An Application of the Associate Hopfield Network for Pattern Matching in Chart Analysis
Source abstract
Abstract
Chart patterns are significant for financial market behavior analysis. Lots of approaches have been proposed to detect specific patterns in financial time series data, most of them can be categorized as distance-based or training-based. In this paper, we applied a trainable continuous Hopfield Neural Network for financial time series pattern matching. The Perceptually Important Points (PIP) segmentation method is used as the data preprocessing procedure to reduce the fluctuation. We conducted a synthetic data experiment on both high-level noisy data and low-level noisy data. The result shows that our proposed method outperforms the Template Based (TB) and Euclidean Distance (ED) and has an advantage over Dynamic Time Warping (DTW) in terms of the processing time. That indicates the Hopfield network has a potential advantage over other distance-based matching methods.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Time Series Analysis and Forecasting · Stock Market Forecasting Methods · Neural Networks and Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Division of Computer Science and Technology, Beijing Normal University-Hong Kong Baptist University United International College, Zhuhai 519000, China
Funding
Beijing Normal University – Hong Kong Baptist University United International College
References (30)
Show source-provided references
1. Bulkowski, T.N. (2011). Encyclopedia of Chart Patterns, John Wiley & Sons.
2. A hidden semi-Markov model for chart pattern matching in financial time series10.1007/s00500-017-2703-7 ↗
3. Stock time series pattern matching: Template-based vs. rule-based approaches10.1016/j.engappai.2006.07.003 ↗
4. A review on time series data mining10.1016/j.engappai.2010.09.007 ↗
5. Effect of segmentation on financial time series pattern matching10.1016/j.asoc.2015.10.012 ↗
6. Clustering and Classification for Time Series Data in Visual Analytics: A Survey10.1109/ACCESS.2019.2958551 ↗
7. Representing financial time series based on data point importance10.1016/j.engappai.2007.04.009 ↗
8. Dimensionality reduction for fast similarity search in large time series databases10.1007/PL00011669 ↗
9. Keogh, E., Chu, S., Hart, D., and Pazzani, M. (December, January 29). An online algorithm for segmenting time series. Proceedings of the 2001 IEEE International Conference on Data Mining, San Jose, CA, USA.
10. OBST-based segmentation approach to financial time series10.1016/j.engappai.2013.08.015 ↗
11. Stock market trading rule discovery using technical charting heuristics10.1016/S0957-4174(02)00034-9 ↗
12. Applying genetic algorithms with speciation for optimization of grid template pattern detection in financial markets10.1016/j.eswa.2020.113191 ↗
13. An algorithmic framework for frequent intraday pattern recognition and exploitation in forex market10.1007/s10115-017-1052-2 ↗
14. Zhang, Z., Jiang, J., Liu, X., Lau, R., Wang, H., and Zhang, R. (2010, January 18–22). A real time hybrid pattern matching scheme for stock time series. Proceedings of the Twenty-First Australasian Conference on Database Technologies, Brisbane, Australia.
15. Berndt, D.J., and Clifford, J. (1994). Using Dynamic Time Warping to Find Patterns in Time Series, KDD Workshop.
16. Neural networks and physical systems with emergent collective computational abilities10.1073/pnas.79.8.2554 ↗
17. Do Hebb: The Organization of Behavior, Wiley: New York; 194910.1016/S0361-9230(99)00182-3 ↗
18. Orthogonal Patterns in A Binary Neural Network
19. Efficient Continuous-Time Asymmetric Hopfield Networks for Memory Retrieval10.1162/neco.2010.05-09-1014 ↗
20. Learning Associative Memories by Error Backpropagation10.1109/TNN.2010.2099239 ↗
21. A discrete gradient method to enhance the numerical behaviour of Hopfield networks10.1016/j.neucom.2014.10.091 ↗
22. On the Maximum Storage Capacity of the Hopfield Model
23. Generating exponentially stable states for a Hopfield Neural Network10.1016/j.neucom.2017.08.032 ↗
24. On a Model of Associative Memory with Huge Storage Capacity10.1007/s10955-017-1806-y ↗
25. Do-Hyun, K., Jinha, P., Byungnam, K., and Constantine, D. (2017). Enhanced storage capacity with errors in scale-free Hopfield neural networks: An analytical study. PLoS ONE, 12.10.1371/journal.pone.0184683 ↗
26. O(2)-Valued Hopfield Neural Networks10.1109/TNNLS.2019.2897994 ↗
27. Kim, S.H., Lee, H.S., Ko, H.J., Jeong, S.H., Byun, H.W., and Oh, K.J. (2018). Pattern matching trading system based on the dynamic time warping algorithm. Sustainability, 10.10.20944/preprints201810.0660.v1 ↗
28. Keogh, E.J., and Pazzani, M.J. (1999, January 15–18). Scaling up Dynamic Time Warping to Massive Datasets. Proceedings of the European Conference on Principles of Data Mining and Knowledge Discovery, Prague, Czech Republic.10.1007/978-3-540-48247-5_1 ↗
29. A new approach of integrating piecewise linear representation and weighted support vector machine for forecasting stock turning points10.1016/j.asoc.2019.02.039 ↗
30. Improving the integration of piece wise linear representation and weighted support vector machine for stock trading signal prediction10.1016/j.asoc.2017.03.007 ↗