Article Sidebar

Download
PDF
Statistic
Read Counter : 66 Download : 67

Main Article Content

Abstract

This study forecasted inflation in Indonesia using the Recurrent Neural Network Long Short-Term Memory (RNN-LSTM) model, ideal for nonlinear, complex time series data. It evaluated the effects of different activation functions, such as Logistic, Gompertz, and Hyperbolic Tangent (tanh); and weight update methods, such as Stochastic Gradient Descent (SGD) and Adaptive Gradient (AdaGrad) on RNN-LSTM performance. Monthly inflation data from January 2005 to December 2023 underwent preprocessing, including normalization and autoregressive lag-based input selection. Model accuracy was assessed with Root Mean Squared Error (RMSE) and Symmetric Mean Absolute Percentage Error (SMAPE). The findings indicated that the RNN-LSTM model with the logistic activation function and SGD optimization achieved the highest accuracy, outperforming traditional models such as Exponential Smoothing (ETS), Autoregressive Integrated Moving Average (ARIMA), Feedforward Neural Network (FFNN), and Recurrent Neural Network (RNN). Additionally, optimal learning rate and epoch values were identified, enhancing model stability and precision. In conclusion, the study confirms that the RNN-LSTM model is effective for inflation forecasting when optimized with specific activation functions and optimization methods. It recommends further exploration of neuron configurations and alternative models, such as the Gated Recurrent Unit (GRU), to improve forecast accuracy.  

Keywords

forecasting inflation frequency approach SGD RNN-LSTM

Article Details

License

Authors who publish with this journal agree to the following terms:

  1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
  2. 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 acknowledgment of its initial publication in this journal.
  3. 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).
How to Cite
Hermansah, Muhajir, M. ., & Canas Rodrigues, P. . (2024). Indonesian Inflation Forecasting with Recurrent Neural Network Long Short-Term Memory (RNN-LSTM). Enthusiastic : International Journal of Applied Statistics and Data Science, 4(2), 132–142. https://doi.org/10.20885/enthusiastic.vol4.iss2.art5
Download Citation
Endnote/Zotero/Mendeley (RIS)
BibTeX

