Monthly trend forecasting performance of convolutional neural networks in the Nasdaq market

Year 2026, Volume: 6 Issue: 1, 16 - 35, 31.01.2026

Özüm Emre Aşırım

https://doi.org/10.61112/jiens.1668165

https://izlik.org/JA97NK57GH

Abstract

Accurate short-term forecasting in stock markets is essential for agile trading strategies, yet the volatile, nonstationary nature of financial data complicates predictive modeling. This study examines the performance of one-dimensional convolutional neural networks (CNNs) in identifying monthly directional movements for NASDAQ-listed equities. Although CNNs have proven effective in pattern recognition, many stock forecasting studies still rely on recurrent architectures. In this paper, by concentrating on CNNs and a sliding-window technique to generate lagged input features, we streamline the computational process for stock trend forecasting. Historical closing prices from multiple NASDAQ companies serve as both training and out-of-sample test sets. Pearson correlation, emphasizing directional alignment between actual and predicted data, is our primary evaluation metric, while mean squared error (MSE) is used to measure predictive accuracy. Through varying hyperparameters, such as network depth, batch size, and window segmentation, we show that CNNs remain robust under diverse conditions. Most scenarios yield strong positive correlations, indicating these networks can effectively capture local price dynamics with minimal hyperparameter tuning. This paper contributes to the field by confirming CNNs’ viability for stock trading and offers a reproducible framework. Our findings support the use of CNN-based pipelines for practitioners seeking rapid, directionally accurate stock trend insights.

Keywords

Deep learning , Finance , Stock market , Forecasting , Neural networks , Algorithmic trading

Nasdaq piyasasında evrişimsel sinir ağlarının aylık yönelim tahmin performansı

https://izlik.org/JA97NK57GH

Abstract

Borsa alanında kısa vadeli doğru kestirimler, çevik alım-satım yöntemleri için büyük önem taşır. Ancak, parasal verilerin değişken ve durağan olmayan yapısı, kestirimsel modeli zorlaştırmaktadır. Bu çalışma, NASDAQ’ta işlem gören şirketlerin aylık yönelim değişimlerini belirlemede bir boyutlu evrişimsel sinir ağlarının (ESA) başarımını incelemektedir. ESA’lar örüntü tanımada etkili olduklarını kanıtlamış olsa da, birçok borsa kestirim çalışması hâlâ yinelemeli yapılara dayanmaktadır. Bu yazıda, ESA’lara ve kaydırmalı pencere yöntemiyle gecikmeli girdi özellikleri üretmeye odaklanarak, borsa eğilimi kestirimi için hesaplamalı işlemi sadeleştiriyoruz.

Birden çok NASDAQ şirketine ait geçmiş kapanış değerleri, hem eğitme hem de dış örneklerle sınama için kullanılmıştır. Gerçek ve kestirilen veriler arasındaki yönsel uyumu öne çıkaran Pearson bağıntısı, başlıca değerlendirme ölçümüzdür; kestirim doğruluğunu ölçmek için ise Ortalama Karesel Hata (OKH) kullanılmaktadır. Ağ derinliği, yığın boyutu ve pencere bölütlemesi gibi çeşitli üst düzenleyici değerleri değiştirerek, ESA’ların farklı koşullar altında da sağlamlığını koruduğunu gösteriyoruz. Çoğu durumda güçlü ve olumlu bağıntılar elde edilmiştir; bu da, bu ağların yerel fiyat devinimlerini çok az ayarlamayla etkili biçimde yakalayabildiğini göstermektedir.

Bu yazı, ESA’ların borsa alım-satımı için uygunluğunu doğrulayarak alana katkı sunmakta ve yeniden uygulanabilir bir düzenek önermektedir. Bulgularımız, hızlı ve yönsel olarak doğru borsa eğilim bilgileri arayan uygulayıcılar için ESA tabanlı işlem düzeneklerinin kullanımını desteklemektedir.

