Impementasi Algoritma GRU Untuk Trading Strategy pada Cryptocurrency Berbasis Web

I Gede Bayu Balawa Tangub; Neny Sulistianingsih; Tomi Tri Sujaka

doi:10.31004/riggs.v5i2.10129

Authors

I Gede Bayu Balawa Tangub Universitas Bumigora
Neny Sulistianingsih Universitas Bumigora
Tomi Tri Sujaka Universitas Bumigora

DOI:

https://doi.org/10.31004/riggs.v5i2.10129

Keywords:

GRU, Trading Strategy, Cryptocurrency, Berbasis Web

Abstract

Perkembangan investasi cryptocurrency, khususnya Ethereum (ETH), terus meningkat seiring dengan bertambahnya jumlah investor aset digital. Namun, tingginya volatilitas harga cryptocurrency menyebabkan proses pengambilan keputusan trading menjadi lebih kompleks dan berisiko. Oleh karena itu, diperlukan metode prediksi yang mampu menghasilkan informasi harga secara akurat untuk mendukung pengambilan keputusan investasi. Penelitian ini bertujuan untuk membandingkan performa algoritma Gated Recurrent Unit (GRU) dan Bidirectional Gated Recurrent Unit (Bi-GRU) dalam memprediksi harga penutupan Ethereum serta mengimplementasikan model terbaik ke dalam sistem trading strategy berbasis web. Metode penelitian menggunakan pendekatan Cross Industry Standard Process for Data Mining (CRISP-DM) yang meliputi tahapan business understanding, data understanding, data preparation, modeling, evaluation, dan deployment. Dataset yang digunakan berupa data historis harian ETH-USD yang diperoleh dari Yahoo Finance pada periode 9 November 2016 hingga 16 Januari 2026. Proses penelitian mencakup prapemrosesan data, pelatihan model, evaluasi performa menggunakan RMSE, MAE, MSE, R², dan Explained Variance, serta implementasi sistem berbasis web. Hasil penelitian menunjukkan bahwa model GRU memberikan performa yang lebih baik dibandingkan Bi-GRU dengan nilai RMSE sebesar 150,99, MAE sebesar 117,70, MSE sebesar 22.798,51, R² sebesar 0,96, dan Explained Variance sebesar 0,98. Hasil prediksi kemudian diintegrasikan ke dalam strategi trading berbasis aturan yang menghasilkan sinyal buy, sell, dan hold. Sistem berhasil diimplementasikan menggunakan Vercel dan Hugging Face Spaces. Hasil penelitian menunjukkan bahwa algoritma GRU efektif untuk prediksi harga Ethereum dan berpotensi mendukung pengambilan keputusan trading berbasis data secara lebih objektif.

Downloads

Download data is not yet available.

References

[1] J. Akuntansi and B. Rolando, “The Impact of Cryptocurrency on the Traditional Banking System in Indonesia : A Threat or Complement,” vol. 5, no. 1, pp. 1–14, 2025.

[2] U. Kristen, S. Wacana, J. Diponegoro, and K. Sidorejo, “Penerapan Data Mining Untuk Memprediksi Harga Cryptocurrency Ethereum Menggunakan Metode Backpropagation Neural Network 1,2,” vol. 10, no. 1, pp. 3–9, 2023.

[3] M. Alfarizi and D. Lestarini, “Predicting Cryptocurrency Prices Using Machine Learning : A Case Study on Bitcoin,” vol. 9, no. 6, pp. 3612–3621, 2025.

[4] R. S. Andromeda, N. Anisa, and S. Winarsih, “Perbandingan Kinerja Metode LSTM dan GRU dalam Prediksi Harga Close Cryptocurrency Performance Comparison of LSTM and GRU Methods in Predicting Cryptocurrency Closing Prices,” vol. 14, pp. 366–379, 2025.

[5] M. F. Reza, T. Informatika, U. Islam, S. Agung, A. Wahid, and A. S. Winarsih, “Implementasi Model Gated Recurrent Unit ( Gru ) Atau Extreme Gredient Boosting ( Xgboost ) Untuk Prediksi Harga,” vol. 3, no. 1, pp. 209–222, 2025.

[6] K. S. Zamzami, M. Ayu, D. Widyadara, and A. B. Setiawan, “Aplikasi Prediksi Harga Ethereum Menggunakan Metode ARIMA,” pp. 302–307, 2022.

[7] X. Kong, Z. Chen, W. Liu, K. Ning, L. Zhang, and S. Muhammad, Deep learning for time series forecasting : a survey, vol. 16, no. 7. Springer Berlin Heidelberg, 2025. doi: 10.1007/s13042-025-02560-w.

[8] I. D. Mienye, “A Comprehensive Review of Deep Learning : Architectures , Recent Advances , and Applications,” 2024.

[9] Cho et al., “Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation,” 2014.

[10] Y. Duan, Y. Liu, Y. Wang, S. Ren, and Y. Wang, “Improved BIGRU Model and Its Application in Stock Price Forecasting,” pp. 1–19, 2023.

[11] N. Aulia, “Prediksi Harga Ethereum Berdasarkan Informasi Blockchain Menggunakan Metode Long Short Term Memory,” 2020.

[12] A. Shukla, “Journal of Artificial Intelligence & Cloud Computing Modern JavaScript Frameworks and JavaScript ’ s Future as a Full- Stack Programming Language,” vol. 2, no. 4, pp. 1–5.