References

  1. D. Ruhiat and C. Suwanda, “Peramalan Data Deret Waktu Berpola Musiman Menggunakan Metode Regresi Spektral (Studi Kasus: Debit Sungai Citarum-Nanjung),” Teorema Teori dan Riset Matematika, Vol. 4, No. 1, pp. 1–12, Mar. 2019, doi: 10.25157/teorema.v4i1.1887.
  2. R.B.R. Putra and H. Hendry, “Multivariate Time Series Forecasting pada Penjualan Barang Retail dengan Recurrent Neural Network,” Jurnal Inovtek Polbeng Seri Informatika, Vol. 7, No. 1, pp. 71–82, Jun. 2022, doi: 10.35314/isi.v7i1.2398.
  3. C. Tian, J. Ma, C. Zhang, and P. Zhan, “A Deep Neural Network Model for Short-Term Load Forecast Based on Long Short-Term Memory Network and Convolutional Neural Network,” Energies, Vol. 11, No. 12, Dec. 2018, Art. no. 3493, doi: 10.3390/en11123493.
  4. W. Hastomo, A.S.B. Karno, N. Kalbuana, E. Nisfiani, and L. ETP, “Optimasi Deep Learning untuk Prediksi Saham di Masa Pandemi Covid-19,” Jurnal Edukasi dan Penelitian Informatika, Vol. 7, No. 2, pp.140–133, Aug. 2021, doi: 10.26418/jp.v7i2.47411.
  5. M.W.P. Aldi, Jondri, and A. Aditsania, “Analisis dan Implementasi Long Short Term Memory Neural Network untuk Prediksi Harga Bitcoin,” e-Proceeding of Engineering, Vol. 5, No. 2, pp. 3548–3555, 2018.
  6. C.H. Cordova, M.N.L. Portocarrero, R. Salas, R. Torres, P.C. Rodrigues, and J.L. López-Gonzales, “Air Quality Assessment and Pollution Forecasting Using Artificial Neural Networks in Metropolitan Lima-Peru,” Scientific Reports, Vol. 11, No. 1, Dec. 2021, Art. no. 24232 (2021), doi: 10.1038/s41598-021-03650-9.
  7. K. Wong, A.P. Wibawa, H.S. Pakpahan, A. Prafanto, and H.J. Setyadi, “Prediksi Tingkat Inflasi Dengan Menggunakan Metode Backpropagation Neural Network,” Sains, Aplikasi, Komputasi dan Teknologi Informasi, Vol. 1, No. 2, pp. 8–13, Aug. 2019, doi: 10.30872/jsakti.v1i2.2600.
  8. B. Hauriza, M. Muladi, and I.M. Wirawan, “Prediksi Tingkat Inflasi Bulanan Indonesia Menggunakan Metode Jaringan Saraf Tiruan,” Jurnal Teknologi dan Informasi, Vol. 11, No. 2, pp. 152–167, Sep. 2021, doi: 10.34010/jati.v11i2.4924.
  9. H. Hermansah, D. Rosadi, A. Abdurakhman, and H. Utami, “Automatic Time Series Forecasting Using Nonlinear Autoregressive Neural Network Model With Exogenous Input,” Bulletin of Electrical Engineering and Informatics, Vol. 10, No. 5, pp. 2836–2844, Oct. 2021, doi: 10.11591/eei.v10i5.2862.
  10. P. Cihan, “Effect of Parameter Selection on Heart Attack Risk Prediction in an RNN Model,” in 5th International Conference on Applied Engineering and Natural Sciences ICAENS 2023, 2023, pp. 56–60, doi: 10.59287/icaens.964.
  11. B. Xu, R. Huang, and M. Li, “Revise Saturated Activation Functions,” 2016, arXiv:1602.05980.
  12. O.A. Vilca-Huayta and U. Y. Tito, “Efficient Function Integration and a Case Study with Gompertz Functions for Covid-19 Waves,” International Journal of Advanced Computer Science and Applications (IJACSA), Vol. 13, No. 8, pp. 545–551, 2022, doi: 10.14569/IJACSA.2022.0130863.
  13. T. De Ryck, S. Lanthaler, and S. Mishra, “On the Approximation of Functions by Tanh Neural Networks,” Neural Networks, Vol. 143, pp. 732–750, Nov. 2021, doi: 10.1016/j.neunet.2021.08.015.
  14. K. Banerjee et al., “Optimizing Deep Learning RNN Topologies on Intel Architecture,” Supercomputer Frontiers and Innovations, Vol. 6, No. 3, pp. 64–85, Sep. 2019, doi: 10.14529/jsfi190304.
  15. M. Xia, H. Shao, X. Ma, and C.W. de Silva, “A Stacked GRU-RNN-Based Approach for Predicting Renewable Energy and Electricity Load for Smart Grid Operation,” IEEE Transactions on Industrial Informatics, Vol. 17, No. 10, pp. 7050–7059, Oct. 2021, doi: 10.1109/TII.2021.3056867.
