A Review of Statistical, Machine Learning, and Deep Learning Methods for Stock Price Prediction: Toward Explainable Hybrid Models

Paper ID: EIJTEM_2026_13_3_28-37

Author's Name: Kulkarni Parag, Sanjay Azade

Volume: 13

Issue: 3

Year: 2026

Page No: 28-37

Abstract:

Stock price prediction is a long-standing and challenging problem in financial data science owing to the nonlinear, non-stationary, and noisy nature of market data. Over four decades, forecasting approaches have evolved from linear statistical models such as ARIMA and GARCH, through classical machine learning methods including Support Vector Machines, Decision Trees, and Random Forests, to deep learning architectures such as LSTM, GRU, CNN, and Transformer networks. Hybrid models integrating statistical and deep learning components — for example ARIMA-LSTM, CNN-BiLSTM-Attention, SARIMA-GARCH-CNN-BiLSTM, and Transformer-GRU frameworks — now represent the state of the art, consistently outperforming standalone baselines. This paper reviews 42 peer-reviewed stock-prediction studies, supported by 10 foundational and methodological references, organised using a PRISMA-informed screening process, with the primary studies published between 2001 and 2025, with emphasis on 2023–2025. We categorise the methods through a taxonomy, synthesise their reported performance with explicit attention to dataset and metric-scale heterogeneity, present a bibliometric overview, and critically evaluate persistent gaps. Three gaps emerge as central: the absence of standardised benchmarks and economic-utility metrics, the limited use of Indian-market (Nifty 50 / NSE) data, and the near-total absence of explainability frameworks such as SHAP and LIME. We argue that the most promising direction is the development of explainable hybrid models validated on Indian equity data, and position this review as the foundation for such work.

Keywords: Stock price forecasting; ARIMA; GARCH; LSTM; GRU; Transformer; hybrid models; explainable AI; SHAP; Nifty 50; literature review; PRISMA-informed screening

References:

