Candlestick Type Prediction in Financial Charts

Zahra Ahmadzadeh Layegh; Mahdi Bahaghighat; Zahra Noori

doi:10.35377/saucis...1850817

Candlestick Type Prediction in Financial Charts

Abstract

AI-powered financial market prediction is a leading and popular research area nowadays. While most research has focused on portfolio optimization, trend analysis, and price prediction, the primary focus of this paper is the prediction of candlestick type in financial charts. As this is a relatively new field in market prediction, few studies have been conducted, and this study aims to advance this developing topic. Candlesticks provide a visual representation of price changes over time. Candlestick patterns can be classified into reversal and continuation patterns, which can signal potential market changes. While continuation patterns indicate that the same trend continues for a bullish or bearish market, reversal patterns signal the opposite, showing transitions from upward to downward momentum or vice versa. We first proposed thirty-three attributes, including thirty-two input features and an output/prediction variable, to build our datasets. In practice, we considered four types of candlesticks—Doji, Hanging Man, Hammer, and Marubozu—that have the highest frequencies in the price chart. Second, numerous machine learning and deep learning models have been developed to achieve optimal accuracy. An ablation study validated the significant contribution of the newly engineered features, while SHAP-based explainable AI analysis highlighted their interpretability and impact on model decisions. When evaluated on hourly data, the proposed Hybrid Transformer-LSTM (HTL) model could enhance performance, achieving an accuracy of approximately 86%.

Keywords

Ethical Statement

It is declared that during the preparation process of this study, scientific and ethical principles were followed, and all the studies benefited from are stated in the bibliography.

References

D. Nath, Ankit, D. R. Neog, and S. S. Gautam, “Application of machine learning and deep learning in finite element analysis: A comprehensive review,” Arch. Comput. Methods Eng., vol. 31, pp. 2945–2984, 2024, doi: 10.1007/S11831-024-10063-0.
C. Zhang, Y. Zhang, M. Cucuringu, and Z. Qian, “Volatility forecasting with machine learning and intraday commonality,” J. Financ. Econom., vol. 22, no. 2, pp. 492–530, 2024, doi: 10.1093/JJFINEC/NBAD005.
S. M. Acosta, R. M. A. Oliveira, and ˆA. M. O. Sant’Anna, “Machine learning algorithms applied to intelligent tyre manufacturing,” Int. J. Comput. Integr. Manuf., vol. 37, no. 4, pp. 497–507, 2024, doi: 10.1080/0951192X.2023.2177734.
K. Hernandez and A. B. Hoskins, “Machine learning algorithms applied to wildfire data in California’s central valley,” Trees For. People, vol. 15, p. 100516, 2024, doi: 10.1016/J.TFP.2024.100516.
Y. W. Bhowte, A. Roy, K. B. Raj, M. Sharma, K. Devi, and P. LathaSoundarraj, “Advanced fraud detection using machine learning techniques in accounting and finance sector,” in Proc. 9th Int. Conf. Sci. Technol. Eng. Math. (ICONSTEM), 2024, pp. 1–6, doi: 10.1109/ICONSTEM60960.2024.10568756.
S. Mousavi and M. Bahaghighat, “Phishing website detection: An in-depth investigation of feature selection and deep learning,” Expert Syst., vol. 42, no. 1, p. e13824, 2025, doi: 10.1111/EXSY.13824.
M. Rostami, M. Bahaghighat, and M. M. Zanjireh, “Bitcoin daily close price prediction using optimized grid search method,” Acta Univ. Sapientiae, Inform., vol. 13, no. 2, pp. 265–287, 2021, doi: 10.2478/AUSI-2021-0012.
J. Shen and M. O. Shafiq, “Short-term stock market price trend prediction using a comprehensive deep learning system,” J. Big Data, vol. 7, p. 66, 2020, doi: 10.1186/S40537-020-00333-6.

