M&W 파동 패턴과 유전자 알고리즘을 이용한 주식 매매 시스템 개발 = Development of a Stock Trading System Using M & W Wave Patterns and Genetic Algorithms

다국어 초록 (Multilingual Abstract)

Investors prefer to look for trading points based on the graph shown in the chart rather than complex analysis, such as corporate intrinsic value analysis and technical auxiliary index analysis. However, the pattern analysis technique is difficult and computerized less than the needs of users. In recent years, there have been many cases of studying stock price patterns using various machine learning techniques including neural networks in the field of artificial intelligence(AI). In particular, the development of IT technology has made it easier to analyze a huge number of chart data to find patterns that can predict stock prices.
Although short-term forecasting power of prices has increased in terms of performance so far, long-term forecasting power is limited and is used in short-term trading rather than long-term investment. Other studies have focused on mechanically and accurately identifying patterns that were not recognized by past technology, but it can be vulnerable in practical areas because it is a separate matter whether the patterns found are suitable for trading. When they find a meaningful pattern, they find a point that matches the pattern. They then measure their performance after n days, assuming that they have bought at that point in time. Since this approach is to calculate virtual revenues, there can be many disparities with reality.
The existing research method tries to find a pattern with stock price prediction power, but this study proposes to define the patterns first and to trade when the pattern with high success probability appears.
The M & W wave pattern published by Merrill(1980) is simple because we can distinguish it by five turning points. Despite the report that some patterns have price predictability, there were no performance reports used in the actual market. The simplicity of a pattern consisting of five turning points has the advantage of reducing the cost of increasing pattern recognition accuracy. In this study, 16 patterns of up conversion and 16 patterns of down conversion are reclassified into ten groups so that they can be easily implemented by the system. Only one pattern with high success rate per group is selected for trading. Patterns that had a high probability of success in the past are likely to succeed in the future. So we trade when such a pattern occurs. It is a real situation because it is measured assuming that both the buy and sell have been executed.
We tested three ways to calculate the turning point. The first method, the minimum change rate zig-zag method, removes price movements below a certain percentage and calculates the vertex. In the second method, high-low line zig-zag, the high price that meets the n-day high price line is calculated at the peak price, and the low price that meets the n-day low price line is calculated at the valley price. In the third method, the swing wave method, the high price in the center higher than n high prices on the left and right is calculated as the peak price. If the central low price is lower than the n low price on the left and right, it is calculated as valley price. The swing wave method was superior to the other methods in the test results. It is interpreted that the transaction after checking the completion of the pattern is more effective than the transaction in the unfinished state of the pattern.
Genetic algorithms(GA) were the most suitable solution, although it was virtually impossible to find patterns with high success rates because the number of cases was too large in this simulation. We also performed the simulation using the Walk-forward Analysis(WFA) method, which tests the test section and the application section separately. So we were able to respond appropriately to market changes. In this study, we optimize the stock portfolio because there is a risk of over-optimized if we implement the variable optimality for each individual stock. Therefore, we selected the number of constituent stocks as 20 to in...

국문 초록 (Abstract)

투자자들은 기업의 내재가치 분석, 기술적 보조지표 분석 등 복잡한 분석보다 차트(chart)에 나타난 그래프(graph)의 모양으로 매매 시점을 찾는 직관적인 방법을 더 선호하는 편이다. 하지만 패턴(pattern) 분석 기법은IT 구현의 난이도 때문에 사용자들의 요구에 비해 전산화가 덜 된 분야로 여겨진다. 최근에는 인공지능(artificial intelligence, AI) 분야에서 신경망을 비롯한 다양한 기계학습(machine learning) 기법을 사용하여 주가의 패턴을연구하는 사례가 많아졌다. 특히 IT 기술의 발전으로 방대한 차트 데이터를 분석하여 주가 예측력이 높은 패턴을 발굴하는 것이 예전보다 쉬워졌다. 지금까지의 성과로 볼 때 가격의 단기 예측력은 높아졌지만, 장기 예측력은 한계가 있어서 장기 투자보다 단타 매매에서 활용되는 수준이다. 이외에 과거 기술력으로 인식하지 못했던패턴을 기계적으로 정확하게 찾아내는 데 초점을 맞춘 연구도 있지만 찾아진 패턴이 매매에 적합한지 아닌지는별개의 문제이기 때문에 실용적인 부분에서 취약할 수 있다. 본 연구는 주가 예측력이 있는 패턴을 찾으려는기존 연구 방법과 달리 패턴들을 먼저 정의해 놓고 확률기반으로 선택해서 매매하는 방법을 제안한다. 5개의전환점으로 정의한 Merrill(1980)의 M&W 파동 패턴은 32가지의 패턴으로 시장 국면 대부분을 설명할 수 있다.
전환점만으로 패턴을 분류하기 때문에 패턴 인식의 정확도를 높이기 위해 드는 비용을 줄일 수 있다. 32개 패턴으로 만들 수 있는 조합의 수는 전수 테스트가 불가능한 수준이다. 그래서 최적화 문제와 관련한 연구들에서가장 많이 사용되고 있는 인공지능 알고리즘(algorithm) 중 하나인 유전자 알고리즘(genetic algorithm, GA)을 이용하였다. 그리고 미래의 주가가 과거를 반영한다 해도 같게 움직이지 않기 때문에 전진 분석(walk-forward analysis, WFA)방법을 적용하여 과최적화(overfitting)의 실수를 줄이도록 하였다. 20종목씩 6개의 포트폴리오(portfolio)를 구성하여 테스트해 본 결과에 따르면 패턴 매매에서 가격 변동성이 어느 정도 수반되어야 하며 패턴이 진행 중일 때보다 패턴이 완성된 후에 진입, 청산하는 것이 효과적임을 확인하였다.

