A novel deep-learning based approach for time series forecasting using sarima, neural prophet and fb prophet

Authors

Keywords:

Time-series analysis, Time-Series forecasting, artificial intelligence, SARIMA, Neural prophet model, Fb prophet model, Evaluation parameters

Abstract

Objective: The article aims to explore and evaluate a novel deep-learning approach for time series forecasting using three specific models: SARIMA (Seasonal Auto-Regressive Integrated Moving Average), Neural Prophet, and Facebook Prophet. The primary goal is to assess the effectiveness of these models in predicting stock market values in the Gulf region, providing insights into the best-suited models for forecasting tasks.

Methods: The study employs Python libraries and frameworks to implement the SARIMA, Neural Prophet, and Facebook Prophet models. The models are trained using stock market data from the Mulkia Gulf Real Estate dataset. The methodology includes data preprocessing, model training, evaluation, and comparison using metrics such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE).

Results: The evaluation results show that SARIMA performs well in general prediction tasks, especially when datasets contain seasonality trends. Facebook Prophet excels with smaller datasets containing seasonal data, while Neural Prophet demonstrates its ability to capture complex, non-linear patterns. However, Neural Prophet requires more intricate data and fine-tuning for optimal results.

Contribution: This study provides a comparative analysis of deep-learning models for time series forecasting, offering valuable insights into their strengths and weaknesses. The findings contribute to the understanding of which models are most suitable for stock market prediction and how they can be adapted to different data types and scenarios.

Conclusion: The research concludes that each model—SARIMA, Facebook Prophet, and Neural Prophet—has its unique strengths in time series forecasting. SARIMA is reliable for handling seasonal data, Facebook Prophet is efficient for smaller datasets with clear trends, and Neural Prophet is best for more complex datasets. The study highlights the importance of selecting the appropriate model based on the specific requirements of the forecasting task.

References

Bergmeir, C., Hyndman, R. J., & Koo, B. (2018). A note on the validity of cross-validation for evaluating autoregressive time series prediction. Computational Statistics & Data Analysis, 120, 70-83.

Cerqueira, V., Torgo, L., & Mozetič, I. (2020). Evaluating time series forecasting models: An empirical study on performance estimation methods. Machine Learning, 109, 1997-2028.

Chatfield, C (2000). Time-series forecasting. CRC press.

González Mata, A. (2020). A comparison between LSTM and Facebook Prophet models: a financial forecasting case study.

Jha, B. K., & Pande, S. (2021). Time series forecasting model for supermarket sales using FB-prophet. In 2021 5th International Conference on Computing Methodologies and Communication (ICCMC) (pp. 547-554). IEEE.

Khare, K., Darekar, O., Gupta, P., & Attar, V. Z. (2017, May). Short term stock price prediction using deep learning. In 2017 2nd IEEE international conference on recent trends in electronics, information & communication technology (RTEICT) (pp. 482-486). IEEE.

Kritharas, P. (2014). Developing a SARIMAX model for monthly wind speed forecasting in the uk (Doctoral dissertation, Loughborough University).

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.

Madsen, H. (2007). Time series analysis. CRC Press.

Mahmud, S. (2020). Bangladesh COVID-19 daily cases time series analysis using Facebook prophet model. Available at SSRN 3660368.

Masini, R. P., Medeiros, M. C., & Mendes, E. F. (2023). Machine learning advances for time series forecasting. Journal of economic surveys, 37(1), 76-111.Nikou, M., Mansourfar, G., & Bagherzadeh, J. (2019). Stock price prediction using DEEP learning algorithm and its comparison with machine learning algorithms. Intelligent Systems in Accounting, Finance and Management, 26(4), 164-174.

Nontapa, C., Kesamoon, C., Kaewhawong, N., & Intrapaiboon, P. (2021). A New Hybrid Forecasting Using Decomposition Method with SARIMAX Model and Artificial Neural Network. Computer Science, 16(4), 1341-1354.

Samek, W., Montavon, G., Lapuschkin, S., Anders, C. J., & Müller, K. R. (2021). Explaining deep neural networks and beyond: A review of methods and applications. Proceedings of the IEEE, 109(3), 247-278.

Shohan, M. J. A., Faruque, M. O., & Foo, S. Y. (2022). Forecasting of electric load using a hybrid LSTM-neural prophet model. Energies, 15(6), 2158.

Sivaramakrishnan, S., Fernandez, T. F., Babukarthik, R. G., & Premalatha, S. (2022). Forecasting time series data using arima and facebook prophet models. In Big data management in Sensing (pp. 47-59). River Publishers.

Torres, J. F., Hadjout, D., Sebaa, A., Martínez-Álvarez, F., & Troncoso, A. (2021). Deep learning for time series forecasting: a survey. Big Data, 9(1), 3-21.

Triebe, O., Hewamalage, H., Pilyugina, P., Laptev, N., Bergmeir, C., & Rajagopal, R. (2021). Neuralprophet: Explainable forecasting at scale. arXiv preprint arXiv:2111.15397.

Zunic, E., Korjenic, K., Hodzic, K., & Donko, D. (2020). Application of facebook's prophet algorithm for successful sales forecasting based on real-world data. arXiv preprint arXiv:2005.07575.

Downloads

Published

2024-05-06

How to Cite

Albeladi, K., Zafar, B., & Mueen, A. (2024). A novel deep-learning based approach for time series forecasting using sarima, neural prophet and fb prophet. Journal of Management & Technology, 24(Special), 72–86. Retrieved from https://revistagt.fpl.emnuvens.com.br/get/article/view/2818

Issue

Vol. 24 No. Special (2024)

Section

ARTIGO

License

Copyright (c) 2024 Journal of Management & Technology

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Authors who publish with this journal agree to the following terms: • 1. The author(s) authorize the publication of the article in the journal. • 2. The author(s) ensure that the contribution is original and unpublished and is not being evaluated in other journal(s). • 3. The journal is not responsible for the opinions, ideas and concepts expressed in the texts because they are the sole responsibility of the author(s). • 4. The publishers reserve the right to make adjustments and textual adaptation to the norms of APA. • 5. Authors retain copyright and grant the journal right of first publication, with the work [SPECIFY PERIOD OF TIME] after publication simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal. • 6. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal. • 7. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access) at http://opcit.eprints.org/oacitation-biblio.html