Optimization of Long Short Term Memory Model for Gold Price Prediction Using Adaptive Moment Estimation

septia amryliana; Syamsul Bahri; Muhammad Rijal Alfian

doi:10.20956/j.v21i3.42872

Authors

septia amryliana Universitas Mataram
Syamsul Bahri Universitas Mataram
Muhammad Rijal Alfian Universitas Mataram

DOI:

https://doi.org/10.20956/j.v21i3.42872

Keywords:

Gold Price Prediction, Artificial Intelligence, Long Short Term Memory, Adaptive Moment Estimation

Abstract

The era of globalization and rapidly evolving economic dynamics place the financial sector at the center of attention for market participants and investors. Financial instruments such as gold play a crucial role as hedging tools and portfolio diversification, yet face significant challenges due to complex and unpredictable price fluctuations. Artificial intelligence technology, particularly Long Short Term Memory (LSTM) models and Adaptive Moment Estimation (ADAM), offers relevant solutions for predicting financial asset prices with strong temporal fluctuations, such as gold prices. This research aims to optimize the LSTM model using the ADAM technique to enhance the accuracy of gold price predictions. The research findings indicate that the LSTM model optimized with ADAM can provide highly accurate gold price predictions with low error rates. The LSTM model used has 3 layers with 128, 64, and 32 units, and uses 100 epochs in the model training process. At the 100th epoch, the final loss obtained was 0,000336. Model evaluation results showed a MAPE of around 0,0108 or 1,08% an accuracy rate of about 98,92%, and a low loss value of 0,00025.

References

[1] Bansal, M., Goyal, A., & Choudhary, A., 2022. A comparative analysis of K-nearest neighbor, genetic, support vector machine, decision tree, and long short term memory algorithms in machine learning. Decision Analytics Journal, 3, 100071.

[2] Cahyani, I., Suhery, C., & Bahri, S., 2023, Implementasi Metode Elman Recurrent Neural Network (ERNN) untuk Prediksi Harga Saham Perbankan di Indonesia, Coding Jurnal Komputer Dan Aplikasi, 11(2), 180-189.

[3] Goodfellow, I., Bengio, Y., & Courville, A., 2016, Deep Learning, MIT Press.

[4] Huong Le, Kim, J., & Kim, H., 2017, An Effective Intrusion Detection Classifier Using Long Short Term Memory With Gradient Descent Optimization, In 2017 International Conference On Platform Technology And Service (Platcon) (Pp. 1-6), IEEE.

[5] Jamaluddin, J., & Haryanto. T., 2023, Pemanfaatan Model Long Short Term Memory (LSTM) Untuk Prediksi Harga Emas Sebagai Instrumen Investasi Dalam Mempersiapkan Ancaman Resesi Global 2023, Indonesian Journal Of Computer Science, 12(2).

[6] Laghrissi, F., Douzi, S., Douzi, K., & Hssina, B. (2021). Intrusion detection systems using long short-term memory (LSTM). Journal of Big Data, 8(1), 65.

[7] Liu, Y., Li, D., Wan, S., Wang, F., Dou, W., Xu, X., … Qi, L. (2021). A long short‐term memory‐based model for greenhouse climate prediction. International Journal of Intelligent Systems. doi:10.1002/int.22620

[8] Mardikawati, B., Diharjo, N. N., Saifullah, S., Widyatiningtyas, R., Gandariani, T., & Widarman, A., 2023, Pemanfaatan Artificial Intelligence dan Mendeley Untuk Penyusunan Karya Ilmiah: Pelatihan Interaktif Berbasis Teknologi, Community Development Journal: Jurnal Pengabdian Masyarakat, 4(6), 11453-11462.

[9] Masrichah, S., 2023, Ancaman dan Peluang Artificial Intelligence (AI), Jurnal Pendidikan Dan Sosial Humaniora, 3(3), 83-101.

[10] Mutiara, A., Fitriyati, N., & Mahmudi, M., 2024, Analisis Laju Prediksi Inflasi Di Indonesia: Perbandingan Model GARCH/ARCH Dengan Long Short Term Memory, Jurnal Lebesgue: Jurnal Ilmiah Pendidikan Matematika, Matematika Dan Statistika, 5(1), 94-110.

[11] Owen, M., Vincent, V., Ambarita, R. B., & Indra, E., 2022, Implementasi Metode Long Short Term Memory untuk Memprediksi Pergerakan Nilai Harga Emas, Jurnal Tekinkom (Teknik Informasi Dan Komputer, 5(1), 96-104

[12] Pardosi, A. R., & Iriani, I., 2024, Analisis Perencanaan Peramalan dan Safety Stock Sprite 250ML dengan Metode Time Series Di PT. XYZ, Jupiter: Publikasi Ilmu Keteknikan Industri, Teknik Elektro Dan Informatika, 2(2), 10-21.

[13] Pipin, S. J., Purba, R., & Kurniawan, H., 2023, Prediksi Saham Menggunakan Recurrent Neural Network (RNN-LSTM) dengan Optimasi Adaptive Moment Estimation, Journal Of Computer System And Informatics (Josyc), 4(4), 806-815.

[14] Purwantoro, S. A., 2023, Sistem Pertahanan Rakyat Semesta Menyongsong Indonesia Emas 2045, Indonesia Emas Group.

[15] Qiu, J., Wang, B., & Zhou, C., 2020, Forecasting Stock Prices With Long Short Term Memory Neural Network Based On Attention Mechanism, Advanced Design And Intelligent Computing, 15(1).

[16] Rahmawati, A., Akramunnas, B. W., Purbolingga, Y., & Putri, D. M., 2023, Analisis Prediksi Harga Minyak West Texas Intermediate Menggunakan Artificial Neural Network dengan Optimisasi Adaptive Moment, Aptek, 142-148.

[17] Reicita, F. A., 2019, Analisis Perencanaan Produksi Pada PT. Armstrong Industri Indonesia dengan Metode Forecasting dan Agregat Planning, Jurnal Ilmiah Teknik Industri, 7(3).

[18] Rizkilloh, M. F., & Widiyanesti, S., 2022, Prediksi Harga Cryptocurrency Menggunakan Algoritma Long Short Term Memory (LSTM), Jurnal RESTI (Rekayasa Sistem Dan Teknologi Informasi, 6(1), 25-31.

[19] Salsabila, S. E., 2020, Model Prediksi Penjualan Multi-Item Time Series Berbasis Machine Learning Menggunakan Metode Autoregressive Integrated Moving Average dan Long Short Term Memory Pada Produk Perishable (Studi Kasus: Retail Sayur Tosaga).

[20] Saragih, T. H., & Huda, N., 2022, Jaringan Syaraf Tiruan Backpropagation Dengan Adaptive Moment Estimation untuk Klasifikasi Penyakit Covid-19 Di Kalimantan Selatan, Epsilon, 16(2).

[21] Satria, T. G., Pramudya, F. S., Adinugroho, M. F., Anatia, S., & Kusumaningrum, T. D. (2023). Signature Authentication Model using Adaptive Moment Estimation Optimization in Multilayer Backpropagated Artificial Neural Networks. Procedia Computer Science, 227, 840-848.

[22] Wei, W. W. S., 2006, Time Series Analysis: Univariate And Multivariate Methods. Pearson Education, Inc., New York.