A New Algorithmic Trading Approach Based on Ensemble Learning and Candlestick Pattern Recognition in Financial Assets

Abstract

Financial assets considered as time series are chaotic in nature. The main goal of investors is to take a position at the right time and in the right direction by making predictions about the future of this chaotic series. These time series consist of the opening, low, high, and closing prices of a certain period. The approaches used to make predictions about trend direction and strength using moving averages and indicators based on them have noise and lag problems as they are obtained statistically. Candlestick charts, on the other hand, reflect the price-based psychology of bear and bull investors, and facilitate the interpretation of price movements by consolidating the said opening, closing, lowest and highest prices in a single image. It is known that it was applied to Japanese rice markets for the first time in history and there are more than 100 candle patterns. In this study, an extensible architecture software framework using factory patterns and an object-oriented approach is proposed for defining candlestick patterns and developing intelligent learning algorithms based on them. In the studies carried out for financial assets, the profit factor, which shows the portfolio gain of the strategy, is used. It is desirable that this number of wins be greater than 1. When the proposed approach is tested for 5 major financial assets, this value was obtained as greater than 1 for all assets. The proposed software framework can also be used in the development of new robotic approaches in terms of being applicable to all kinds of financial assets in every period.

Keywords

• Financial forecasting
• ensemble learning
• pattern recognition
• xgboost

References

1. [1] Filiz, E., Karaboğa, H. A., Akoğul, S. (2017). Bist-50 endeksi değişim değerlerinin sınıflandırılmasında makine öğrenmesi yöntemleri ve yapay sinir ağları kullanımı, Çukurova Üniversitesi Sosyal Bilimler Enstitüsü Dergisi, 26(1), 231-241.
2. [2] Pabuçcu, H. (2019). Borsa endeksi hareketlerinin tahmini: trend belirleyici veri, Selçuk Üniversitesi Sosyal Bilimler Meslek Yüksekokulu Dergisi, 22(1), 246-256.
3. [3] Şişmanoğlu, G., Koçer, F., Önde, M. A., Sahingöz, O. K. (2020). Derin Öğrenme yöntemleri ile borsada fiyat tahmini, Bitlis Eren Üniversitesi Fen Bilimleri Dergisi, 9(1), 434-445.
4. [4] Santur, Y. Deep learning based regression approach for algorithmic stock trading: A case study of the Bist30, Gümüşhane Üniversitesi Fen Bilimleri Enstitüsü Dergisi, 10(4), 1195-1211.
5. [5] Budak, C. (2019). Teknik analiz indikatörlerinin performans karşılaştırması üzerine bir araştırma (Doctoral dissertation), Marmara Universitesi
6. [6] Bozkurt, Y. (2021). Piyasa performans oranlarına göre oluşturulmuş portföylerin getiri oranlarının değerlendirilmesi: BİST 100 endeksi firmaları üzerine bir uygulama (Master's thesis), Aydın Adnan Menderes Üniversitesi, Sosyal Bilimler Enstitüsü.
7. [7] Madbouly, M. M., Elkholy, M., Gharib, Y. M., Darwish, S. M. (2020, April). Predicting stock market trends for japanese candlestick using cloud model, In The International Conference on Artificial Intelligence and Computer Vision (pp. 628-645), Springer, Cham.
8. [8] Kusuma, R. M. I., Ho, T. T., Kao, W. C., Ou, Y. Y., Hua, K. L. (2019). Using deep learning neural networks and candlestick chart representation to predict stock market, arXiv preprint arXiv:1903.12258.

