Research PaperNo Access

Mining subsequent trend patterns from financial time series

Yuqing Wan

http://orcid.org/0000-0003-2002-5996

Department of Computer and Information Science, University of Macau, P. R. China

E-mail Address: qinggor@qq.com

Search for more papers by this author

Raymond Yiu Keung Lau

Department of Information Systems, City University of Hong Kong, P. R. China

E-mail Address: raylau@cityu.edu.hk

Search for more papers by this author

, and

Yain-Whar Si

Department of Computer and Information Science, University of Macau, P. R. China

E-mail Address: fstasp@umac.mo

Search for more papers by this author

https://doi.org/10.1142/S0219691320500101Cited by:8 (Source: Crossref)

Abstract

Chart patterns are one of the important tools used by the financial analysts for predicting future price trends (subsequent trends) in stock markets. Although many works related to the descriptions of chart patterns and several effective methods to identify chart patterns from the financial time series have been proposed in recent years, there is no in-depth study about the general characteristics of the subsequent trends. In this paper, we proposed a general framework for mining subsequent trend for chart patterns. We extensively analyze the characteristics of subsequent trends of chart patterns found with the proposed framework. Based on the analysis, we propose a concept called subsequent trend pattern by mining frequently occurring shapes from these trends. The process of subsequent trend pattern mining was evaluated on a dataset containing 502 time series from S&P 500 and a test dataset containing 494 stocks from Yahoo finance. The proposed concept of subsequent trend pattern provides a solid foundation for the understanding of chart patterns in predicting future price movement and extends the formal definition of chart patterns.

Keywords:

