Fuzzy Decision Mechanism for Stock Market Trading

Abstract

Investors utilize various methods to make buy/sell decisions depending on time-dependent stock market prices. In this study, a fuzzy decision mechanism that makes buy/sell decisions for stock market data is proposed. The proposed mechanism generates instant buy/sell decisions by evaluating three popular indicators which are the Moving Average Convergence/Divergence (MACD) Strategy, Chaikin Money Flow (CMF), and Stochastic Oscillator (SO). The fuzzy decision mechanism has three inputs and one output which are defined by using Gaussian membership functions. In the design of the decision mechanism, Mamdani inference method is used and the rule table is defined by nine rules. Therefore, the structure of the proposed fuzzy decision mechanism is simple and straightforward. The performance of the proposed fuzzy decision mechanism is compared with two classical decision mechanisms using MACD and CMF indicators separately. In the comparisons, the stock market data of Borsa Istanbul 100 Index (XU100), Dow Jones Industrial Average (^DJI), and S&P 500 (^GSPC) are used. The comparison results show that the proposed fuzzy decision mechanism provides significantly higher profit than the mechanisms using either MACD or CMF indicators for all stock market data.

Keywords

• Fuzzy logic
• Stock market
• Technical indicators
• Technical analysis
• XU100
• ^DJI
• ^GSPC

Hisse Senedi Piyasası için Bulanık Karar Mekanizması

Öz

Yatırımcılar, hisse senedi/borsa değerlerinin zamana bağlı olarak alım/satım kararlarını vermek için çeşitli yöntemler kullanmaktadırlar. Bu çalışmada, hisse senedi piyasası verilerine ilişkin alım/satım kararlarını veren bir bulanuk karar mekanizması önerilmiştir. Önerilen çıkarım mekanizması üç popular gösterge olan Hareketli Ortalama Yakınsama/Iraksama (MACD), Chaikin Para Akışı (CMF) ve Stokastik Osilatör (SO) göstergelerini değerlendirerek anlık alım/satım kararları üretmektedir. Bulanık karar mekanizmasının, Gauss üyelik fonksiyonları kullanılarak tanımlanmış üç adet girişi ve bir adet çıkışı vardır. Karar mekanizmasının tasarımında Mamdani çıkarım yöntemi kullanılmış ve kural tablosu dokuz kural ile tanımlanmıştır. Bu nedenle, önerilen bulanık karar mekanizmasının yapısı basit ve anlaşılırdır. Önerilen bulanık karar mekanizmasının performansı, MACD ve CMF göstergelerini ayrı ayrı kullanan iki klasik karar mekanizması ile karşılaştırılmıştır. Karşılaştırmalarda Borsa Istanbul 100 Endeksi (BIST100), Dow Jones Borsası Endüstri Endeksi (^DJI) ve S&P 500 (^GSPC) borsa verileri kullanılmıştır. Karşılaştırma sonuçları, önerilen bulanık karar mekanizmasının tüm borsa verileri için MACD veya CMF göstergelerini kullanan klasik karar mekanizmalarından önemli ölçüde daha yüksek kar sağladığını göstermektedir.

Anahtar Kelimeler

• bulanık mantık
• borsa
• teknik göstergeler
• teknik analiz
• BIST100
• ^DJI
• ^GSPC

References

1. Acheme, D., Vincent, O., Folorunso, O. and Isaac, O. (2014). A predictive stock market technical analysis using fuzzy logic, Computer and Information Science 7. doi: 10.5539/cis.v7n3p1.
2. Adebiyi, A. A., Ayo, C.K. and Otokiti S.O. (2011). Fuzzy-neural model with hybrid market indicators for stock forecasting, Int. J. Electron. Financ. 5 (3), 286–297. doi: 10.1504/IJEF.2011.041342.
3. Altay, E. and Satman, M.H. (2005). Stock market forecasting: Artificial neural networks and linear regression comparison in an emerging market, Journal of Financial Management and Analysis 18(2), 18–33.
4. Altunkaynak, A. (2010). A predictive model for well loss using fuzzy logic approach. Hydrol. Process., 24: 2400-2404. https://doi.org/10.1002/hyp.7642.
5. Appel, G. and Dobson, E. (2008). Understanding MACD (Moving Average Convergence Divergence), Traders Press, Inc.
6. Atiya, A., Talaat, N. and Shaheen, S. (1997). An efficient stock market forecasting model using neural network, in: Proceedings of International Conference on Neural Networks, pp. 2112–2115.
7. Atsalakıs, G., Protoparadakıs, E. and Valavanıs, K. (2015). Stock trend forecasting in turbulent market periods using neuro-fuzzy systems, Oper Res Int J 16, 245–269doi: 10.1007/s12351-015-0197-6.
8. Avcı, E. (2007). Forecasting daily and sessional returns of the ise-100 index with neural network model, Journal of Dogus University 8(2), 128–142.

9. Boyacioglu, M. and Avci, D. (2010). An adaptive network-based fuzzy inference system (anfis) for the prediction of stock market return: The case of the istanbul stock exchange, Expert Systems with Applications 37, 7908–7912. doi: 10.1016/j.eswa.2010.04.045.
10. Cohen, G. (2020). Algorithmic setups for trading popular u.s. etfs, Cogent Economics & Finance 8 (1), 1720056. doi: 10.1080/23322039.2020.1720056.
11. Gamil, A., Elfouly, R.S. and Darwish, N. (2007). Stock technical analysis using multi agent and fuzzy logic, in: World Congress on Engineering.
12. Huang, Q., Yang, J., Feng, X., Liew, A.W. and Li, X. (2020). Automated trading point forecasting based on bicluster mining and fuzzy inference, IEEE Transactions on Fuzzy Systems 28 (2), 259–272. doi: 10.1109/TFUZZ.2019.2904920.
13. Lauguico, S., Concepcion II, R., Alejandrino, J., Macasaet, D., Tobias, R.R., Bandala, A. and Dadios, E. (2019). A fuzzy logic-based stock market trading algorithm using bollinger bands, in: 2019 IEEE 11th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management (HNICEM), pp. 1–6. doi: 10.1109/HNICEM48295.2019.9072734.
14. Mamdani, E. and Assilian, S. (1975). An experiment in linguistic synthesis with a fuzzy logic controller, International Journal of Man-Machine Studies 7 (1), 1–13. doi: https://doi.org/10.1016/S0020-7373(75)80002-2.
15. Murphy, J.J. (1999). Technical Analysis of the FinancialMarkets, Institute of Finance, New York.
16. Naranjo, R., Arroyo, J. and Santos, M. (2018). Fuzzy modeling of stock trading with fuzzy candlesticks, Expert Systems with Applications 93, 15–27. doi: 10.1016/j.eswa.2017.10.002.
17. Rosillo, R., Fuente, D. and Brugos, José A. (2013). Technical analysis and the Spanish stock exchange: testing the RSI, MACD, momentum and stochastic rules using Spanish market companies. Applied Economics. 45. 1541-1550. 10.1080/00036846.2011.631894.
18. Su, C.H. and Cheng, C.H. (2016). A hybrid fuzzy time series model based on anfis and integrated nonlinear feature selection method for forecasting stock, Neurocomputing 205, 264–273. doi: 10.1016/j.neucom.2016.03.068.
19. Thomsett, M.C. (2010). CMF-Chaikin Money Flow: Changes Anticipating Price Reversal, FT Press.