참고문헌 (Reference)

1 이재원, "통합 다중 시뮬레이션에 의한 신경망 기반 주식 거래 시스템의 성능 최적화" 한국정보처리학회 14 (14): 127-134, 2007

2 이종식, "입력변수 및 학습사례 선정을 동시에 최적화하는 GA-MSVM 기반 주가지수 추세 예측 모형에 관한 연구" 한국지능정보시스템학회 23 (23): 147-168, 2017

3 이재원, "이동 평균선 패턴과 전환점 행렬에 기반한 주식 거래 시스템" 한국정보과학회 18 (18): 528-532, 2012

4 유재필, "기계학습과 데이터 시각화 기법을 이용한 주가 패턴 분석" 한국엔터프라이즈아키텍처학회 14 (14): 189-197, 2017

5 이재원, "고변동 주가 패턴의 감독 학습에 기반한 주식 거래 시스템" 한국정보과학회 19 (19): 23-29, 2013

6 Hill, A., "Using the ZigZag Feature for Elliott Wave Counts" StockCharts

7 Zbikowski, K., "Using Volume Weighted Support Vector Machines with Walk Forward Testing and Feature Selection for the Purpose of Creating Stock Trading Strategy" 42 (42): 1797-1805, 2015

8 Harris, S. J., "TradeStation made easy! : using EasyLanguage to build profits with the world's most popular trading software" Wiley 2011

9 Shiller, R. J., "The Use of Volatility Measures in Assessing Market Efficiency" 36 (36): 291-304, 1981

10 Levy, R. A., "The Predictive Significance of Five-Point Chart Patterns" 44 (44): 316-323, 1971

11 Pardo, R., "The Design, Testing, and Optimization of Trading Systems" Wiley 1992

12 김선웅, "Support Vector Machines와 유전자 알고리즘을 이용한 지능형 트레이딩 시스템 개발" 한국지능정보시스템학회 16 (16): 71-92, 2010

13 Cao, L. J., "Support Vector Machine with Adaptive Parameters in Financial Time Series Forecasting" 14 (14): 1506-1518, 2003

14 Kamijo, K., "Stock Price Pattern Recognition-a Recurrent Neural Network Approach-" 215-221, 1990

15 Leigh, W., "Stock Market Trading Rule Discovery Using Technical Charting Heuristics" 23 (23): 155-159, 2002

16 Kim, W. J., "Real Stock Chart Analysis" Joheunttang 2016

17 Kim, M. J., "Optimization of Ensemble of SVMs Using Genetic Algorithms" 1-14, 2009

18 Merrill, A. A., "M&W WAVE PATTERNS" 43-54, 1980

19 Merrill, A. A., "M and W WAVES - MORE DATA" 23-29, 1984

20 Han, H., "Let's find out by pattern and trading with indices" Saenghwaljihyesa 2000

21 Baek, J. W., "Left Shoulder" Detection in Korea Composite Stock Price Index Using an Auto - Associative Neural Network and Sign Variables" 27 (27): 320-322, 2000

22 Bao, D., "Intelligent Stock Trading System by Turning Point Confirming and Probabilistic Reasoning" 34 (34): 620-627, 2008

23 Bulkowski, T. N., "Getting Started in Chart Patterns" Wiley 2006

24 Lee, J., "Forecasting System of KOSPI 200 using Patterns" 30 (30): 508-510, 2003

25 Yoon, J. S., "Follow chart analysis" Gilbert 2017

26 Pardo, R., "Evaluation and Optimization of Trading Strategies" Wiley 2008

27 Fama, E. F., "Efficient capital markets: A review of theory and empirical work" 25 (25): 383-417, 1970

28 Kim, J. H., "Description of the chart" Iremedia 2013

29 Liu, J. N. K., "Automatic Extraction and Identification of Chart Patterns towards Financial Forecast" 7 (7): 1197-1208, 2007

30 Mitchell, M., "An Introduction to Genetic Algorithms" The MIT Press 1996

31 Lee, S. Y., "7th Sense, System Trading with CybosTrader" Daishin Economic Research Institute 2004