Comparative Analysis of Time Series Forecasting Models for Stock Price Prediction: ARIMA, LSTM, and Prophet
Article Sidebar
Main Article Content
Abstract
Stock price forecasting with a uniform approach is a challenging process due to nonlinearity, regime changes, and seasonality. The following paper would like to address the practical problem of selecting an appropriate model through comparing three widely used models such as ARIMA, LSTM, and Prophet based on how they are applied to different attributes of data and forecast-related tasks. The structured direct comparison will be our proposal, as to be able to identify the strengths and shortcomings in abiding by each model. Each of the model is methodologically trained and tested on the same data stock price series and parameterized by the time of standard errors: MAE, MSE, RMSE and MAPE. Experimental design is founded on the canonical setups and reasonable hyperparameters to an algorithm and the results are measured based on the hold-out samples, which have volatile intervals. The results show that under the conditions of intricate dynamics and large volatility, LSTM delivers the greatest general results with MAE = 277.50, MSE = 165,244.61, RMSE = 406.50 and MAPE = 3.09%. ARIMA performs well on stable, approximately linear and stationary segments but struggles with nonlinearity and long-term dependencies. Prophet is effective when strong seasonal patterns are present and is robust to missing values and outliers. We conclude that ARIMA suits stable series, LSTM is preferable for complex and rapidly changing markets, and Prophet is advantageous under pronounced seasonality. These findings offer practical guidance for model selection aligned with data properties and forecasting goals.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
All articles published in JIWE are licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) License. Readers are allowed to
- Share — copy and redistribute the material in any medium or format under the following conditions:
- Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use;
- NonCommercial — You may not use the material for commercial purposes;
- NoDerivatives — If you remix, transform, or build upon the material, you may not distribute the modified material.
References
[1] T. Shen, ‘Machine Learning Applications in Stock Price Prediction’, Advances in Economics, Management and Political Sciences, vol. 94, pp. 257–267, Oct. 2024, doi: 10.54254/2754-1169/94/2024OX0211.
[2] Y. L. Tan, Y. H. Pang, S. Y. Ooi, W. H. Khoh, and F. S. Hiew, ‘Stacking Ensemble Approach for Churn Prediction: Integrating CNN and Machine Learning Models with CatBoost Meta-Learner’, Journal of Engineering Technology and Applied Physics, vol. 5, no. 2, pp. 99–107, Sep. 2023, doi: 10.33093/jetap.2023.5.2.12.
[3] H. H. Mohd Zaki, ‘The Determinants of House Prices in Malaysia’, International Journal of Management, Finance and Accounting, vol. 2, no. 1, pp. 1–18, Feb. 2021, doi: 10.33093/ijomfa.2021.2.1.1.
[4] S. Tiwary and P. K. Mishra, “Time-series forecasting of stock prices using ARIMA: A case study of TESLA and NIO,” Proceedings of the International Conference on Industrial Engineering and Operations Management, 2022, doi: 10.46254/in02.20220427.
[5] C. Pereira da Veiga, C. R. Pereira da Veiga, F. M. Girotto, D. A. B. Marconatto, Z. Su, et al., “Implementation of the ARIMA model for prediction of economic variables: evidence from the health sector in Brazil,” Humanities and Social Sciences Communications, vol. 11, no. 1, pp. 1068, 2024, doi: 10.1057/s41599-024-03023-3.
[6] S. Makridakis, E. Spiliotis, and V. Assimakopoulos, “Statistical and machine learning forecasting methods: Concerns and ways forward,” PLOS ONE, vol. 13, no. 3, pp. e0194889, 2018, doi: 10.1371/journal.pone.0194889.
[7] A. I. E. Nensi, M. Al Maida, K. A. Notodiputro, Y. Angraini, and L. N. A. Mualifah, “Performance analysis of ARIMA, LSTM, and Hybrid ARIMA-LSTM in forecasting the composite stock price index,” CAUCHY Journal of Pure and Applied Mathematics, vol. 10, no. 2, pp. 588–604, 2025, doi: 10.18860/cauchy.v10i2.33379.
[8] I. Sardar, M. A. Akbar, V. Leiva, A. Alsanad, and P. Mishra, “Machine learning and automatic ARIMA/Prophet models-based forecasting of COVID-19,” Stochastic Environmental Research and Risk Assessment, vol. 37, no. 1, pp. 345–359, 2023, doi: 10.1007/s00477-022-02307-x.
[9] M. Y. Wijaya, N. Fitriyati, and N. R. Sandika, “Assessing ARIMA model performance in hierarchical time series forecasting of tourist arrivals: The role of data normalization and bottom-up strategy,” Journal of Modern Applied Statistical Methods, vol. 24, no. 2, pp. 4, 2025, doi: 10.53941/jmasm.2025.100004.
[10] H. A. Adam, F. Raditiansyah, M. R. Imani, M. Faris, and A. R. Lubis, “Comparison of ARIMA and LSTM Models in Stock Price Forecasting: A Case Study of GOTO.JK,” —
[11] X. Pan, “Stock price prediction system LSTM based on deep learning,” Journal of Economics and Public Finance, vol. 10, no. 4, 2024, doi: 10.22158/jepf.v10n4p235.
[12] O. V. Johnson, X. Chew, K. W. Khaw, and Z. L. Chong, “CRATSM: An effective hybridization of deep neural models for customer retention prediction in the telecom industry,” Journal of Engineering Technology and Applied Physics, vol. 6, no. 2, pp. 66–78, 2024, doi: 10.33093/jetap.2024.6.2.10.
