Gold Price Prediction Using a Hybrid LSTM and Prophet Model Enhanced with News Sentiment Analysis
Keywords:
Gold price forecasting, LSTM, Prophet, Hybrid model, Sentiment analysisAbstract
This study aims to improve the accuracy of gold price forecasting by combining statistical and deep learning methods with sentiment analysis. Three models were developed and compared: (1) a pure Long Short-Term Memory (LSTM) model, (2) a hybrid LSTM + Prophet model, and (3) a hybrid LSTM + Prophet + Sentiment model. The datasets consisted of daily gold prices and financial news sentiment from 2013 to 2023. Each model was evaluated using Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), R-squared (R2), and Mean Absolute Percentage Error (MAPE). The pure LSTM model achieved an R2 of 0.9375, while the hybrid LSTM + Prophet model improved performance to 0.9394 with lower error rates. The integration of sentiment data resulted in stable but not significantly higher accuracy. Overall, the hybrid LSTM + Prophet model produced the best results, confirming that combining statistical trend decomposition with deep learning effectively enhances forecasting stability and interpretability for financial time series data such as gold prices.
Downloads
References
[1] D. Makala and Z. Li, “Prediction of gold price with ARIMA and SVM,” J. Phys. Conf. Ser., vol. 1767, no. 1, 2021, doi: 10.1088/1742-6596/1767/1/012022.
[2] J. Chai, C. Zhao, Y. Hu, and Z. G. Zhang, “Structural analysis and forecast of gold price returns,” J. Manag. Sci. Eng., vol. 6, no. 2, pp. 135–145, 2021, doi: 10.1016/j.jmse.2021.02.011.
[3] N. Tripurana, B. Kar, S. Chakravarty, B. K. Paikaray, and S. Satpathy, “Gold Price Prediction Using Machine Learning Techniques,” CEUR Workshop Proc., vol. 3283, pp. 274–281, 2021, doi: 10.54097/gdm0kc53.
[4] S. Setyowibowo, M. As’ad, S. Sujito, and E. Farida, “Forecasting of Daily Gold Price using ARIMA-GARCH Hybrid Model,” J. Ekon. Pembang., vol. 19, no. 2, pp. 257–270, 2022, doi: 10.29259/jep.v19i2.13903.
[5] Y. F. Wijaya and A. Triayudi, “Penerapan Data Mining Pada Prediksi Harga Emas dengan Menggunakan Algoritma Regresi Linear Berganda dan ARIMA,” J. Comput. Syst. Informatics, vol. 5, no. 1, pp. 73–81, 2023, doi: 10.47065/josyc.v5i1.4615.
[6] R. A. Dalimuthe, R. T. Adek, and C. Agusniar, “Prediksi Harga Emas Menggunakan Algoritma Long Short-Term Memory (Lstm),” SENASTIKA Univ. Malikussaleh PREDIKSI, pp. 1–10, 2024.
[7] F. Fauzi, S. Aulia, A. R. Syaifullah, and T. W. Utami, “Peramalan Harga Emas Menggunakan Pendekatan Long-Short Term Memory (LSTM),” J. Edukasi dan Penelit. Inform., vol. 10, no. 2, p. 252, 2024, doi: 10.26418/jp.v10i2.78332.
[8] B. Taylor, S. J.Letham, “Forecasting at Scale,” Am. Stat., vol. 72, no. 1, pp. 37–45, 2018, doi: 10.1080/00031305.2017.1380080.
[9] A. Primawati, I. S. Sitanggang, A. Annisa, and D. A. Astuti, “Perbandingan Kinerja LSTM dan Prophet untuk Prediksi Deret Waktu (Studi Kasus Produksi Susu Sapi Harian),” J. Edukasi dan Penelit. Inform., vol. 9, no. 3, p. 428, 2023, doi: 10.26418/jp.v9i3.72031.
