• Journal of the Korean Data and Information Science Society
• /
• v.21 no.4
• /
• pp.777-782
• /
• 2010

We introduce some techniques to decompose the impulse (the unit sample) into several dilated pieces in the discrete time domain. From the decomposition of the impulse, we obtain localized moving averages. Thus we construct hybrid Bollinger bands that may give various strategies for stock traders. By simulations, we report that more than 94% of stock prices of companies in KOSPI 200 are inside this hybrid Bollinger band.

• Journal of Intelligence and Information Systems
• /
• v.22 no.2
• /
• pp.115-125
• /
• 2016

The Bollinger Band indicating the current price position in the recent price action range is obtained by adding/substracting the simple standard deviation (SSD) to/from the simple moving average (SMA). In this paper, we first compare the characteristics of the SMA and the exponential moving average (EMA) in the operator's point of view. A basic equation is obtained between the interval length N of the SMA operator and the weighting factor ${\rho}$ of the EMA operator, that makes the centers of the 1st order momentums of each operator impulse respoinse identical. For equivalent N and ${\rho}$, frequency response examples are obtained and compared by using the discrete time Fourier transform. Based on observation that the SMA operator reacts more excessively than the EMA operator, we propose a novel exponential standard deviation (ESD) band centered at the EMA and derive an auto recursive formula for the proposed ESD band. Practical examples for the ESD band show that it has a smoother bound on the price action range than the Bollinger Band. Comparisons are also made for the gap corrected chart to show the advantageous feature of the ESD band even in the case of gap occurrence. Trading techniques developed for the Bollinger Band can be straight forwardly applied to those for the ESD band.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.11a
• /
• pp.1636-1638
• /
• 2012

주식시장에서 개별 종목의 등락을 예측하는 것은 불가능하다. 미래가 정해져 있다면 그것을 아는 순간 거래는 성립되지 않기 때문이다. 따라서 개별 종목의 등락은 기업의 가치뿐만 아니라 투자참여자의 수급에 의해서 결정되므로 등락 확률은 예측불가인 0.5에 가깝다. 따라서 개별종목의 총합인 종합지수 역시 예측이 불가능해도 확률적인 틀은 제시할 수 있다. 바이노미알 분포를 사용하여 n을 충분히 증가시키면 가우시안 분포가 되고 이를 이동평균선으로 지표화한 Bollinger Band를 이용하는 것이다. 중심선에 480일선을 상하한폭을 $2{\sigma}$, $4{\sigma}$로 하여 그 틀을 제시하고, 이를 주요 종합지수로 검증하였다.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.5
• /
• pp.697-703
• /
• 2022

Due to the recent economic downturn caused by Covid-19 and the unstable international situation, many investors are choosing the derivatives market as a means of investment. However, the derivatives market has a greater risk than the stock market, and research on the market of market participants is insufficient. Recently, with the development of artificial intelligence, machine learning has been widely used in the derivatives market. In this paper, reinforcement learning, one of the machine learning techniques, is applied to analyze the scalping technique that trades futures in minutes. The data set consists of 21 attributes using the closing price, moving average line, and Bollinger band indicators of 1 minute and 3 minute data for 6 months by selecting 4 products among futures products traded at trading firm. In the experiment, DNN artificial neural network model and three reinforcement learning algorithms, namely, DQN (Deep Q-Network), A2C (Advantage Actor Critic), and A3C (Asynchronous A2C) were used, and they were trained and verified through learning data set and test data set. For scalping, the agent chooses one of the actions of buying and selling, and the ratio of the portfolio value according to the action result is rewarded. Experiment results show that the energy sector products such as Heating Oil and Crude Oil yield relatively high cumulative returns compared to the index sector products such as Mini Russell 2000 and Hang Seng Index.