Investment decision making by using fuzzy candlestick pattern and genetic algorithm

Lee, Chih‐Hao; Liaw, Yi‐Ching; Hsu, Lindroos

doi:10.1109/fuzzy.2011.6007707

Cited by 8 publications

(6 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They proposed the following three confirmation factors: the opening on the day after a reversal pattern, the changes in real bodies between the two days, and the changes in volume. C.-H. L. Lee, et al [9], C.-H. L. Lee, et al [10]proposed an approach to extract fuzzy candlestick patterns from a financial time series and to select a set of patterns for investment decision making. T.-H. Lu, et al [8]investigated the profitability of two-day candlestick patterns by buying based on bullish (bearish) patterns and holding until bearish (bullish) patterns occurred.…”

Section: Methodsmentioning

confidence: 99%

A NOVEL mechanism for forecasting based on pattern recognition

Zhou¹,

Jin²,

He³

2016

Proceedings of the 2016 2nd Workshop on Advanced Research and Technology in Industry Applications

View full text Add to dashboard Cite

Trend prediction is an attractive topic, because determining the buy and sell points is one of the most important issues for investors in the stock market. The main purpose of this paper is to find an effective mechanism to identify the buy and sell signals. Based on the principle of pattern recognition, we establish a novel mechanism to recognize up or down patterns and the pinpoint for buying or selling. Using all stocks listed on the US NASDAQ, which includes 4460 companies for the period Jan. 1st 2010 to Dec. 31th 2010, our empirical study examines the predictive power of our trading strategies. The results indicate that our new strategies are profitable and that the accuracy rate of our predictions is above 67%.The main contribution of our study is that we find the trend to be more important than the isolated price. We first propose the novel pattern of "uptrend" or "downtrend", while a continuous unidirectional trend may forecast the uptrend or downtrend in the future, two continuous unidirectional trends could verify the uptrend or down trend. That is, when a stock is on the rise, there must appear continuous up lines on the chart, and if the stock is falling, two down lines appear. We named this strategy as the "Two-line Strategy"

show abstract

Section: Methodsmentioning

confidence: 99%

A NOVEL mechanism for forecasting based on pattern recognition

Zhou¹,

Jin²,

He³

2016

Proceedings of the 2016 2nd Workshop on Advanced Research and Technology in Industry Applications

View full text Add to dashboard Cite

show abstract

“…Nowadays, stock market prediction is frequently based on techniques and tools of artificial intelligence. Construction methods of stock price prediction algorithms by genetic algorithms are presented in [1], [4], [6], [13], and [14]. Soft computing methods, like neural networks and fuzzy systems, for time series prediction are described, e.g.…”

Section: Recent Papersmentioning

confidence: 99%

“…In [13], Japanese candlestick patterns are modelled using fuzzy linguistic variables. This model is further used in [14] and extended with a genetic algorithm for the selection of the fittest candlestick patterns.…”

Section: Recent Papersmentioning

confidence: 99%

Genetically Evolved Agents for Stock Price Prediction

2013

APH

View full text Add to dashboard Cite

Our intention is to evolve agents genetically to maximize their stock price prediction ability. A newly designed stock price prediction algorithm benchmark is used as a fitness function. A portfolio of seven US blue-chip stocks has been set for experimental purposes. We use daily time series of stock prices from 2000 to 2011 divided into two segments, in-sample for genetic algorithm evolution and out-of-sample for evaluation. Agents act as prediction algorithms based on Japanese candlestick patterns expressed as logical formulas and encoded by a tree encoding. Evaluation by the benchmark shows this is a promising way to develop successful stock prices prediction algorithm.

show abstract

“…Candlestick patterns are believed to provide a reversal signal so that they can be a tool for choosing the right entry time in investing. Previous researchers [11], [12] built rules on each pattern by comparing the length of the lower shadows, the length of the upper shadows, and the length of the real body with the previous few days for each type of candlestick. Meanwhile, Kusuma et al [13] conducted a study to predict future stock market movements with candlestick charts using the Convolutional Neural Network.…”

Section: Introductionmentioning

confidence: 99%

Candlestick Pattern Classification Using Feedforward Neural Network

Karmelia¹,

Widjaja²,

Hansun³

2022

ijasca

View full text Add to dashboard Cite

Investment in the capital market can help boost a country’s economic growth. Without a doubt, in investing, a technical analysis of the condition of the stock is needed at that time. One of the technical analyses that can be done is to look at the historical data of stocks. Candlestick charts can summarize historical data that contain price value for Open, High, Low, and Close (OHLC) in the form of a chart. A group of candlesticks will form a pattern that can help investors to see whether the stock is trending up or down. The number of candlestick patterns and the manual determination of candlestick patterns may take time and effort. Feedforward Neural Network (FNN) is one of the algorithms that can help map the input and output of a given dataset. This study aims to implement FNN to classify candlestick patterns found in historical stock data. The test results show that the accuracy for each model scenario does not guarantee whether all patterns can be properly recognized. This is mainly caused by an imbalanced dataset and the classification process cannot be done properly. Testing with the original data has an accuracy of above 85% on each stock, but the average F1-score is below 45%. Further experiments using random under-sampling and Synthetic Minority Oversampling Technique (SMOTE) result in decreased accuracy value, where the lowest is 59% in PT Bukit Asam Tbk share, and an increased average F1-score, but less than 15%. Keywords: Candlestick patterns, feedforward neural network, investment, historical data, OHLC, SMOTE, stocks.

show abstract

Investment decision making by using fuzzy candlestick pattern and genetic algorithm

Cited by 8 publications

References 15 publications

A NOVEL mechanism for forecasting based on pattern recognition

A NOVEL mechanism for forecasting based on pattern recognition

Genetically Evolved Agents for Stock Price Prediction

Candlestick Pattern Classification Using Feedforward Neural Network

Contact Info

Product

Resources

About