Keywords

Derin öğrenme , Finans , Yapay sinir ağları , Borsa , Öngörü , Algoritmik alım satım

References

• Durairaj DM, Mohan BHK (2022) A convolutional neural network based approach to financial time series prediction. Neural Comput Appl 34:13319–13337. https://doi.org/10.1007/s00521-021-06671-7
• Arratia A, Sepúlveda E (2020) Convolutional neural networks, image recognition and financial time series forecasting. In: Bitetta V, Bordino I, Ferretti A, Gullo F, Pascolutti S, Ponti G (eds) Mining data for financial applications. Springer, Cham, vol 11985, pp 51–60. https://doi.org/10.1007/978-3-030-53973-4_5
• Moghar A, Hamiche M (2020) Stock market prediction using LSTM recurrent neural network. Procedia Comput Sci 170:1168–1173. https://doi.org/10.1016/j.procs.2020.03.049
• Fischer T, Krauss C (2018) Deep learning with long short-term memory networks for financial market predictions. Eur J Oper Res 270(2):654–669. https://doi.org/10.1016/j.ejor.2017.11.054
• Yañez C, Kristjanpoller W, Minutolo MC (2024) Stock market index prediction using transformer neural network models and frequency decomposition. Neural Comput Appl 36:15777–15797. https://doi.org/10.1007/s00521-023-08201-3
• Kallurkar HS, Chandavarkar BR (2024) A hybrid CNN–LSTM model for transaction fee forecasting in post EIP-1559 Ethereum. SN Comput Sci 5(3):638. https://doi.org/10.1007/s42979-024-02564-w
• Readshaw J, Giani S (2021) Using company-specific headlines and convolutional neural networks to predict stock fluctuations. Neural Comput Appl 33:17353–17367. https://doi.org/10.1007/s00521-021-06324-9
• Passalis N, Avramelou L, Seficha S, et al (2022) Multisource financial sentiment analysis for detecting Bitcoin price change indications using deep learning. Neural Comput Appl 34:19441–19452. https://doi.org/10.1007/s00521-022-07432-w
• Saravanos C, Kanavos A (2024) Forecasting stock market volatility using social media sentiment analysis. Neural Comput Appl. https://doi.org/10.1007/s00521-024-08934-0
• Wojarnik G (2023) The potential of convolutional neural networks for the analysis of stock charts. Procedia Comput Sci 225:941–950. https://doi.org/10.1016/j.procs.2023.01.097
• Cao J, Wang J (2019) Stock price forecasting model based on modified convolution neural network and financial time series analysis. Int J Commun Syst 32(10):e3987. https://doi.org/10.1002/dac.3987
• Lin CT, Wang YK, Huang PL, et al (2022) Spatial-temporal attention-based convolutional network with text and numerical information for stock price prediction. Neural Comput Appl 34:14387–14395. https://doi.org/10.1007/s00521-021-06884-w
• Gu S, Kelly B, Xiu D (2020) Empirical asset pricing via machine learning. Rev Financ Stud 33(5):2223–2273. https://doi.org/10.1093/rfs/hhz057
• Liu Y, Huang X, Xiong L, et al (2025) Stock price prediction with attentive temporal convolution-based generative adversarial network. Array 25:100374. https://doi.org/10.1016/j.array.2024.100374
• Vanstone B, Finnie G (2009) An empirical methodology for developing stockmarket trading systems using artificial neural networks. Expert Syst Appl 36(3):6668–6680. https://doi.org/10.1016/j.eswa.2008.08.022
• Garlapati A, Krishna DR, Garlapati K, Yaswanth NMS, Rahul U, Narayanan G (2021) Stock price prediction using Facebook Prophet and ARIMA models. 6th Int Conf Convergence Technol (I2CT), Maharashtra, India, pp 1–7
• Asirim ÖE, Aşırım A, Salepçioğlu MA (2024) Performance of Prophet in stock-price forecasting: Comparison with ARIMA and MLP networks. 6th Int Conf Intell Comput Data Sci (ICDS), Marrakech, Morocco, pp 1–7
• Elseidi M (2024) A hybrid Facebook Prophet-ARIMA framework for forecasting high-frequency temperature data. Model Earth Syst Environ 10:1855–1867. https://doi.org/10.1007/s40808-023-01868-2
• Long B, Tan F, Newman M (2023) Forecasting the monkeypox outbreak using ARIMA, Prophet, NeuralProphet, and LSTM models in the United States. Forecasting 5(1):127–137. https://doi.org/10.3390/forecast5010007