[10] D. Rizkya, H. Roosaputri, and C. Dewi, “Perbandingan Algoritma ARIMA , Prophet , dan LSTM dalam Prediksi Penjualan Tiket Wisata Taman Hiburan ( Studi Kasus : Saloka Theme Park ),” vol. 4, no. 3, pp. 507–517, 2023.
[11] M. Costola, O. Hinz, M. Nofer, and L. Pelizzon, “Machine learning sentiment analysis, COVID-19 news and stock market reactions,” Res. Int. Bus. Financ., vol. 64, p. 101881, 2023, doi: 10.1016/j.ribaf.2023.101881.
[12] Christophorus Bintang Saputra and D. P. Koesrindartoto, “Pemanfaatan Analisis Sentimen Youtube untuk Prediksi Harga Saham: Studi pada Investor Retail Indonesia,” J. Manaj., vol. 21, no. 1, pp. 1–17, 2024, doi: 10.25170/jm.v21i1.5184.
[13] S. Darvishan, S. Heidari, and M. Zarei, “Investigating the Impact of Investor Sentiment and Volatility on Investment Behavior in the Gold Market,” J. Accounting, Financ. Econ. Sci., vol. 4, no. 4, pp. 136–143, 2024, doi: 10.61186/jafes.4.4.136.
[14] G. Jun-gang, “EasyChair Preprint Time-Series Prediction Research Based on Combined Prophet-LSTM Models,” 2023, [Online]. Available: https://easychair.org/publications/preprint/42PsG%0A
[15] A. Amini and R. Kalantari, “Gold price prediction by a CNN-Bi-LSTM model along with automatic parameter tuning,” PLoS One, vol. 19, no. 3 March, pp. 1–17, 2024, doi: 10.1371/journal.pone.0298426.
[16] A. D. Arisandi, L. Atika, Ferdiansyah, E. S. Negara, and K. R. N. Wardani, “Prediksi Mata Uang Bitcoin Menggunakan LSTM dan Analisis Sentimen pada Sosial Media Pendahuluan Metode Penelitian,” J. Ilm. KOMPUTASI, vol. 19, no. 4, pp. 1–9, 2020.
[17] F. Nekouei, “Gold Price Prediction LSTM 96% Accuracy.” Kaggle, 2022. [Online]. Available: https://www.kaggle.com/code/farzadnekouei/gold-price-prediction-lstm-96-accuracy/notebook#Step-12:-Visualizing-Results
[18] A. Sinha, “Sentiment Analysis of Commodity News (Gold),” 2022. [Online]. Available: https://www.kaggle.com/datasets/ankurzing/sentiment-analysis-in-commodity-market-gold/data
[19] M. Owen, V. Vincent, R. Br Ambarita, and E. Indra, “Implementasi Metode Long Short Term Memory Untuk Memprediksi Pergerakan Nilai Harga Emas,” J. Tek. Inf. dan Komput., vol. 5, no. 1, p. 96, 2022, doi: 10.37600/tekinkom.v5i1.507.
[20] M. Beck et al., “xLSTM: Extended Long Short-Term Memory,” Adv. Neural Inf. Process. Syst., vol. 37, no. NeurIPS, pp. 1–57, 2024.
[21] A. Fernando Pratama et al., “Implementasi Analisis Sentimen dan Model Deep Learning untuk Prediksi Harga Bitcoin,” J. Jupiter, vol. 15 No. 1, pp. 403–412, 2023.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
(1)Â Copyright of the published articles will be transferred to the journal as the publisher of the manuscripts. Therefore, the author confirms that the copyright has been managed by the journal.
(2) Publisher of JTMI: Jurnal Teknologi dan Manajemen Informatika is University of Merdeka Malang.
(3) The copyright follows Creative Commons Attribution–ShareAlike License (CC BY SA): This license allows to Share — copy and redistribute the material in any medium or format, Adapt — remix, transform, and build upon the material, for any purpose, even commercially.
