PERBANDINGAN KINERJA GRU DAN SVR UNTUK PREDIKSI EMAS DI INDONESIA
DOI:
https://doi.org/10.51903/informatika.v5i1.1105Keywords:
Prediksi Harga Emas, Gated Recurrent Unit, SVR, Analisis Deret Waktu, Deep LearningAbstract
Emas merupakan instrumen investasi yang banyak diminati di Indonesia, terutama saat terjadi ketidakstabilan ekonomi. Namun, volatilitas harga emas yang dipengaruhi oleh faktor makroekonomi domestik dan global membuat prediksinya menjadi tantangan tersendiri. Penelitian ini membandingkan kinerja dua model prediksi, yaitu Gated Recurrent Unit (GRU) dan Support Vector Regression (SVR), dalam meramalkan harga emas jangka pendek berdasarkan data historis harian periode 2020–2025 sebanyak 1.345 data. Data diolah melalui proses normalisasi dan pembentukan data sekuensial dengan jendela waktu 60 hari. Kedua model dievaluasi menggunakan metrik regresi seperti RMSE, MAE, MSE, dan R². Hasil menunjukkan bahwa model GRU lebih unggul dibandingkan SVR dalam menangkap pola non-linear dan temporal pada data deret waktu, serta menghasilkan prediksi yang lebih akurat. Harga emas pada 7 Mei 2025 diperkirakan sebesar Rp1.736.978. Temuan ini menunjukkan bahwa model deep learning seperti GRU memiliki potensi besar dalam analisis data keuangan dan dapat memberikan kontribusi praktis bagi investor, peneliti, dan pembuat kebijakan. Penelitian selanjutnya disarankan untuk mengintegrasikan variabel makroekonomi dan pendekatan hybrid guna meningkatkan akurasi prediksi.
References
[1] U. Kalsum, R. Hidayat, and S. Oktaviani, “The Effect of Inflation, US Dollar Exchange Rates, Interest Rates, and World Oil Prices on Gold Price Fluctuations in Indonesia 2014 – 2019,” Journal of Business Management Review, vol. 1, no. 3, pp. 155–171, Sep. 2020, doi: 10.47153/jbmr13.342020.
[2] S. L. Sentiko, A. Y. Zakiyyah, and Meiliana, “Gold Price Prediction Using Machine Learning and Deep Learning,” in 2024 6th International Conference on Cybernetics and Intelligent System (ICORIS), IEEE, Nov. 2024, pp. 1–5. doi: 10.1109/ICORIS63540.2024.10903557.
[3] V. G. S and H. V S, “Gold Price Prediction and Modelling using Deep Learning Techniques,” in 2020 IEEE Recent Advances in Intelligent Computational Systems (RAICS), IEEE, Dec. 2020, pp. 28–31. doi: 10.1109/RAICS51191.2020.9332471.
[4] S. Annas, Z. Rais, A. Aswi, Indrayasaro, and Nurfajriani, “Implementation of Support Vector Regression (SVR) Analysis in Predicting Gold Prices in Indonesia,” 2023, pp. 97–107. doi: 10.2991/978-94-6463-332-0_12.
[5] M. YURTSEVER, “Gold Price Forecasting Using LSTM, Bi-LSTM and GRU,” European Journal of Science and Technology, Dec. 2021, doi: 10.31590/ejosat.959405.
[6] S. B. Primananda and S. M. Isa, “Forecasting Gold Price in Rupiah using Multivariate Analysis with LSTM and GRU Neural Networks,” Advances in Science, Technology and Engineering Systems Journal, vol. 6, no. 2, pp. 245–253, Mar. 2021, doi: 10.25046/aj060227.
[7] M. R. Pahlevi, K. Kusrini, and T. Hidayat, “Comparison of LSTM and GRU Models for Forex Prediction,” sinkron, vol. 8, no. 4, pp. 2254–2263, Oct. 2023, doi: 10.33395/sinkron.v8i4.12709.
[8] J. Lian, “Comparative Analysis of LSTM, GRU and Transformer Deep Learning Models for Cryptocurrency ZEC Price Prediction Performance,” 2024, pp. 396–405. doi: 10.2991/978-94-6463-408-2_45.
[9] M. J. Hamayel and A. Y. Owda, “A Novel Cryptocurrency Price Prediction Model Using GRU, LSTM and bi-LSTM Machine Learning Algorithms,” AI, vol. 2, no. 4, pp. 477–496, Oct. 2021, doi: 10.3390/ai2040030.
[10] N. P. J. R. Dewi, N. L. W. S. R. Ginantra, I. W. A. S. Darma, and I. G. A. Indrawan, “Application of Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) Algorithm in Gold Price Prediction,” in 2023 11th International Conference on Cyber and IT Service Management (CITSM), IEEE, Nov. 2023, pp. 1–6. doi: 10.1109/CITSM60085.2023.10455749.
