Prediksi Inflasi Indonesia Berdasarkan Fuzzy Ann Menggunakan Algoritma Genetika

Authors

  • Anwar Rifa'i Universitas Budi Luhur, Jakarta, Indonesia

DOI:

https://doi.org/10.31961/eltikom.v5i1.215

Keywords:

Backpropagation, Genetic Algorithm, Inflation, Neural Network, Prediction

Abstract

Monetary policy makers have a fear of inflation because it can trigger an increase in poverty and soar-ing budget uses. A high level of inflation will result in a country's economic collapse. Monetary policy making needs to be studied to prevent this. One effort that can be done is to predict the inflation that will occur. Inflation rate time series data can be used to predict future inflation rates. Pemangku kebijakan moneter memiliki ketakutan terhadap inflasi karena dapat memicu naiknya angka kemiskinan dan mel-onjaknya penggunaan anggaran. Tingkat Inflasi yang tinggi akan mengakibatkan jatuhnya perekonomian suatu negara. Pengambilan kebijakan moneter perlu dikaji secara mendalam untuk mencegah hal terse-but. Salah satu upaya yang dapat dilakukan adalah dengan melakukan prediksi inflasi yang akan terjadi. Data tingkat inflasi dari waktu ke waktu merupakan modal untuk melakukan prediksi tingkat inflasi pada waktu mendatang. Suatu prediksi yang baik memiliki nilai error yang kecil. Pada prediksi menggunakan fuzzy artificial neural network (Fuzzy ANN) metode backpropagation, nilai error dapat diperkecil dengan melakukan optimasi pada bobot yang dihasilkan. Pada penelitian ini, optimasi bobot Fuzzy AAN dil-akukan menggunakan algoritma genetika. Model prediksi yang diperoleh selanjutnya dievaluasi menggunakan MAPE untuk menentukan keakuratan prediksi. Hasil penelitian menunjukkan bahwa pred-iksi menggunakan backpropagation neural network dioptimasi menggunakan algoritma genetika (10,33%) lebih baik dibandingkan dengan prediksi menggunakan backpropagation neural network saja (11,67%). Setelah mengetahui bahwa kedua model memiliki hasil prediksi yang cukup baik, keakuratan kedua model dibandingkan menggunakan independent sampe t-test berdasarakan error yang dihasilkan. Hasilnya menjukkan bahwa pada tingkat kepercayaan 95% prediksi menggunakan Fuzzy ANN yang telah dioptimasi menggunakan algoritma genetika (M= 0,69, SD= 0,0421) lebih baik secara signifikan dibandingkan degan fuzzy  ANN saja (M= 0.97, SD= 0,04634 ),  t(22 )= 1.71714, p=0.013.

Downloads

Download data is not yet available.