S. Yogeshwaran, M. J. Kaur, and P. Maheshwari, “Project based learning: Predicting bitcoin prices using deep learning,” in Proc. IEEE Glob. Eng. Educ. Conf. (EDUCON), 2019, pp. 1449–1454, doi: 10.1109/EDUCON.2019.8725091.
M. M. Patel, S. Tanwar, R. Gupta, and N. Kumar, “A deep learning-based cryptocurrency price prediction scheme for financial institutions,” J. Inf. Secur. Appl., vol. 55, p. 102583, 2020, doi: 10.1016/J.JISA.2020.102583.
T. Phaladisailoed and T. Numnonda, “Machine learning models comparison for bitcoin price prediction,” in Proc. 2018 10th Int. Conf. Inf. Technol. Electr. Eng. (ICITEE), 2018, pp. 506–511, doi: 10.1109/ICITEED.2018.8534911.
R. Roleda, “Predictive value of candlestick type on price movements in stock markets,” in Proc. De La Salle Univ. Res. Congr. (DLSU Research Congress), Manila, Philippines, Jun. 19–21, 2019.
O. B. Sezer, M. U. Gudelek, and A. M. Ozbayoglu, “Financial time series forecasting with deep learning: A systematic literature review: 2005–2019,” Appl. Soft Comput., vol. 90, Art. no. 106181, 2020, doi: 10.1016/J.ASOC.2020.106181.
A. N. Puteri, S. Syamsu, T. L. Putra, and A. D. Achmad, “Support vector machine for predicting candlestick chart movement on foreign exchange,” MATRIK: J. Manaj. Tek. Inform. Rekayasa Komput., vol. 22, no. 2, pp. 249–260, 2023, doi: 10.30812/MATRIK.V22I2.2676.
J.-H. Chen and Y.-C. Tsai, “Dynamic deep convolutional candlestick learner,” 2022, arXiv:2201.08669.
Y. R. Wang and Y. C. Tsai, “The protection of data sharing for privacy in financial vision,” Appl. Sci., vol. 12, no. 15, p. 7408, 2022, doi: 10.3390/APP12157408.
M. R. Kabir, D. Bhadra, M. Ridoy, and M. Milanova, “LSTM–transformer-based robust hybrid deep learning model for financial time series forecasting,” Sci., vol. 7, no. 1, Art. no. 7, 2025, doi: 10.3390/sci7010007.
D. Vallarino, “An AI-enhanced forecasting framework: Integrating LSTM and transformer-based sentiment for stock price prediction,” J. Econ. Anal., vol. 4, no. 3, pp. 1–15, 2025, doi: 10.58567/jea04030001.
N. S. R. Gona et al., “Hybrid LSTM-transformer model for stock market prediction: A deep learning approach,” in Proc. 2025 IEEE Int. Conf. Artif. Intell. Test. (AITest), 2025, pp. 87–93, doi: 10.1109/AITEST66680.2025.00018.
Y. Nejatbakhsh and M. Aliasgari, “Enhancing stock market prediction with hybrid deep learning: Integrating LSTM, transformer attention, federated learning, and sentiment analysis,” IEEE Access, vol. 14, pp. 3926–3942, 2026, doi: 10.1109/access.2025.3649668.
T. Akhila, J. F. Raj, D. K. Jesintha, R. Krishnan, V. Kumar, and P. Sundaravadivel, “Hybrid deep learning for international trading: Integrating LSTM and transformer models,” in Proc. 2025 4th Int. Conf. Sentiment Anal. Deep Learn. (ICSADL), 2025, pp. 1172–1179, doi: 10.1109/icsadl65848.2025.10933130.
C. Wang, Y. Chen, S. Zhang, and Q. Zhang, “Stock market index prediction using deep Transformer model,” Expert Syst. Appl., vol. 208, Art. no. 118128, 2022, doi: 10.1016/j.eswa.2022.118128.
Y. Ji et al., “Galformer: A transformer with generative decoding and a hybrid loss function for multi-step stock market index prediction,” Sci. Rep., vol. 14, Art. no. 23762, 2024, doi: 10.1038/s41598-024-72045-3.
Y. Chen, W. Shen, H. Liu, and X. Cao, “EMAT: Enhanced multi-aspect attention transformer for financial time series forecasting,” Entropy, vol. 27, no. 10, Art. no. 1029, 2025, doi: 10.3390/e27101029.
B. Asal, “Transformer-based deep learning framework for interpretable cardiac arrest detection using tabular clinical data,” in Proc. 2025 10th Int. Conf. Comput. Sci. Eng. (UBMK), 2025, pp. 847–852, doi: 10.1109/UBMK67458.2025.11206850.
Y. Fan and P. Waldmann, “Tabular deep learning: A comparative study applied to multi-task genome-wide prediction,” BMC Bioinformatics, vol. 25, p. 322, 2024, doi: 10.1186/s12859-024-05940-1.
