DPP: Deep predictor for price movement from candlestick charts

Hung, Chih‐Chieh; Chen, Ying‐Ju

doi:10.1371/journal.pone.0252404

Cited by 16 publications

(7 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Numerous approaches have been proposed to solve this complex problem involving robust stock price prediction and the formation of the optimized combination of stocks to maximize the return on investment. For future stock price prediction, the use of machine learning and deep learning algorithms and models have been proposed in many works [3][4][5][6][7][8][9]. The performances of the learning-based systems and models have been improved with the use of text mining and natural language processing algorithms on the rich and unstructured data on social media [10][11][12][13].…”

Section: Related Workmentioning

confidence: 99%

Design and Analysis of Optimized Portfolios for Selected Sectors of the Indian Stock Market

Sen¹,

Dutta²

2022

2022 International Conference on Decision Aid Sciences and Applications (DASA)

View full text Add to dashboard Cite

Portfolio optimization is a challenging problem that has attracted considerable attention and effort from researchers. The optimization of stock portfolios is a particularly hard problem since the stock prices are volatile and estimation of their future volatilities and values, in most cases, is very difficult, if not impossible. This work uses three ratios, the Sharpe ratio, the Sortino ratio, and the Calmar ratio, for designing the mean-variance optimized portfolios for six important sectors listed in the National Stock Exchange (NSE) of India. Three portfolios are designed for each sector maximizing the ratios based on the historical prices of the ten most important stocks of each sector from Jan 1. 2017 to Dec 31. 2020. The evaluation of the portfolios is done based on their cumulative returns over the test period from Jan 1, 2021, to Dec 31, 2021. The ratio that yields the maximum cumulative returns for both the training and the test periods for the majority of the sectors is identified. Additionally, the sectors which exhibit the maximum cumulative returns for the same ratio are also identified. The results provide useful insights for the investors in the stock market in making their investment decisions based on the current return and risks associated with the six sectors and their stocks.

show abstract

Section: Related Workmentioning

confidence: 99%

Design and Analysis of Optimized Portfolios for Selected Sectors of the Indian Stock Market

Sen¹,

Dutta²

2022

2022 International Conference on Decision Aid Sciences and Applications (DASA)

View full text Add to dashboard Cite

show abstract

“…In 2020, Birogul [ 25 ] employed a real-time object detection system (YOLO) to recognize buy–sell objects inside 2D candlestick charts; from these buy–sell objects, the trader can make their decision on the stock. Not long after that, Hung [ 24 ] proposed a deep predictor framework for price movement based on candlestick charts. He explored a CNN-autoencoder to acquire the best sub-chart representation and applied recurrent neural networks to predict the stock price movement.…”

Section: Related Workmentioning

confidence: 99%

“…Many researchers have applied deep learning to the question of stock market prediction. There are several approaches for stock market prediction, such as analyzing indicators of historical time series data [ 16 , 17 , 18 , 19 , 20 ], or using candlestick chart converted from historical data [ 21 , 22 , 23 , 24 , 25 , 26 ], or analyzing the social media [ 27 , 28 , 29 , 30 , 31 , 32 ], or analyzing the financial news [ 33 , 34 , 35 , 36 ]. However, using a single classifier may not achieve maximum performance compared with using combined classifiers.…”

Section: Introductionmentioning

confidence: 99%

Stock Price Movement Prediction Using Sentiment Analysis and CandleStick Chart Representation

Huang

2021

Sensors

View full text Add to dashboard Cite

Determining the price movement of stocks is a challenging problem to solve because of factors such as industry performance, economic variables, investor sentiment, company news, company performance, and social media sentiment. People can predict the price movement of stocks by applying machine learning algorithms on information contained in historical data, stock candlestick-chart data, and social-media data. However, it is hard to predict stock movement based on a single classifier. In this study, we proposed a multichannel collaborative network by incorporating candlestick-chart and social-media data for stock trend predictions. We first extracted the social media sentiment features using the Natural Language Toolkit and sentiment analysis data from Twitter. We then transformed the stock’s historical time series data into a candlestick chart to elucidate patterns in the stock’s movement. Finally, we integrated the stock’s sentiment features and its candlestick chart to predict the stock price movement over 4-, 6-, 8-, and 10-day time periods. Our collaborative network consisted of two branches: the first branch contained a one-dimensional convolutional neural network (CNN) performing sentiment classification. The second branch included a two-dimensional (2D) CNN performing image classifications based on 2D candlestick chart data. We evaluated our model for five high-demand stocks (Apple, Tesla, IBM, Amazon, and Google) and determined that our collaborative network achieved promising results and compared favorably against single-network models using either sentiment data or candlestick charts alone. The proposed method obtained the most favorable performance with 75.38% accuracy for Apple stock. We also found that the stock price prediction achieved more favorable performance over longer periods of time compared with shorter periods of time.

show abstract

“…Consequently, it has been used to design a decision support framework that can be used by traders to provide suggested indicators of future stock price direction [8]. Hung et al (2021), taking a new approach, proposed a deep predictive (DPP) method for price action by using candlestick charts in stock historical data. This method consists of three steps: 1. parsing a particular candlestick chart into sub-charts; 2.…”

Section: Introductionmentioning

confidence: 99%

“…Using the CNNautoencoder to get the best representation of subcharts; 3. Application of RNN to predict price movements from a collection of sub-chart representations [9]. Sadeghi and Farid (2021) aim to design a stock market prediction based on candle patterns and use fuzzy logic to model market rules and candles.…”

Section: Introductionmentioning

confidence: 99%

A New Algorithmic Trading Approach Based on Ensemble Learning and Candlestick Pattern Recognition in Financial Assets

AYCEL

SANTUR

2022

Turkish Journal of Science and Technology

View full text Add to dashboard Cite

Financial assets considered as time series are chaotic in nature. The main goal of investors is to take a position at the right time and in the right direction by making predictions about the future on this chaotic series. These time series consist of the opening, low, high and closing price of a certain period. The approaches used to make predictions about trend direction and strength using moving averages and indicators based on them have noise and lag problems as they are obtained statistically. Candlestick charts, on the other hand, reflect the price-based psychology of bear and bull investors, as well as facilitating the interpretation of price movements by consolidating the said opening, closing, lowest and highest prices in a single image. It is known that it was applied to Japanese rice markets for the first time in history and there are 100+ candle patterns. In this study, an extensible architecture software framework using factory pattern and object-oriented approach is proposed for defining candlestick patterns and developing intelligent learning algorithms based on them. The proposed software framework can also be used in the development of new robotic approaches in terms of being applicable to all kinds of financial assets in every period.

show abstract

DPP: Deep predictor for price movement from candlestick charts

Cited by 16 publications

References 26 publications

Design and Analysis of Optimized Portfolios for Selected Sectors of the Indian Stock Market

Design and Analysis of Optimized Portfolios for Selected Sectors of the Indian Stock Market

Stock Price Movement Prediction Using Sentiment Analysis and CandleStick Chart Representation

A New Algorithmic Trading Approach Based on Ensemble Learning and Candlestick Pattern Recognition in Financial Assets

Contact Info

Product

Resources

About