AMSC: 68U35

References

1. B. S. Alhashel, F. W. Almudhaf and J. A. Hansz , Can technical analysis generate superior returns in securitized property markets? Evidence from East Asia markets, Pacific-Basin Finance J. 47 (2018) 92–108. Crossref, Web of Science, Google Scholar
2. D. J. Berndt and J. Clifford , Using dynamic time warping to find patterns in time series, in KDD Workshop, Vol. 10 (Seattle, WA, 1994), pp. 359–370. Google Scholar
3. R. Bisoi, P. Dash and A. Parida , Hybrid variational mode decomposition and evolutionary robust kernel extreme learning machine for stock price and movement prediction on daily basis Appl. Soft Comput. 74 (2019) 652–678. Crossref, Web of Science, Google Scholar
4. T. N. Bulkowski , Encyclopedia of Chart Patterns, 2nd edn. (John Wiley & Sons, 2011). Google Scholar
5. T. N. Bulkowski , Encyclopedia of Candlestick Charts, Vol. 332 (John Wiley & Sons, 2012). Crossref, Google Scholar
6. R. Cervelló-Royo, F. Guijarro and K. Michniuk , Stock market trading rule based on pattern recognition and technical analysis: Forecasting the DJIA index with intraday data, Expert Syst. Appl. 42(14) (2015) 5963–5975. Crossref, Web of Science, Google Scholar
7. Y. Chen and Y. Hao , Integrating principle component analysis and weighted support vector machine for stock trading signals prediction, Neurocomputing 321 (2018) 381–402. Crossref, Web of Science, Google Scholar
8. B. Chiu, E. Keogh and S. Lonardi , Probabilistic discovery of time series motifs, in Proc. Ninth ACM SIGKDD International Conf. Knowledge Discovery and Data Mining (ACM, 2003), pp. 493–498. Crossref, Google Scholar
9. F.-L. Chung, T.-C. Fu, R. Luk and V. Ng , Flexible time series pattern matching based on perceptually important points, in Int. Joint Conf. Artificial Intelligence Workshop on Learning from Temporal and Spatial Data (Seattle, Washington, USA, 2001), pp. 1–7. Google Scholar
10. V. K. Dabhi and S. Chaudhary , Financial time series modeling and prediction using postfix-gp, Comput. Economic. 47(2) (2016) 219–253. Crossref, Web of Science, Google Scholar
11. E. J. De Fortuny, T. De Smedt, D. Martens and W. Daelemans , Evaluating and understanding text-based stock price prediction models, Inf. Process. Management 50(2) (2014) 426–441. Crossref, Web of Science, Google Scholar
12. R. D. Edwards, J. Magee and W. C. Bassetti , Technical Analysis of Stock Trends (CRC Press, 2007). Google Scholar
13. S. Fong, Y.-W. Si and J. Tai , Trend following algorithms in automated derivatives market trading, Expert Syst. Appl. 39(13) (2012) 11378–11390. Crossref, Web of Science, Google Scholar
14. T.-C. Fu, F.-L. Chung, R. Luk and C.-M. Ng , Stock time series pattern matching: Template-based vs. rule-based approaches, Eng. Appl. Artific. Intell. 20(3) (2007) 347–364. Crossref, Web of Science, Google Scholar
15. R. H. Gálvez and A. Gravano , Assessing the usefulness of online message board mining in automatic stock prediction systems, J. Comput. Sci. 19 (2017) 43–56. Crossref, Web of Science, Google Scholar
16. X. Ge and P. Smyth , Deformable Markov model templates for time-series pattern matching, in Proc. Sixth ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining (ACM, 2000), pp. 81–90. Crossref, Google Scholar
17. E. Guariglia , Entropy and fractal antennas, Entropy 18(3) (2016) 84. Crossref, Web of Science, Google Scholar
18. E. Guariglia , Primality, fractality and image analysis, Entropy 21(3) (2019) 304. Crossref, Web of Science, Google Scholar
19. J. Han, J. Pei, Y. Yin and R. Mao , Mining frequent patterns without candidate generation: A frequent-pattern tree approach, Data Min. Knowl. Discov. 8(1) (2004) 53–87. Crossref, Web of Science, Google Scholar
20. S. Hochreiter and J. Schmidhuber , Long short-term memory, Neur. Comput. 9(8) (1997) 1735–1780. Crossref, Web of Science, Google Scholar
21. O. K. International, S&p 500 companies with financial information http://data.okfn.org/data/core/s-and-p-500-companies (Accessed on: 14 Augst 2018). Google Scholar
22. B. M. Kamich , Chart Patterns (Bloomberg Press, New York, 2009). Google Scholar
23. E. Keogh, S. Chu, D. Hart and M. Pazzani , An online algorithm for segmenting time series, in Proc. IEEE Int. Conf. Data Mining, 2001, ICDM 2001 (IEEE, 2001), pp. 289–296. Crossref, Google Scholar
24. E. J. Keogh and M. J. Pazzani , A simple dimensionality reduction technique for fast similarity search in large time series databases, in Knowledge Discovery and Data Mining, Current Issues and New Applications (Springer, 2000), pp. 122–133. Google Scholar