[11] A. Mohammadjafari, “Comparative Study of Bitcoin Price Prediction,” May 2024, [Online]. Available: http://arxiv.org/abs/2405.08089
[12] A. Bouteska, M. Z. Abedin, P. Hajek, and K. Yuan, “Cryptocurrency price forecasting – A comparative analysis of ensemble learning and deep learning methods,” International Review of Financial Analysis, vol. 92, p. 103055, Mar. 2024, doi: 10.1016/j.irfa.2023.103055.
[13] R. Kaur et al., “Development of a cryptocurrency price prediction model: leveraging GRU and LSTM for Bitcoin, Litecoin and Ethereum,” PeerJ Comput Sci, vol. 11, p. e2675, Mar. 2025, doi: 10.7717/peerj-cs.2675.
[14] G. D. Aryoso, B. Kanata, and M. S. Yadnya, “Rainfall Prediction Using Gate Recurrent Unit (Gru) for The Mataram City Area,” Jurnal Penelitian Pendidikan IPA, vol. 11, no. 2, pp. 1114–1119, 2025, doi: 10.29303/jppipa.v11i2.9874.
[15] J. M. Valente and S. Maldonado, “SVR-FFS: A novel forward feature selection approach for high-frequency time series forecasting using support vector regression,” Expert Syst Appl, vol. 160, p. 113729, Dec. 2020, doi: 10.1016/j.eswa.2020.113729.
[16] M. Bai et al., “Deep graph gated recurrent unit network-based spatial–temporal multi-task learning for intelligent information fusion of multiple sites with application in short-term spatial–temporal probabilistic forecast of photovoltaic power,” Expert Syst Appl, vol. 240, p. 122072, Apr. 2024, doi: 10.1016/j.eswa.2023.122072.
[17] B. Wen et al., “Scalable and Efficient Support Vector Regression Model in Power Systems,” in 2024 IEEE Smart World Congress (SWC), IEEE, Dec. 2024, pp. 2532–2538. doi: 10.1109/SWC62898.2024.00382.
[18] Md. J. Islam, S. Ahmad, F. Haque, M. B. I. Reaz, M. A. S. Bhuiyan, and Md. R. Islam, “Application of Min-Max Normalization on Subject-Invariant EMG Pattern Recognition,” IEEE Trans Instrum Meas, vol. 71, pp. 1–12, 2022, doi: 10.1109/TIM.2022.3220286.
[19] H. W. Herwanto, A. N. Handayani, A. P. Wibawa, K. L. Chandrika, and K. Arai, “Comparison of Min-Max, Z-Score and Decimal Scaling Normalization for Zoning Feature Extraction on Javanese Character Recognition,” in 2021 7th International Conference on Electrical, Electronics and Information Engineering (ICEEIE), IEEE, Oct. 2021, pp. 1–3. doi: 10.1109/ICEEIE52663.2021.9616665.
[20] M. DAGHARI, C. ABDELHAMID, H. SAKLI, and D. SEETHARAMDOO, “Design And Simulations Of Stable Pass-Band Filtering Response Using Miniaturized Element Frequency Selective Surface (MEFSS),” in 2019 15th International Wireless Communications & Mobile Computing Conference (IWCMC), IEEE, Jun. 2019, pp. 821–825. doi: 10.1109/IWCMC.2019.8766557.
[21] H. S. Obaid, S. A. Dheyab, and S. S. Sabry, “The Impact of Data Pre-Processing Techniques and Dimensionality Reduction on the Accuracy of Machine Learning,” in 2019 9th Annual Information Technology, Electromechanical Engineering and Microelectronics Conference (IEMECON), IEEE, Mar. 2019, pp. 279–283. doi: 10.1109/IEMECONX.2019.8877011.
[22] Y.-S. Kim, M. K. Kim, N. Fu, J. Liu, J. Wang, and J. Srebric, “Investigating the impact of data normalization methods on predicting electricity consumption in a building using different artificial neural network models,” Sustain Cities Soc, vol. 118, p. 105570, Jan. 2025, doi: 10.1016/j.scs.2024.105570.
[23] M. Abumohsen, A. Y. Owda, and M. Owda, “Electrical Load Forecasting Using LSTM, GRU, and RNN Algorithms,” Energies (Basel), vol. 16, no. 5, p. 2283, Feb. 2023, doi: 10.3390/en16052283.
[24] H. Ismail Fawaz, G. Forestier, J. Weber, L. Idoumghar, and P.-A. Muller, “Deep learning for time series classification: a review,” Data Min Knowl Discov, vol. 33, no. 4, pp. 917–963, Jul. 2019, doi: 10.1007/s10618-019-00619-1.
[25] P. Jia, H. Liu, S. Wang, and P. Wang, “Research on a Mine Gas Concentration Forecasting Model Based on a GRU Network,” IEEE Access, vol. 8, pp. 38023–38031, 2020, doi: 10.1109/ACCESS.2020.2975257.
[26] G. Bathla, “Stock Price prediction using LSTM and SVR,” in 2020 Sixth International Conference on Parallel, Distributed and Grid Computing (PDGC), IEEE, Nov. 2020, pp. 211–214. doi: 10.1109/PDGC50313.2020.9315800
.png)