References

M. Uddin and A. Moniruzzaman, “Inflation, inflation uncertainty and relative price variability in Bangladesh,” Eurasian Econ. Rev., no. 6, pp. 389–427, 2016, doi: 10.1007/s40822-016-0055-8.
K. U. Ehigiamusoe, H. H. Lean, and C. C. Lee, “Moderating effect of inflation on the finance–growth nexus: insights from West Afri-can countries,” Empir. Econ., vol. 57, no. 2, pp. 399–422, 2019, doi: 10.1007/s00181-018-1442-7.
J. H. Powell, “Monetary policy and risk management at a time of low inflation and low unemployment,” Bus. Econ., vol. 53, no. 4, pp. 173–183, 2018, doi: 10.1057/s11369-018-0099-8.
L. A. Gil-Alana, A. Mervar, and J. E. Payne, “The stationarity of inflation in Croatia: anti-inflation stabilization program and the change in persistence,” Econ. Chang. Restruct., vol. 50, no. 1, pp. 45–58, 2017, doi: 10.1007/s10644-016-9181-2.
N. Videla, “Hamilton–Jacobi approach for quasi-exponential inflation: predictions and constraints after Planck 2015 results,” Eur. Phys. J. C, vol. 77, no. 3, 2017, doi: 10.1140/epjc/s10052-017-4711-2.
Y. Wang, Y. Tu, and S. X. Chen, “Improving inflation prediction with the quantity theory,” Econ. Lett., vol. 149, pp. 112–115, 2016, doi: 10.1016/j.econlet.2016.10.023.
M. Tule, A. Salisu, and C. Chiemeke, “Improving Nigeria’s Inflation Forecast with Oil Price: The Role of Estimators,” J. Quant. Econ., 2019, doi: 10.1007/s40953-019-00178-8.
W. P. Gaglianone, J. V. Issler, and S. M. Matos, “Applying a microfounded-forecasting approach to predict Brazilian inflation,” Empir. Econ., vol. 53, no. 1, pp. 137–163, 2017, doi: 10.1007/s00181-016-1163-8.
J.-S. Jang, C.-T. Sun, and E. Mizutani, Neuro Fuzzy and Soft Computing. Prentice Hall, 1997.
J. Nayak, G. T. Chandrasekhar, B. Naik, D. Pelusi, and A. Abraham, “Special issue on ‘Soft computing techniques: applications and challenges’ neural computing and applications,” Neural Comput. Appl., vol. 32, no. 12, p. 7585, 2020, doi: 10.1007/s00521-020-04902-x.
K. Szafranek, “Bagged neural networks for forecasting Polish (low) inflation,” Int. J. Forecast., vol. 35, no. 3, pp. 1042–1059, 2019, doi: 10.1016/j.ijforecast.2019.04.007.
G. S. M. Thakur, R. Bhattacharyya, and S. S. Mondal, “Artificial Neural Network Based Model for Forecasting of Inflation in India,” Fuzzy Inf. Eng., vol. 8, no. 1, pp. 87–100, 2016, doi: 10.1016/j.fiae.2016.03.005.
N. R. Sari, W. F. Mahmudy, and A. P. Wibawa, “Backpropagation on neural network method for inflation rate forecasting in Indone-sia,” Int. J. Adv. Soft Comput. its Appl., vol. 8, no. 3, pp. 69–87, 2016.
Y. Yolanda, “Analysis of factors affecting inflation and its impact on human development index and poverty in Indonesia,” Eur. Res. Stud. J., vol. 20, no. 4, pp. 38–56, 2017, doi: 10.35808/ersj/873.
Suyanto, Artificial Intelligence Searching, Reasoning, Planning, dan Learning Revisi Kedua. Bandung: Informatika Bandung, 2014.
Z. Chen, A. Huang, and X. Qiang, “Improved Neural Networks Based on Genetic Algorithm for Pulse Recognition,” Comput. Biol. Chem., vol. 88, no. May, p. 107315, 2020, doi: 10.1016/j.compbiolchem.2020.107315.
X. Wang and B. Wang, “Research on prediction of environmental aerosol and PM2.5 based on artificial neural network,” Neural Comput. Appl., vol. 31, no. 12, pp. 8217–8227, Dec. 2019, doi: 10.1007/s00521-018-3861-y.
Y. chen Wu and J. wen Feng, “Development and Application of Artificial Neural Network,” Wirel. Pers. Commun., vol. 102, no. 2, pp. 1645–1656, 2018, doi: 10.1007/s11277-017-5224-x.
R. Fuller, Neural Fuzzy Systems. Åbo: Åbo Akademi., 1995.
L.-X. Wang, A Course in Fuzzy Systems and Control. Prentice-Hall, 1997.
N. Borisagar, D. Barad, and P. Raval, “Chronic Kidney Disease Prediction Using Back Propagation Neural Network Algorithm,” in Proceedings of International Conference on Communication and Networks, 2017, vol. 508, pp. 295–303, doi: 10.1007/978-981-10-2750-5.
Y. Liu, Y. Chen, S. Wu, G. Peng, and B. Lv, “Composite leading search index: a preprocessing method of internet search data for stock trends prediction,” Ann. Oper. Res., vol. 234, no. 1, pp. 77–94, 2015, doi: 10.1007/s10479-014-1779-z.

Downloads

Published

15-05-2022

How to Cite

[1]
Rifa’i, A. 2022. Prediksi Inflasi Indonesia Berdasarkan Fuzzy Ann Menggunakan Algoritma Genetika. Jurnal ELTIKOM : Jurnal Teknik Elektro, Teknologi Informasi dan Komputer. 5, 1 (May 2022), 12–24. DOI:https://doi.org/10.31961/eltikom.v5i1.215.

Issue

Section

Articles