S. Y. Kuo and Y. H. Chou, “Building intelligent moving average-based stock trading system using metaheuristic algorithms,” IEEE Access, vol. 9, pp. 140383–140396, 2021, doi: 10.1109/ACCESS.2021.3119041.
S. Dinesh, R. N. Rao, S. P. Anusha, and R. Samhitha, “Prediction of trends in stock market using moving averages and machine learning,” in Proc. 2021 6th Int. Conf. Convergence Technol. (I2CT), 2021, doi: 10.1109/I2CT51068.2021.9418097.
D. Vezeris, I. Karkanis, and T. Kyrgos, “AdTurtle: An advanced turtle trading system,” J. Risk Financ. Manag., vol. 12, no. 2, p. 96, 2019, doi: 10.3390/JRFM12020096.
N. Wcisło, M. Guze, and I. J. J´o´zwiak, “Artificial intelligence models supporting economical decisions compared to traditional decision making strategies in the example of stock market,” Sci. Pap. Silesian Univ. Technol., Organ. Manag. Ser., no. 167, pp. 569–577, 2022, doi: 10.29119/1641-3466.2022.167.38.
¨U. Aycel and Y. Santur, “A new algorithmic trading approach based on ensemble learning and candlestick pattern recognition in financial assets,” Turk. J. Sci. Technol., vol. 17, no. 2, pp. 167–184, 2022, doi: 10.55525/tjst.1124256.
A. Heinz, M. Jamaloodeen, A. Saxena, and L. Pollacia, “Bullish and bearish engulfing Japanese candlestick patterns: A statistical analysis on the S&P 500 index,” Q. Rev. Econ. Finance, vol. 79, pp. 221–244, 2021, doi: 10.1016/J.QREF.2020.06.006.
S. Janibeigi, M. Bahaghighat, Z. Yaghoubi, and N. T. Javan, “Integrating computer vision: Advancements in fire and smoke detection using CNNs,” CLEI Electron. J., vol. 29, no. 2, paper 5, 2026, doi: 10.19153/cleiej.29.2.5.
B. Richhariya, M. Tanveer, and A. H. Rashid, “Diagnosis of Alzheimer’s disease using universum support vector machine based recursive feature elimination (USVM-RFE),” Biomed. Signal Process. Control, vol. 59, p. 101903, 2020, doi: 10.1016/J.BSPC.2020.101903.
J. Cervantes, F. Garcia-Lamont, L. Rodr´ıguez-Mazahua, and A. Lopez, “A comprehensive survey on support vector machine classification: Applications, challenges and trends,” Neurocomputing, vol. 408, pp. 189–215, 2020, doi: 10.1016/J.NEUCOM.2019.10.118.
T. T. Ho and Y. Huang, “Stock price movement prediction using sentiment analysis and candlestick chart representation,” Sensors, vol. 21, no. 23, Art. no. 7957, 2021, doi: 10.3390/S21237957.
J. Cao and J. Wang, “Stock price forecasting model based on modified convolution neural network and financial time series analysis,” Int. J. Commun. Syst., vol. 32, no. 12, Art. no. e3987, 2019, doi: 10.1002/DAC.3987.
E. M. Senan et al., “Diagnosis of chronic kidney disease using effective classification algorithms and recursive feature elimination techniques,” J. Healthc. Eng., vol. 2021, p. 1004767, 2021, doi: 10.1155/2021/1004767.
S. M. Thampi, S. Piramuthu, K.-C. Li, S. Berretti, M. Wozniak, and D. Singh, Eds., Machine Learning and Metaheuristics Algorithms, and Applications Commun. Comput. Inf. Sci. vol. 1366. Singapore: Springer, 2021, doi: 10.1007/978-981-16-0419-5.
L. Breiman, “Random forests,” Mach. Learn., vol. 45, no. 1, pp. 5–32, 2001, doi: 10.1023/A:1010933404324.
A. Rostamian and J. G. O’Hara, “Event prediction within directional change framework using a CNN-LSTM model,” Neural Comput. Appl., vol. 34, pp. 17193–17205, 2022, doi: 10.1007/S00521-022-07687-3.
A. Yadav, C. K. Jha, and A. Sharan, “Optimizing LSTM for time series prediction in Indian stock market,” Procedia Comput. Sci., vol. 167, pp. 2091–2100, 2020, doi: 10.1016/J.PROCS.2020.03.257.
Pamir, N. Javaid, A. Almogren, M. Adil, M. U. Javed, and M. Zuair, “RFE based feature selection and KNNOR based data balancing for electricity theft detection using BiLSTM-LogitBoost stacking ensemble model,” IEEE Access, vol. 10, pp. 112948–112963, 2022, doi: 10.1109/ACCESS.2022.3215532.
S. Saffari and M. Bahaghighat, “Informatics and measurement in healthcare: Deep learning for diabetic patient readmission prediction,” Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie ´Srodowiska, vol. 15, no. 4, pp. 56–64, 2025, doi: 10.35784/iapgos.7835.