[1] G. E. P. Box, G. M. Jenkins, and G. C. Reinsel, Time Series Analysis: Forecasting and Control, 4th ed. Hoboken, NJ: Wiley, 2008.
[2] R. J. Hyndman and G. Athanasopoulos, Forecasting: Principles and Practice, 3rd ed. Melbourne, Australia: OTexts, 2021. [Online]. Available: https://otexts.com/fpp3/
[3] P. H. Vuong, L. H. Phu, T. H. V. Nguyen, L. N. Duy, P. T. Bao, and T. D. Trinh, “A bibliometric literature review of stock price forecasting: From statistical model to deep learning approach,” Sci. Prog., vol. 107, no. 1, 2024, doi: 10.1177/00368504241236557.
[4] R. F. Engle, “Autoregressive conditional heteroscedasticity with estimates of the variance of United Kingdom inflation,” Econometrica, vol. 50, no. 4, pp. 987–1007, 1982, doi: 10.2307/1912773.
[5] H. White, “Economic prediction using neural networks: The case of IBM daily stock returns,” in Proc. IEEE Int. Conf. Neural Networks, vol. 2, San Diego, CA, 1988, pp. 451–458, doi: 10.1109/ICNN.1988.23959.
[6] F. E. H. Tay and L. J. Cao, “Application of support vector machines in financial time series forecasting,” Omega, vol. 29, no. 4, pp. 309–317, 2001, doi: 10.1016/S0305-0483(01)00026-3.
[7] K. Kim, “Financial time series forecasting using support vector machines,” Neurocomputing, vol. 55, no. 1–2, pp. 307–319, 2003, doi: 10.1016/S0925-2312(03)00372-2.
[8] Y. Gu, “A comparative analysis study of stock prediction based on Random Forest and Decision Tree,” in Proc. 2024 Int. Conf. Electronics and Devices, Computational Science (ICEDCS), 2024, pp. 96–101, doi: 10.1109/ICEDCS64328.2024.00025.
[9] A. H. Khan, A. Shah, A. Ali, R. Shahid, Z. U. Zahid, M. U. Sharif, et al., “A performance comparison of machine learning models for stock market prediction with a novel investment strategy,” PLOS ONE, vol. 18, no. 9, art. e0286362, 2023, doi: 10.1371/journal.pone.0286362.
[10] R. Panggabean et al., “Performance comparison of Random Forest Regression and SVR models in stock price prediction,” Jurnal Pilar Nusa Mandiri, vol. 20, no. 2, 2024, doi: 10.33480/pilar.v20i2.6072. [VERIFY author/volume]
[11] S. Siami-Namini, N. Tavakoli, and A. Siami Namin, “A comparison of ARIMA and LSTM in forecasting time series,” in Proc. 17th IEEE Int. Conf. Machine Learning and Applications (ICMLA), Orlando, FL, 2018, pp. 1394–1401, doi: 10.1109/ICMLA.2018.00227.
[12] T. Fischer and C. Krauss, “Deep learning with long short-term memory networks for financial market predictions,” Eur. J. Oper. Res., vol. 270, no. 2, pp. 654–669, 2018, doi: 10.1016/j.ejor.2017.11.054.
[13] M. Agrawal, P. K. Shukla, R. Nair, A. Nayyar, and M. Masud, “Stock prediction based on technical indicators using deep learning model,” Comput. Mater. Continua, vol. 70, no. 1, pp. 287–304, 2022, doi: 10.32604/cmc.2022.014683.
[14] M. Barua, T. Kumar, K. Raj, and A. M. Roy, “Comparative analysis of deep learning models for stock price prediction in the Indian market,” FinTech, vol. 3, no. 4, pp. 551–568, 2024, doi: 10.3390/fintech3040029.
[15] M. Kolambe and S. Arora, “Comparative analysis of LSTM variants for stock price forecasting on NSE India: GRU’s dominance and enhancements,” Int. J. Inf. Technol. Comput. Sci., vol. 16, no. 6, pp. 43–60, 2024, doi: 10.5815/ijitcs.2024.06.04.
[16] C. Wang, Y. Chen, S. Zhang, and Q. Zhang, “Stock market index prediction using deep Transformer model,” Expert Syst. Appl., vol. 208, art. 118128, 2022, doi: 10.1016/j.eswa.2022.118128.
[17] T. Muhammad, A. B. Aftab, M. M. Ahsan, M. M. Muhu, M. Ibrahim, S. I. Khan, et al., “Transformer-based deep learning model for stock price prediction: A case study on Bangladesh stock market,” Int. J. Comput. Intell. Appl., vol. 22, no. 3, art. 2350013, 2023, doi: 10.1142/S146902682350013X.