  16. T. Szandała, “Review and Comparison of Commonly Used Activation Functions for Deep Neural Networks,” in Bio-inspired Neurocomputing, Vol. 903, A.K. Bhoi, P.K. Mallick, C.-M. Liu, and V. E. Balas, Eds., Singapore, Singapore: Springer, 2021, pp. 203–224, doi: 10.1007/978-981-15-5495-7_11.
  17. M.H.E. Ali, A.B. Abdel-Raman, and E.A. Badry, “Developing Novel Activation Functions Based Deep Learning LSTM for Classification,” IEEE Access, Vol. 10, pp. 97259–97275, 2022, doi: 10.1109/ACCESS.2022.3205774.
  18. P. Ranjan, P. Khan, S. Kumar, and S.K. Das, “log-Sigmoid Activation-Based Long Short-Term Memory for Time-Series Data Classification,” IEEE Transactions on Artificial Intelligence, Vol. 5, No. 2, pp. 672–683, Feb. 2024, doi: 10.1109/TAI.2023.3265641.
  19. Data Strategis BPS. Badan Pusat Statistik, 2009. [Online]. Available: https://www.bps.go.id/id/publication/2009/08/15/70be6e12dc0e2d87204a6d58/data-strategis-bps-2009.html. Accessed: September 16, 2024.
  20. R.J. Hyndman, A.B. Koehler, R.D. Snyder, and S. Grose, “A State Space Framework for Automatic Forecasting Using Exponential Smoothing Methods,” International Journal of Forecasting, Vol. 18, No. 3, pp. 439–454, Jul. 2002, doi: 10.1016/S0169-2070(01)00110-8.
  21. R.J. Hyndman and Y. Khandakar, “Automatic Time Series Forecasting: The forecast Package for R,” Journal of Statistical Software, Vol. 27, No. 3, pp. 1–22, 2008, doi: 10.18637/jss.v027.i03.
  22. H. Hermansah, D. Rosadi, A. Abdurakhman, and H. Utami, “Selection of Input Variables of Nonlinear Autoregressive Neural Network Model for Time Series Data Forecasting,” Media Statistika, Vol. 13, No. 2, pp. 116–124, Dec. 2020, doi: 10.14710/medstat.13.2.116-124.
  23. F. Martínez, F. Charte, M.P. Frías, and A.M. Martínez-Rodríguez, “Strategies for Time Series Forecasting with Generalized Regression Neural Networks,” Neurocomputing, Vol. 491, pp. 509–521, Jun. 2022, doi: 10.1016/j.neucom.2021.12.028.
  24. A.A. Rizal and S. Soraya, “Multi Time Steps Prediction dengan Recurrent Neural Network Long Short Term Memory,” MATRIK Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer, Vol. 18, No. 1, pp. 115–124, Nov. 2018, doi: 10.30812/matrik.v18i1.344.
  25. S. Sen, D. Sugiarto, and A. Rochman, “Komparasi Metode Multilayer Perceptron (MLP) dan Long Short Term Memory (LSTM) dalam Peramalan Harga Beras,” Ultimatics Jurnal Teknik Informatika, Vol. 12, No. 1, pp. 35–41, Jul. 2020, doi: 10.31937/ti.v12i1.1572.
  26. C. Yin, Y. Zhu, J. Fei, and X. He, “A Deep Learning Approach for Intrusion Detection Using Recurrent Neural Networks,” IEEE Access, Vol. 5, pp. 21954–21961, 2017, doi: 10.1109/ACCESS.2017.2762418.
  27. I.N. Husada and H. Toba, “Pengaruh Metode Penyeimbangan Kelas Terhadap Tingkat Akurasi Analisis Sentimen pada Tweets Berbahasa Indonesia,” Jurnal Teknik Informatika dan Sistem Informasi, Vol. 6, No. 2, pp. 400–413, Aug. 2020, doi: 10.28932/jutisi.v6i2.2743.
  28. J. Qiu, B. Wang, and C. Zhou, “Forecasting Stock Prices with Long-Short Term Memory Neural Network Based on Attention Mechanism,” PLoS One, Vol. 15, No. 1, Jan. 2020, Art. no. e0227222, doi: 10.1371/journal.pone.0227222.
  29. N.S. Keskar and R. Socher, “Improving Generalization Performance by Switching from Adam to SGD,” 2017, arXiv: 1712.07628.
  30. A.K. Tyagi and A. Abraham, Recurrent Neural Networks. Boca Raton, FL, USA: CRC Press, 2022.