S. Thawkar, “A hybrid model using teaching–learning-based optimization and Salp swarm algorithm for feature selection and classification in digital mammography,” J. Ambient Intell. Humaniz. Comput., vol. 12, pp. 8793–8808, 2021, doi: 10.1007/S12652-020-02662-Z.
E. O. Omuya, G. O. Okeyo, and M. W. Kimwele, “Feature selection for classification using principal component analysis and information gain,” Expert Syst. Appl., vol. 174, Art. no. 114765, 2021, doi: 10.1016/J.ESWA.2021.114765.
S. Pande, A. Khamparia, and D. Gupta, “Feature selection and comparison of classification algorithms for wireless sensor networks,” J. Ambient Intell. Humaniz. Comput., vol. 14, pp. 1977–1989, 2023, doi: 10.1007/S12652-021-03411-6.
E. Taghizadeh et al., “Breast cancer prediction with transcriptome profiling using feature selection and machine learning methods,” BMC Bioinformatics, vol. 23, p. 266, 2022, doi: 10.1186/S12859-022-04965-8.
C. A. Ramezan, “Transferability of recursive feature elimination (RFE)-derived feature sets for support vector machine land cover classification,” Remote Sens., vol. 14, no. 24, p. 6218, 2022, doi: 10.3390/RS14246218.
J. Fields, K. Chovanec, and P. Madiraju, “A survey of text classification with transformers: How wide? How large? How long? How accurate? How expensive? How safe?,” IEEE Access, vol. 12, pp. 6518–6531, 2024, doi: 10.1109/ACCESS.2024.3349952.
A. R. Sajun, I. Zualkernan, and D. Sankalpa, “A historical survey of advances in transformer architectures,” Appl. Sci., vol. 14, no. 10, p. 4316, 2024, doi: 10.3390/APP14104316.
L. Papa, P. Russo, I. Amerini, and L. Zhou, “A survey on efficient vision transformers: Algorithms, techniques, and performance benchmarking,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 46, no. 11, pp. 7682–7700, 2024, doi: 10.1109/TPAMI.2024.3392941.
S. Aburass, O. Dorgham, J. Al Shaqsi, M. Abu Rumman, and O. Al-Kadi, “Vision transformers in medical imaging: A comprehensive review of advancements and applications across multiple diseases,” J. Imaging Inform. Med., vol. 38, no. 6, pp. 3928–3971, 2025, doi: 10.1007/s10278-025-01481-y.
Y. O. Sharrab, H. Attar, M. A. H. Eljinini, Y. Al-Omary, and W. E. Al-Momani, “Advancements in speech recognition: A systematic review of deep learning transformer models, trends, innovations, and future directions,” IEEE Access, vol. 13, pp. 46925–46940, 2025, doi: 10.1109/ACCESS.2025.3550855.
O. O. Oladimeji and A. O. Ibitoye, “Multi-scale adaptive attention framework for improved lung disease classification,” Sakarya Univ. J. Comput. Inf. Sci., vol. 8, no. 3, pp. 400–409, 2025, doi: 10.35377/saucis...1635644.
I. Markoulidakis, G. Kopsiaftis, I. Rallis, and I. Georgoulas, “Multi-class confusion matrix reduction method and its application on net promoter score classification problem,” in Proc. 14th Int. Conf. Pervasive Technol. Related Assistive Environ. (PETRA), 2021, pp. 412–419, doi: 10.1145/3453892.3461323.
ˇZ. Vujovi´c, “Classification model evaluation metrics,” Int. J. Adv. Comput. Sci. Appl., vol. 12, no. 6, pp. 599–606, 2021, doi: 10.14569/IJACSA.2021.0120670.
M. F. Amin, “Confusion matrix in binary classification problems: A step-by-step tutorial,” J. Eng. Res., vol. 6, no. 5, 2022.
J. F. Pimentel, L. Murta, V. Braganholo, and J. Freire, “Understanding and improving the quality and reproducibility of Jupyter notebooks,” Empir. Softw. Eng., vol. 26, p. 65, 2021, doi: 10.1007/S10664-021-09961-9.
A. A. Shahul Hameed and C. Ravi, “Bitcoin price prediction using optimized multiplicative long short term memory with attention mechanism using modified cuckoo search optimization,” Concurr. Comput. Pract. Exp., vol. 34, no. 13, p. e7384, 2022, doi: 10.1002/CPE.7384.
G. Kumar, U. P. Singh, and S. Jain, “Stock price forecasting based on the relationship among Asian stock markets using deep learning,” Concurr. Comput. Pract. Exp., vol. 35, no. 22, p. e7864, 2023, doi: 10.1002/CPE.7864.