• Hiransha M, Gopalakrishnan EA, Menon VK, Soman KP (2018) NSE stock market prediction using deep-learning models. Procedia Comput Sci 132:1351–1362. https://doi.org/10.1016/j.procs.2018.05.244
• Zhang W, Chen Z, Miao J, Liu X (2022) Research on graph neural network in stock market. Procedia Comput Sci 214:786–792. https://doi.org/10.1016/j.procs.2022.11.160
• Park HJ, Kim Y, Kim HY (2022) Stock market forecasting using a multi-task approach integrating long short-term memory and the random forest framework. Appl Soft Comput 114:108106. https://doi.org/10.1016/j.asoc.2021.108106
• Phuoc T, Anh PTK, Tam PH, et al (2024) Applying machine learning algorithms to predict the stock price trend in the stock market – The case of Vietnam. Humanit Soc Sci Commun 11:393. https://doi.org/10.1057/s41599-024-02760-6
• Barua M, Kumar T, Raj K, Roy AM (2024) Comparative analysis of deep learning models for stock price prediction in the Indian market. FinTech 3:551–568. https://doi.org/10.3390/fintech3030027
• Kong X, Chen Z, Liu W, et al (2025) Deep learning for time series forecasting: a survey. Int J Mach Learn Cybern 16:5079–5112. https://doi.org/10.1007/s13042-024-01926-2
• Bollen J, Mao H, Zeng X (2011) Twitter mood predicts the stock market. J Comput Sci 2(1):1–8. https://doi.org/10.1016/j.jocs.2010.12.007
• Xie L, Chen Z, Yu S (2024) Deep convolutional transformer network for stock movement prediction. Electronics 13(20):4225. https://doi.org/10.3390/electronics13204225
• Lu W, Li J, Li Y, Sun A, Wang J (2020) A CNN-LSTM-based model to forecast stock prices. Complexity 2020:6622927. https://doi.org/10.1155/2020/6622927
• Mehtab S, Sen J (2020) Stock price prediction using convolutional neural networks on a multivariate time series. 3rd Nat Conf Mach Learn Artif Intell, New Delhi, India, Feb 2020
• Chen S, He H (2018) Stock prediction using convolutional neural network. IOP Conf Ser Mater Sci Eng 435:012026. https://doi.org/10.1088/1757-899X/435/1/012026
• Song X, Deng L, Wang H, et al (2025) Deep learning-based time series forecasting. Artif Intell Rev 58(1):23. https://doi.org/10.1007/s10462-023-10434-5
• Heaton JB, Polson NG, Witte JH (2017) Deep learning for finance: deep portfolios. Appl Stoch Models Bus Ind 33(1):3–12. https://doi.org/10.1002/asmb.2209
• Wan L, Tao Y, Wang J, et al (2025) A multi-scale multi-head attention network for stock trend prediction considering textual factors. Appl Soft Comput 171:112388. https://doi.org/10.1016/j.asoc.2023.112388
• Börjesson L, Singull M (2020) Forecasting financial time series through causal and dilated convolutional neural networks. Entropy 22(10):1094. https://doi.org/10.3390/e22101094
• Wang Z (2025) Application of CNN-based financial risk identification and management convolutional neural networks in financial risk. Syst Soft Comput 7:200215. https://doi.org/10.1016/j.sasoc.2024.200215
• Chen C, Zhang P, Liu Y, Liu J (2020) Financial quantitative investment using convolutional neural network and deep learning technology. Neurocomputing 390:384–390. https://doi.org/10.1016/j.neucom.2019.01.109
• Kong X, Chen Z, Liu W, et al (2025) Deep learning for time series forecasting: a survey. Int J Mach Learn Cybern 16:5079–5112. https://doi.org/10.1007/s13042-024-01926-2
• Nelson DMQ, Pereira ACM, de Oliveira RA (2017) Stock market's price movement prediction with LSTM neural networks. Int Jt Conf Neural Netw (IJCNN), Anchorage, AK, USA, pp 1419–1426. https://doi.org/10.1109/IJCNN.2017.7966019
• Krauss C, Do XA, Huck N (2017) Deep neural networks, gradient-boosted trees, random forests: statistical arbitrage on the S&P 500. Eur J Oper Res 259(2):689–702. https://doi.org/10.1016/j.ejor.2016.10.031
• Sezer OB, Gudelek MU, Ozbayoglu AM (2020) Financial time series forecasting with deep learning: A systematic literature review: 2005–2019. Appl Soft Comput 90:106181. https://doi.org/10.1016/j.asoc.2020.106181