[18] S. P. Kallimath, N. Darapaneni, and A. R. Paduri, “Deep learning approaches for stock price prediction: A comparative study on Nifty 50 dataset,” EAI Endorsed Trans. Intell. Syst. Mach. Learn. Appl., vol. 1, 2025, doi: 10.4108/eai.ismla.7481.
[19] S. Kulshreshtha and A. Vijayalakshmi, “An ARIMA-LSTM hybrid model for stock market prediction using live data,” J. Eng. Sci. Technol. Rev., vol. 13, no. 4, pp. 117–123, 2020, doi: 10.25103/jestr.134.11.
[20] D. N. Kalange, “Prediction of stock prices using LSTM-ARIMA hybrid deep learning model,” Asian J. Probab. Stat., vol. 27, no. 8, pp. 28–39, 2025, doi: 10.9734/ajpas/2025/v27i8791.
[21] J. Zhang, L. Ye, and Y. Lai, “Stock price prediction using CNN-BiLSTM-Attention model,” Mathematics, vol. 11, no. 9, art. 1985, 2023, doi: 10.3390/math11091985.
[22] W. Lu, J. Li, J. Wang, and L. Qin, “A CNN-BiLSTM-AM method for stock price prediction,” Neural Comput. Appl., vol. 33, pp. 4741–4753, 2021, doi: 10.1007/s00521-020-05532-z.
[23] E. Araya et al., “A hybrid GARCH and deep learning method for volatility prediction,” J. Appl. Math., vol. 2024, art. 6305525, 2024, doi: 10.1155/2024/6305525.
[24] A. T. Haryono, R. Sarno, and K. R. Sungkono, “Transformer-gated recurrent unit method for predicting stock price based on news sentiments and technical indicators,” IEEE Access, vol. 11, pp. 77132–77146, 2023, doi: 10.1109/ACCESS.2023.3298445.
[25] P. Hajek and J. Novotny, “Beyond sentiment in stock price prediction: Integrating news sentiment and investor attention with Temporal Fusion Transformer,” in Artificial Intelligence Applications and Innovations (AIAI 2024), IFIP AICT, vol. 713, Springer, 2024, pp. 30–43, doi: 10.1007/978-3-031-63219-8_3.
[26] M. Cerneviciene and A. Kabasinskas, “Explainable artificial intelligence (XAI) in finance: A systematic literature review,” Artif. Intell. Rev., vol. 57, art. 216, 2024, doi: 10.1007/s10462-024-10854-8.
[27] S. M. Lundberg and S.-I. Lee, “A unified approach to interpreting model predictions,” in Adv. Neural Inf. Process. Syst. (NeurIPS), vol. 30, 2017, pp. 4765–4774.
[28] D. Muhammad, I. Ahmed, K. Naveed, and M. Bendechache, “An explainable deep learning approach for stock market trend prediction,” Heliyon, vol. 10, no. 21, art. e40095, 2024, doi: 10.1016/j.heliyon.2024.e40095.
[29] M. N. Ashtiani and B. Raahemi, “News-based intelligent prediction of financial markets using text mining and machine learning: A systematic literature review,” Expert Syst. Appl., vol. 217, art. 119509, 2023, doi: 10.1016/j.eswa.2023.119509.
[30] L. N. Mintarya, J. N. M. Halim, C. Angie, S. Achmad, and A. Kurniawan, “Machine learning approaches in stock market prediction: A systematic literature review,” Procedia Comput. Sci., vol. 216, pp. 96–102, 2023, doi: 10.1016/j.procs.2022.12.115.
[31] P. Agyarko et al., “Hybrid model for stock market volatility,” J. Probab. Stat., vol. 2023, art. 6124649, 2023, doi: 10.1155/2023/6124649.
[32] I. Dharma et al., “Volatility forecasting using GARCH versus EGARCH models for cryptocurrencies, Indonesian stocks, and U.S. stocks,” Integr. J. Bus. Econ., vol. 9, no. 2, 2025.
[33] L. Rubio, A. Palacio Pinedo, A. Mejía Castaño, and F. Ramos, “Forecasting volatility by using wavelet transform, ARIMA and GARCH models,” Eurasian Econ. Rev., vol. 13, no. 3, pp. 803–830, 2023, doi: 10.1007/s40822-023-00243-x.
[34] A. Kurani, P. Doshi, A. Vakharia, and M. Shah, “A comprehensive comparative study of artificial neural network (ANN) and support vector machines (SVM) on stock forecasting,” Ann. Data Sci., vol. 10, no. 1, pp. 183–208, 2023, doi: 10.1007/s40745-021-00344-x.
[35] J. San, “Stock forecasting and portfolio optimization based on ARIMA-GARCH, Random Forest and Monte Carlo models,” in Proc. ICDEBA 2024, Adv. Econ. Bus. Manag. Res., 2025, pp. 582–591.