[13] A. F. Hakim, Y. Irawan, and R. R. Setiawan, “Implementation of the Crisp-Dm Methodology and Naive Bayes Algorithm on A Raw Material Requirement Prediction System to Reduce Food Waste ( Case Study : Adamsafee Bakery , Resto , & Cafe ),” vol. 18, no. 2, pp. 968–983, 2025.

[14] U. D. Nuswantoro, “Pengembangan Web Service Menggunakan Framework Fastapi Untuk Meningkatkan Kemudahan Integrasi Sistem Informasi Akademik Multiplatform,” vol. 12, no. 2, pp. 149–157, 2024.

[15] H. Hewamalage, K. Ackermann, and C. Bergmeir, “Forecast evaluation for data scientists : common pitfalls and best practices,” Data Min. Knowl. Discov., vol. 37, no. 2, pp. 788–832, 2023, doi: 10.1007/s10618-022-00894-5.

[16] DataSolut, “CRISP-DM Standard Process for Data Mining.”

[17] R. R. Laska and A. M. Yolanda, “A Comparative Study of Z-Score and Min-Max Normalization for Rainfall Classification in Pekanbaru,” vol. 2024, no. April, 2024.

[18] M. Ahsan, M. A. P. Mahmud, P. K. Saha, K. D. Gupta, and Z. Siddique, “Effect of Data Scaling Methods on Machine Learning Algorithms and Model Performance,” pp. 5–9, 2021.

[19] C. Alkahfi, A. Kurnia, and A. Saefuddin, “Perbandingan Kinerja Model Berbasis RNN pada Peramalan Data Ekonomi dan Keuangan Indonesia,” MALCOM: Indonesian Journal of Machine Learning and Computer Science, vol. 4, no. 4, pp. 1235–1243, 2024, doi: 10.57152/malcom.v4i4.1415.

[20] R. Jonathan and Suprihadi, “Development of Front-End Web Applications Utilizing Single Page Application Framework and React.js Library,” International Journal Software Engineering and Computer Science (IJSECS), vol. 3, no. 3, pp. 529–536, 2023, doi: 10.35870/ijsecs.v3i3.1943.

[21] Muhammad Romzi and Budi Kurniawan, “Implementasi Pemrograman Python Menggunakan Visual Studio Code,” Jik, vol. XI, no. 2, pp. 1–9, 2020, [Online]. Available: www.python.org

[22] P. L. Seabe and others, “Cryptocurrency Price Prediction Using Deep Learning Models: A Comparative Study of LSTM, GRU, and Bi-LSTM,” SAIEE Research Journal, vol. 114, no. 2, pp. 45–53, 2023.

[23] A. Yunizar, T. Rismawan, D. Marisa Midyanti, J. Rekayasa Sistem Komputer, and F. H. MIPA Universitas Tanjungpura Jalan Hadari Nawawi Pontianak, “Penerapan Metode Recurrent Neural Network Model Gated Recurrent Unit Untuk Prediksi Harga Cryptocurrency,” 2023.

[24] R. Satria A. and N. A. S. W., “Komparasi Algoritma LSTM dan GRU dalam Memprediksi Harga Aset Kripto Bitcoin dan Ethereum,” Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), vol. 9, no. 1, pp. 112–120, 2025.

[25] Y. E. Gür, “Precious Metals Price Forecasting Using Hybrid Deep Learning Models: The Case of Silver (XAG/TRY),” J. Behav. Exp. Finance, vol. 41, p. 100892, 2024.

[26] Y. Gao, R. Wang, and E. Zhou, “Stock Index Forecasting Based on Dimension Reduction and Deep Learning: A LASSO-LSTM and LASSO-GRU Approach,” Knowl. Based. Syst., vol. 223, p. 107056, 2021.

[27] Z. Y. Shehu and others, “Deep Learning for Financial Time Series Forecasting: A Systematic Review of GRU, Bi-GRU, and Transformer Models (2020--2025),” Artif. Intell. Rev., vol. 59, no. 3, p. 142, 2026.

[28] T. O. Kehinde and others, “Evaluating Sequential Deep Learning Models and Transformer Networks for Global Stock Index Prediction,” Expert Syst. Appl., vol. 215, p. 119312, 2023.

[29] S. Ataei and others, “Deep Reinforcement Learning versus Sequence Models in Financial Trading: A Systematic Review of 75 Studies,” IEEE Trans. Neural Netw. Learn. Syst., vol. 36, no. 4, pp. 2145–2158, 2025.

[30] J. Lian, “The Impact of Activation Functions on Deep Learning Performance: Forecasting Zcash Price Volatility,” J. Comput. Sci. Technol., vol. 39, no. 2, pp. 312–325, 2024.

[31] A. D. Gbadebo, “Comparative Analysis of Hybrid Deep Learning and Stochastic Gradient Descent Regression in Multi-Cryptocurrency Price Prediction,” Appl. Soft Comput., vol. 152, p. 111204, 2025.

[32] H. Song and H. Choi, “Forecasting Stock Market Indices Using the Recurrent Neural Network Based Hybrid Models: CNN-LSTM, GRU-CNN, and Ensemble Models,” Applied Sciences, vol. 13, no. 7, 2023, doi: 10.3390/app13074644.