEEE Transactions on Neural Networks and Learning Systems, Vol. 28, No. 10, pp. 2222-2232, Oct. 2017.
[4] T. Fischer and C. Krauss, ‘‘Deep learning with long short-term memory networks for financial market predictions’’, FAU Discussion Papers in Economics, 2017.
[5] Milosevic, Nikola. “Equity forecast: Predicting long term stock price movement using machine learning.” Journal of Economics Library, Vol. 3, No. 2, pp. 288-294, Jun. 2016.
[6] K. Joshi, H.N. Bharathi, Jyothi Rao, “Stock Trend Prediction using News Sentiment Analysis”, International Journal of Computer Science & Information Technology (IJCSIT), Vol. 8, No. 3, pp67-76, July 2016.
[7] Steidlmayer, J. P. & Hawkins, S. B. “Steidlmayer on Markets: Trading with Market Profile”, John Wiley & Sons, Inc. NJ, 2003.
[8] James F. Dalton, Robert Bevan Dalton, and Eric T. Jones, “Markets in Profile”, John Wiley, New York, 2007.
[9] Krauss, C., Do, X. A., Huck, N., “Deep neural networks, gradient-boosted trees, random forests: Statistical arbitrage on the S&P 500”, European Journal of Operational Research Vol 2, pp. 689-702, 2017.
[10] K. Amudha, S. Padmapriya, D. Saravanan, "Ensemble Forecasting Through Learning Process", International Journal of Computer Sciences and Engineering, Vol. 06, No. 02, pp. 332-335, 2018.
[11] S. Velankar, S. Valecha and S. Maji, "Bitcoin price prediction using machine learning," 20th International Conference on Advanced Communication Technology (ICACT), pp. 144-147, 2018
[12] Kondor, D., Posfai, M., Csabai, I. & Vattay, G. “Do the rich get richer? an empirical analysis of ´ the bitcoin transaction network.” Public Library of Science, Vol. 9, pp. 1–10, 2014.
[13] S. Hochreiter, Y. Bengio, P. Frasconi, J. Schmidhuber, S. C. Kremer, J. F. Kolen, "Gradient flow in recurrent nets: The difficulty of learning long-term dependencies" A Field Guide to Dynamical Recurrent Networks, Piscataway, NJ, USA: IEEE Press, 2001.
[14] X. Shi, Z. Chen, H. Wang, D.-Y. Yeung, W.-K. Wong, and W.-C. Woo, ‘‘Convolutional LSTM network: A machine learning approach for precipitation nowcasting,’’ Neural Information Processing Systems, pp. 802–810, 2015.
[15] Bradley, A. P., “The Use of the Area Under the ROC Curve in the Evaluation of Machine Learning Algorithms”, Pattern Recognition, Vol. 30, No. 6, pp. 1145–1159, 1997.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors contributing to this journal agree to publish their articles under the Creative Commons Attribution 4.0 International License, allowing third parties to share their work (copy, distribute, transmit) and to adapt it, under the condition that the authors are given credit and that in the event of reuse or distribution, the terms of this license are made clear.