25. S. Kim and P. Smyth , Segmental hidden Markov models with random effects for waveform modeling, The J. Machine Learn. Res. 7 (2006) 945–969. Web of Science, Google Scholar
26. Y. LeCun, Y. Bengio and G. Hinton , Deep learning, Nature 521(7553) (2015) 436–444. Crossref, Web of Science, Google Scholar
27. Y. Li et al., Quick-motif: An efficient and scalable framework for exact motif discovery, in 2015 IEEE 31st Int. Conf. Data Engineering (IEEE, 2015), pp. 579–590. Crossref, Google Scholar
28. J. Liu, Y.-W. Si, D. Zhang and L. Zhou , Trend following in financial time series with multi-objective optimization, Appl. Soft Comput. 66 (2018) 149–167. Crossref, Web of Science, Google Scholar
29. R. T. F. Nazário, J. L. de Silva, V. A. Sobreiro and H. Kimura , A literature review of technical analysis on stock markets, The Quart. Rev. Economic. Fin. 66 (2017) 115–126. Crossref, Web of Science, Google Scholar
30. P. Patel, E. Keogh, J. Lin and S. Lonardi , Mining motifs in massive time series databases, in ICDM 2003, Proc. 2002 IEEE Int. Conf. Data Mining, 2002 (IEEE, 2002), pp. 370–377. Crossref, Google Scholar
31. J.-M. Poggi and M.-C. Viano , An estimate of the fractal index using multiscale aggregates, J. Time Ser. Anal. 19(2) (1998) 221–233, Wiley Online Library. Crossref, Google Scholar
32. T. Rakthanmanon, B. Campana, A. Mueen, G. Batista, B. Westover, Q. Zhu, J. Zakaria and E. Keogh , Searching and mining trillions of time series subsequences under dynamic time warping, in Proc. 18th ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining (ACM, 2012), pp. 262–270. Crossref, Google Scholar
33. T. Rakthanmanon, B. Campana, A. Mueen, G. Batista, B. Westover, Q. Zhu, J. Zakaria and E. Keogh , Addressing big data time series: Mining trillions of time series subsequences under dynamic time warping, ACM Trans. Knowl. Discovery Data (TKDD), 7(3) (2013) 10. Web of Science, Google Scholar
34. J. Rodrigues, D. Folgado, D. Belo and H. Gamboa , Ssts: A syntactic tool for pattern search on time series, Inf. Proc. Manage. 56(1) (2019) 61–76. Crossref, Web of Science, Google Scholar
35. L. Sacchi, C. Larizza, C. Combi and R. Bellazzi , Data mining with temporal abstractions: Learning rules from time series, Data Mining and Knowl. Discov. 15(2) (2007) 217–247. Crossref, Web of Science, Google Scholar
36. A. Sagheer and M. Kotb , Time series forecasting of petroleum production using deep LSTM recurrent networks, Neurocomputing 323 (2019) 203–213. Crossref, Web of Science, Google Scholar
37. M. Shokoohi-Yekta, Y. Chen, B. Campana, B. Hu, J. Zakaria and E. Keogh , Discovery of meaningful rules in time series, in Proc. 21th ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining (ACM, 2015), pp. 1085–1094. Crossref, Google Scholar
38. Y.-W. Si, and J. Yin , OBST-based segmentation approach to financial time series, Eng. Appl. Artific. Intell. 26(10) (2013) 2581–2596. Crossref, Web of Science, Google Scholar
39. Y. Wan and Y.-W. Si , Adaptive neuro fuzzy inference system for chart pattern matching in financial time series, Appl. Soft Comput. 57 (2017) 1–18. Crossref, Web of Science, Google Scholar
40. Y. Wan and Y.-W. Si , A formal approach to chart patterns classification in financial time series, Inf. Sci. 411 (2017) 151–175. Crossref, Web of Science, Google Scholar
41. Y. Wan and Y.-W. Si , A hidden semi-Markov model for chart pattern matching in financial time series, Soft Comput. 22(19) (2018) 6525–6544. Crossref, Web of Science, Google Scholar
42. Yahoo, Yahoo Finance, https://ca.finance.yahoo.com/q/hp?s=YHOO (Accessed on: 14 August 2018). Google Scholar
43. C.-C. M. Yeh, Y. Zhu, L. Ulanova, N. Begum, Y. Ding, H. A. Dau, D. F. Silva, A. Mueen and E. Keogh , Matrix profile I: All pairs similarity joins for time series: A unifying view that includes motifs, discords and shapelets, In 2016 IEEE 16th Int. Conf. Data Mining (ICDM) (IEEE, 2016), pp. 1317–1322. Crossref, Google Scholar
44. H. D. Zhang and Q. Ke , Fractal properties of financial time series, in Key Engineering Materials, Vol. 43 (Trans Tech Publication, 2010), pp. 683–687. Crossref, Google Scholar
45. X. Zhang, Y. Zhang, S. Wang, Y. Yao, B. Fang and S. Y. Philip , Improving stock market prediction via heterogeneous information fusion, Knowledge-Based Syst. 143 (2018) 236–247. Crossref, Web of Science, Google Scholar
46. F. Zhou, H.-M. Zhou, Z. Yang and L. Yang , EMD2FNN: A strategy combining empirical mode decomposition and factorization machine based neural network for stock market trend prediction, Expert Syst. Appl. 115 (2019) 136–151. Crossref, Web of Science, Google Scholar