9. [9] Hung, C. C., Chen, Y. J. (2021). DPP: Deep predictor for price movement from candlestick charts, Plos one, 16(6), e0252404.
10. [10] Sadeghi, M., Farid, D. (2021). Investigating candlestick patterns using fuzzy logic in the stock trading system, Turkish Journal of Computer and Mathematics Education (TURCOMAT), 12(13), 7786-7806.
11. [11] Yee, L. L., Mei, H. L., Isharuddin, L. (2021). Ichimoku cloud and japanese candlestick prediction combination pattern approached: the case study of malaysia stock market, Multidisciplinary Applied Research and Innovation, 2(2), 190-196.
12. [12] Lin, Y., Liu, S., Yang, H., Wu, H., Jiang, B. (2021). Improving stock trading decisions based on pattern recognition using machine learning technology, PloS one, 16(8), e0255558.
13. [13] Ardiyanti, N. P. W., Palupi, I., Indwiarti, I. (2021). Trading strategy on market stock by analyzing candlestick pattern using artificial neural network (ann) method, Jurnal Media Informatika Budidarma, 5(4), 1273-1282.
14. [14] Chen, J. H., Tsai, Y. C. (2020). Encoding candlesticks as images for pattern classification using convolutional neural networks, Financial Innovation, 6(1), 1-19.
15. [15] Yassini, S. B., Rahnamay Roodposhti, F., Fallahshams, M. (2019). Analyzing the effectiveness of candlestick technical trading strategies in foreign exchange market, International Journal of Finance & Managerial Accounting, 4(15), 25-41.
16. [16] Gökül, U. (2021). Forecast share price using technical analysis tool, Pacific International Journal, 4(1), 01-06.
17. [17] Ho, T. T., Huang, Y. (2021). Stock price movement prediction using sentiment analysis and candlestick chart representation, Sensors, 21(23), 7957.
18. [18] Lin, Y., Liu, S., Yang, H., Wu, H. (2021). Stock trend prediction using candlestick charting and ensemble machine learning techniques with a novelty feature engineering scheme, IEEE Access, 9, 101433-101446.
19. [19] Ananthi, M., Vijayakumar, K. (2021). Stock market analysis using candlestick regression and market trend prediction (CKRM), Journal of Ambient Intelligence and Humanized Computing, 12(5), 4819-4826.
20. [20] Aycel, Ü., Santur, Y. (2022). A new moving average approach to predict the direction of stock movements in algorithmic trading, Journal of New Results in Science, 11(1), 13-25.
21. [21] Kaynar, T., Yiğit, Ö. E. (2021). Öznitelik mühendisliği ile makine öğrenmesi yöntemleri kullanılarak bıst 100 endeksi değişiminin tahminine yönelik bir yaklaşım, Yaşar Üniversitesi E-Dergisi, 16(64), 1741-1762.
22. [22] Koç, Y. (2021). Makine öğrenmesi ile çok terimli hisse senedi yönlü tahmini; BIST100 örneği/Multinomial direction forecast with machine learning algorithms; BIST100 example (Doctoral dissertation), Kadir Has Üniversitesi.
23. [23] Arslankaya, S., Toprak, Ş. Makine öğrenmesi ve derin öğrenme algoritmalarını kullanarak hisse senedi fiyat tahmini, International Journal of Engineering Research and Development, 13(1), 178-192.
24. [24] Aksoy, B. (2021). Pay senedi fiyat yönünün makine öğrenmesi yöntemleri ile tahmini: Borsa İstanbul örneği, Business and Economics Research Journal, 12(1), 89-110.
25. [25] Akdağ, M., Bozma, G. (2021). Stok akış modeli ve facebook prophet algoritması ile bitcoin fiyatı tahmini/Prediction of bitcoin price with stock to flow model and facebook prophet algorithm, Uluslararası Ekonomi İşletme ve Politika Dergisi, 5(1), 16-30.
26. [26] Demirel, A. C., Hazar, A. (2021). Kripto para değerlerine dayanılarak bist 100 endeks hareketi tahmininde destek vektör makineleri uygulaması, Başkent Üniversitesi Ticari Bilimler Fakültesi Dergisi, 5(1), 27-35.
27. [27] Altunbaş, C. (2021). Derin öğrenme ile hisse senedi piyasası tahmini (Master's thesis), Aydın Adnan Menderes Üniversitesi Sosyal Bilimler Enstitüsü.
28. [28] Ustali, N. K., Tosun, N., Tosun, Ö. (2021). Makine öğrenmesi teknikleri ile hisse senedi fiyat tahmini, Eskişehir Osmangazi Üniversitesi İktisadi ve İdari Bilimler Dergisi, 16(1), 1-16.
29. [29] Tanışman, S., Karcıoğlu, A. A., Aybars, U. G. U. R., Bulut, H. (2021). LSTM sinir ağı ve arıma zaman serisi modelleri kullanılarak bitcoin fiyatının tahminlenmesi ve yöntemlerin karşılaştırılması, Avrupa Bilim ve Teknoloji Dergisi, (32), 514-520.
30. [30] Cohen, G. (2021). Optimizing candlesticks patterns for Bitcoin's trading systems, Review of Quantitative Finance and Accounting, 57(3), 1155-1167.