Details

Primary Language

English

Subjects

Artificial Intelligence (Other), Computer Software

Journal Section

Research Article

Authors

Zahra Ahmadzadeh Layegh
0009-0007-9361-5862
Iran

Mahdi Bahaghighat ^*
0000-0002-1813-8417
Iran

Zahra Noori
0009-0007-1390-7057
Iran

Early Pub Date

October 28, 2026

Publication Date

October 30, 2026

Submission Date

December 31, 2025

Acceptance Date

July 21, 2026

Published in Issue

Year 2026 Volume: 9 Number: 5

DOI

https://doi.org/10.35377/saucis...1850817

IZ

https://izlik.org/JA22ZU58YD

Cite

RIS / Bibtex

APA

Ahmadzadeh Layegh, Z., Bahaghighat, M., & Noori, Z. (2026). Candlestick Type Prediction in Financial Charts. Sakarya University Journal of Computer and Information Sciences, 9(5), 1627-1646. https://doi.org/10.35377/saucis...1850817

AMA

1.Ahmadzadeh Layegh Z, Bahaghighat M, Noori Z. Candlestick Type Prediction in Financial Charts. SAUCIS. 2026;9(5):1627-1646. doi:10.35377/saucis.1850817

Chicago

Ahmadzadeh Layegh, Zahra, Mahdi Bahaghighat, and Zahra Noori. 2026. “Candlestick Type Prediction in Financial Charts”. Sakarya University Journal of Computer and Information Sciences 9 (5): 1627-46. https://doi.org/10.35377/saucis. 1850817.

EndNote

Ahmadzadeh Layegh Z, Bahaghighat M, Noori Z (October 1, 2026) Candlestick Type Prediction in Financial Charts. Sakarya University Journal of Computer and Information Sciences 9 5 1627–1646.

IEEE

[1]Z. Ahmadzadeh Layegh, M. Bahaghighat, and Z. Noori, “Candlestick Type Prediction in Financial Charts”, SAUCIS, vol. 9, no. 5, pp. 1627–1646, Oct. 2026, doi: 10.35377/saucis...1850817.

ISNAD

Ahmadzadeh Layegh, Zahra - Bahaghighat, Mahdi - Noori, Zahra. “Candlestick Type Prediction in Financial Charts”. Sakarya University Journal of Computer and Information Sciences 9/5 (October 1, 2026): 1627-1646. https://doi.org/10.35377/saucis. 1850817.

JAMA

1.Ahmadzadeh Layegh Z, Bahaghighat M, Noori Z. Candlestick Type Prediction in Financial Charts. SAUCIS. 2026;9:1627–1646.

MLA

Ahmadzadeh Layegh, Zahra, et al. “Candlestick Type Prediction in Financial Charts”. Sakarya University Journal of Computer and Information Sciences, vol. 9, no. 5, Oct. 2026, pp. 1627-46, doi:10.35377/saucis. 1850817.

Vancouver

1.Zahra Ahmadzadeh Layegh, Mahdi Bahaghighat, Zahra Noori. Candlestick Type Prediction in Financial Charts. SAUCIS. 2026 Oct. 1;9(5):1627-46. doi:10.35377/saucis. 1850817