The intra-day performance of market timing strategies and trading systems based on Japanese candlesticks

Duvinage, Matthieu; Mazza, Paolo; Petitjean, Mikael

doi:10.1080/14697688.2013.768774

Cited by 15 publications

(19 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Unlike previous studies which focus on daily data, Duvinage, Mazza, and Petitjean (2013) test 5-min intraday data of 30 component stocks of the DJIA index. After a correction for the data snooping bias, no single candlestick rule on the double-or-out market timing strategy outperforms the buy-and-hold strategy after transaction costs.…”

Section: Empirical Studiesmentioning

confidence: 99%

Profitability of Candlestick Charting Patterns in the Stock Exchange of Thailand

2017

View full text Add to dashboard Cite

This article investigates the profitability of candlestick patterns. The holding periods are 1, 3, 5, and 10 days. Two exit strategies are studied. One is the Marshall-Young-Rose (MYR) exit strategy and the other is the Caginalp-Laurent (CL) exit strategy. The MYR applies a prespecified date to exit the market. In contrast, the CL sets an exit price equal to an average holding period closing price, assuming that investors liquidate their positions evenly within this period. The daily data include open, high, low, and close prices of component stocks of the SET50 index (the 50 largest capitalization stocks in the Stock Exchange of Thailand [SET]) for a 10-year period from July 3, 2006, to June 30, 2016. This study tests the predictive power of bullish and bearish candlestick reversal patterns both without technical filtering and with technical filtering (Stochastics [%D], Relative Strength Index [RSI], Money Flow Index [MFI]) by applying the skewness adjusted t test and the binomial test. The statistical analysis finds little use of both bullish and bearish candlestick reversal patterns since the mean returns of most patterns are not statistically different from zero. Even the ones with statistically significant returns do have high risks in terms of standard deviations. The binomial test results also indicate that candlestick patterns cannot reliably predict market directions. In addition, this article finds that filtering by %D, RSI, or MFI generally does not increase profitability nor prediction accuracy of candlestick patterns.

show abstract

Section: Empirical Studiesmentioning

confidence: 99%

Profitability of Candlestick Charting Patterns in the Stock Exchange of Thailand

2017

View full text Add to dashboard Cite

show abstract

“…On the other hand, Marshall et al (2006Marshall et al ( , 2008 and Horton (2009) find that candlestick trading strategies do not have any predictive value for major equity markets. In addition, Fock et al (2005) and Duvinage et al (2013) employ 5-min data to investigate the German bond futures market and the U.S. stock market, respectively, and both conclude that candlestick trading strategies do not improve investment performance. It is worthwhile to note that candlestick charting is best applied to daily charts, though it is operationally applicable on any timeframes, such as 5-min or hourly charts (Nison, 1991).…”

Section: Introductionmentioning

confidence: 96%

“…While Duvinage et al (2013) also consider data-snooping bias in their analysis, there are some differences in our research designs. First, they use high-frequency intraday 5-min data from April 1, 2010 to April 13, 2011, whereas we consider the daily data, from January 2, 1992 through December 31, 2012.…”

Section: Introductionmentioning

confidence: 97%

Trend definition or holding strategy: What determines the profitability of candlestick charting?

Chen

Hsu

2015

Journal of Banking & Finance

View full text Add to dashboard Cite

“…Fock et al found no evidence of the predictive ability of candlestick patterns alone or in combination with other common technical indicators in the DAX stock index contract and the Bund interest rate future [14]. Duvingage et al tested the intraday predictive power of Japanese candlesticks at the 5-minute interval on the 30 constituents of the DJIA index and concluded that candlestick trading strategies do not improve investment performance [15]. These conflicting conclusions about candlestick patterns prompt us to investigate further.…”

Section: Introductionmentioning

confidence: 99%

“…However, the use of machine learning technology for candlestick pattern recognition is still less prevalent. Moreover, traditional research on candlestick patterns focuses mainly on a limited number of patterns [9][10][11][12][13][14][15]. The latest artificial intelligence technology prompts us to consider applying pattern recognition to decision-making in the stock market.…”

Section: Introductionmentioning

confidence: 99%

Improving stock trading decisions based on pattern recognition using machine learning technology

et al. 2021

View full text Add to dashboard Cite

PRML, a novel candlestick pattern recognition model using machine learning methods, is proposed to improve stock trading decisions. Four popular machine learning methods and 11 different features types are applied to all possible combinations of daily patterns to start the pattern recognition schedule. Different time windows from one to ten days are used to detect the prediction effect at different periods. An investment strategy is constructed according to the identified candlestick patterns and suitable time window. We deploy PRML for the forecast of all Chinese market stocks from Jan 1, 2000 until Oct 30, 2020. Among them, the data from Jan 1, 2000 to Dec 31, 2014 is used as the training data set, and the data set from Jan 1, 2015 to Oct 30, 2020 is used to verify the forecasting effect. Empirical results show that the two-day candlestick patterns after filtering have the best prediction effect when forecasting one day ahead; these patterns obtain an average annual return, an annual Sharpe ratio, and an information ratio as high as 36.73%, 0.81, and 2.37, respectively. After screening, three-day candlestick patterns also present a beneficial effect when forecasting one day ahead in that these patterns show stable characteristics. Two other popular machine learning methods, multilayer perceptron network and long short-term memory neural networks, are applied to the pattern recognition framework to evaluate the dependency of the prediction model. A transaction cost of 0.2% is considered on the two-day patterns predicting one day ahead, thus confirming the profitability. Empirical results show that applying different machine learning methods to two-day and three-day patterns for one-day-ahead forecasts can be profitable.

show abstract

The intra-day performance of market timing strategies and trading systems based on Japanese candlesticks

Cited by 15 publications

References 12 publications

Profitability of Candlestick Charting Patterns in the Stock Exchange of Thailand

Profitability of Candlestick Charting Patterns in the Stock Exchange of Thailand

Trend definition or holding strategy: What determines the profitability of candlestick charting?

Improving stock trading decisions based on pattern recognition using machine learning technology

Contact Info

Product

Resources

About