[36] S. Selvin, R. Vinayakumar, E. A. Gopalakrishnan, V. K. Menon, and K. P. Soman, “Stock price prediction using LSTM, RNN and CNN-sliding window model,” in Proc. 2017 ICACCI, 2017, pp. 1643–1647, doi: 10.1109/ICACCI.2017.8126078.
[37] V. Vincent, B. J. Saputra, S. Y. Izzatunnisa, H. Lucky, and I. A. Iswanto, “Stock market prediction system using LSTM with technical indicators as voters,” in Proc. 2023 4th Int. Conf. Artificial Intelligence and Data Sciences (AiDAS), 2023, pp. 229–234, doi: 10.1109/AiDAS60501.2023.10284674.
[38] 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.
[39] P. S. Sisodia, A. Gupta, Y. Kumar, and G. K. Ameta, “Stock market analysis and prediction for Nifty 50 using LSTM deep learning approach,” in Proc. 2022 2nd ICIPTM, vol. 2, 2022, pp. 156–161, doi: 10.1109/ICIPTM54933.2022.9753956.
[40] M. E. Karim, M. Foysal, and S. Das, “Stock price prediction using Bi-LSTM and GRU-based hybrid deep learning approach,” in Proc. ICDSA, Lecture Notes in Networks and Systems, Springer, 2023, pp. 701–711, doi: 10.1007/978-981-19-3148-2_60.
[41] M. Lu and X. Xu, “TRNN: An efficient time-series recurrent neural network for stock price prediction,” Inf. Sci., vol. 657, art. 119951, 2024, doi: 10.1016/j.ins.2023.119951.
[42] Y. Qian, “An enhanced Transformer framework with incremental learning for online stock price prediction,” PLOS ONE, vol. 20, no. 1, art. e0316955, 2025, doi: 10.1371/journal.pone.0316955.
[43] X. Li, S. Chen, X. Qiao, and F. Zhao, “Multi-perspective learning based on Transformer for stock price trend,” Int. J. Comput. Intell. Syst., vol. 18, art. 44, 2025, doi: 10.1007/s44196-025-00768-w.
[44] S. Wang, “A stock price prediction method based on BiLSTM and improved Transformer,” IEEE Access, vol. 11, pp. 104211–104223, 2023, doi: 10.1109/ACCESS.2023.3296537.
[45] V. Mahajan, S. Thakan, and A. Malik, “Modeling and forecasting the volatility of NIFTY 50 using GARCH and RNN models,” Economies, vol. 10, no. 5, art. 102, 2022, doi: 10.3390/economies10050102.
[46] D. S. Kotha, T. K. Gundu, and U. M. G. Krishna, “Diving into financial forecasting: Analyzing stock price prediction with LSTM, GRU, and GAN for Nifty50 NSE index,” in Bio-Inspired Computing (IBICA 2023), LNNS, vol. 1229, Springer, 2025, doi: 10.1007/978-3-031-78940-3_25.
[47] W. Bao, J. Yue, and Y. Rao, “A deep learning framework for financial time series using stacked autoencoders and long-short term memory,” PLOS ONE, vol. 12, no. 7, art. e0180944, 2017, doi: 10.1371/journal.pone.0180944.
[48] X. Zhang, S. Qu, J. Huang, B. Fang, and P. S. Yu, “Stock market prediction via multi-source multiple instance learning,” IEEE Access, vol. 6, pp. 50720–50728, 2018, doi: 10.1109/ACCESS.2018.2869735.
[49] M. T. Ribeiro, S. Singh, and C. Guestrin, “‘Why should I trust you?’: Explaining the predictions of any classifier,” in Proc. 22nd ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining (KDD), San Francisco, CA, 2016, pp. 1135–1144, doi: 10.1145/2939672.2939778.
[50] W. J. Yeo, W. Van Der Heever, R. Mao, E. Cambria, R. Satapathy, and G. Mengaldo, “A comprehensive review on financial explainable AI,” Artif. Intell. Rev., vol. 58, art. 189, 2025, doi: 10.1007/s10462-024-11077-7.
[51] L. Dowson, X. Song, and X. Li, “Explainable AI for stock price prediction: A comparative study of deep learning and feature attribution methods,” in Proc. 2025 11th Int. Conf. Communication and Information Processing (ICCIP), Lingshui, China, 2025, pp. 488–494, doi: 10.1145/3784833.3784870.
[52] S. Mehtab and J. Sen, “A robust predictive model for stock price prediction using deep learning and natural language processing,” in Proc. BAICONF, 2019, doi: 10.36227/techrxiv.15023361.

View PDF