[13] C. Pereira da Veiga, C. R. Pereira da Veiga, F. M. Girotto, D. A. B. Marconatto, Z. Su, et al., “Decade-long analysis of sustainable development goals compliance and financial performance tiers in all banking companies listed on Bursa Malaysia,” International Journal of Management, Finance and Accounting, vol. 6, no. 1, pp. 32–86, 2025, doi: 10.33093/ijomfa.2025.6.1.2.
[14] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. MIT Press, 2016.
[15] A. Sunki, C. Satya Kumar, G. Surya Narayana, V. Koppera, and M. Hakeem, “Time series forecasting of stock market using ARIMA, LSTM and FB Prophet,” MATEC Web of Conferences, vol. 392, pp. 01163, 2024, doi: 10.1051/matecconf/202439201163.
[16] S. Chaturvedi, E. Rajasekar, S. Natarajan, and N. McCullen, “A comparative assessment of SARIMA, LSTM RNN and FB Prophet models,” Energy Policy, vol. 168, p. 113097, 2022, doi: 10.1016/j.enpol.2022.113097.
[17] S. J. Taylor and B. Letham, ‘Forecasting at Scale’, The American Statistician, vol. 72, no. 1, pp. 37–45, Jan. 2018, doi: 10.1080/00031305.2017.1380080.
[18] C. Long, C. Yu, and T. Li, “Prophet-based medium and long-term electricity load forecasting research,” Journal of Physics: Conference Series, vol. 2356, no. 1, pp. 012002, 2022, doi: 10.1088/1742-6596/2356/1/012002.
[19] Z. Chen, C. Wang, L. Lv, L. Fan, S. Wen, and Z. Xiang, “Research on peak load prediction of distribution network lines based on Prophet-LSTM model,” Sustainability, vol. 15, no. 15, pp. 11667, 2023, doi: 10.3390/su151511667.
[20] G. Alsheheri, “Comparative analysis of ARIMA and NNAR models for time series forecasting,” Journal of Applied Mathematics and Physics, vol. 13, no. 1, pp. 267–280, 2025, doi: 10.4236/jamp.2025.131012.
[21] C. Jiang, ‘Comparative Analysis of ARIMA and Deep Learning Models for Time Series Prediction’:, in Proceedings of the 2nd International Conference on Data Analysis and Machine Learning, Kuala Lumpur, Malaysia: SCITEPRESS - Science and Technology Publications, 2024, pp. 306–310. doi: 10.5220/0013516200004619.
[22] I. Ahammad, S. K. Roy, M. Hasan, et al., “Advancing stock market predictions with time series analysis including LSTM and ARIMA,” Cloud Computing and Data Science, pp. 226–241, 2024, doi: 10.37256/ccds.5220244470.
[23] D. Duarte and J. Faerman, “Comparison of time series prediction of Healthcare Emergency Department Indicators with ARIMA and Prophet,” 9th International Conference on Computer Science, Engineering and Applications (ICCSEA 2019), pp. 123–133, 2019, doi: 10.5121/csit.2019.91810.
[24] S. Masum, Y. Liu, and J. Chiverton, “Multi-step time series forecasting of electric load using machine learning models,” Springer, pp. 148–159, 2018, doi: 10.1007/978-3-319-91253-0_15.
[25] A. S. Pandit, A. H. B. Jalal, A. K. Toma, and P. Nachev, ‘Analyzing historical and future acute neurosurgical demand using an AI-enabled predictive dashboard’, Sci Rep, vol. 12, no. 1, p. 7603, May 2022, doi: 10.1038/s41598-022-11607-9.
[26] T. Maulenkul, T. Aimyshev, A. Oshibayeva, A. Yazici, et al., ‘Forecasting the future burden of major diseases in Kazakhstan using global burden of disease and time series models (ARIMA, Prophet, LSTM), 2019-2032’, Electronic Journal of General Medicine, vol. 23, no. 1, p. em710, Jan. 2026, doi: 10.29333/ejgm/17734.
[27] L. Menculini, A. Marini, M. Proietti, A. Garinei, et al., “Comparing Prophet and deep learning to ARIMA in forecasting wholesale food prices,” Forecasting, vol. 3, no. 3, pp. 40, 2021, doi: 10.3390/forecast3030040.
[28] U. T. Prodjinotho, P. K. Chetangny, M. B. Agbomahena, V. Zogbochi, L. Medewou, G. Barbier, and D. Chamagne, “Long term forecasting of peak demand and annual electricity consumption of the West African power pool,” International Journal of Energy and Power Engineering, vol. 13, no. 2, 2024, doi: 10.11648/j.ijepe.20241302.11.
[29] M. Fattouh, L. Lyssenko, F. Heilmeyer, T. Ball, and Ch. Haverkamp, ‘Forecasting hospital bed occupancy: a time series approach with prophet’, BMC Medical Informatics and Decision Making, vol. 26, no. 1, p. 162, May 2026, doi: 10.1186/s12911-026-03542-w.
[30] N. Immanuel, “Indonesia Stock Exchange Historical Data,” Kaggle Dataset, 2020.
[31] I. G. T. Suryawan, I. K. N. Putra, P. M. Meliana, and I. G. I. Sudipa, ‘Performance Comparison of ARIMA, LSTM, and Prophet Methods in Sales Forecasting’, SinkrOn, vol. 8, no. 4, pp. 2410–2421, Oct. 2024, doi: 10.33395/sinkron.v8i4.14057.