Analisis Studi Literatur: Perbandingan Model Prediksi Harga Bitcoin Berbasis Long Short-Term Memory (LSTM)
Keywords:
Bitcoin, LSTM, Dinamika Pasar Kripto, Model, indikator teknikalAbstract
Perkembangan aset kripto, yang dipelopori oleh Bitcoin (BTC), menghadirkan tantangan prediksi yang signifikan akibat volatilitas ekstrem serta sifat data yang non-linear dan penuh noise. Model statistik konvensional seperti ARIMA seringkali gagal menangkap dinamika pasar yang kompleks ini, sehingga penelitian beralih ke deep learning, khususnya Long Short-Term Memory (LSTM). LSTM terbukti unggul karena kemampuannya mengatasi vanishing gradient dan mengingat pola jangka panjang pada data deret waktu keuangan. Seiring waktu, fokus penelitian telah berevolusi dari LSTM murni ke arsitektur hibrid yang lebih kompleks. Namun, masih terdapat kekurangan sintesis komparatif mengenai metodologi peramalan yang paling efektif.
Penelitian ini melakukan Systematic Narrative Review terhadap 30 studi literatur yang relevan untuk memetakan lanskap penelitian dan mengidentifikasi praktik terbaik. Tinjauan ini berfokus pada tiga pertanyaan penelitian utama: perbandingan performa antara LSTM murni dengan model hibrid, pengaruh integrasi fitur eksternal (teknikal, sentimen, on-chain) terhadap akurasi, serta praktik validasi dan tantangan metodologis yang dominan.
Hasil analisis data menunjukkan bahwa model hibrid, seperti CNN-LSTM, BiLSTM-Attention, dan Autoencoder-LSTM, secara konsisten memberikan hasil yang lebih unggul dibandingkan LSTM murni. Temuan kunci kedua adalah bahwa rekayasa fitur multivariat, khususnya penambahan data sentimen dan metrik on-chain, terbukti sama pentingnya, atau bahkan lebih penting, daripada arsitektur model dalam meningkatkan akurasi prediksi. Secara metodologis, studi ini mengidentifikasi pentingnya penggunaan validasi time-aware seperti Walk-Forward Validation untuk mencegah lookahead bias dan menghindari pelaporan hasil yang terlalu optimis.
Meskipun model hibrid menunjukkan potensi besar, penelitian ini juga mengidentifikasi tantangan signifikan yang masih ada. Tantangan utama meliputi masalah interpretabilitas atau sifat black-box dari model deep learning, serta kurangnya robustness model terhadap guncangan pasar mendadak atau perubahan rezim.
References
I. F. Riziq and A. R. Dzikrillah, “Implementasi Algoritma LSTM Dan SVR Untuk Prediksi Harga Bitcoin Menggunakan Data Yahoo Finance,” Metik J., vol. 9, no. 2, p. 2025, 2025, doi: 10.47002/metik.v9i2.1077.
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.
Y. Li and W. Dai, “Bitcoin price forecasting method based on CNN‐LSTM hybrid neural network model,” J. Eng., vol. 2020, no. 13, pp. 344–347, 2020, doi: 10.1049/joe.2019.1203.
M. Gautam, “Crypto Price Prediction Using Lstm+Xgboost,” 2025, [Online]. Available: http://arxiv.org/abs/2506.22055
A. Mohammadjafari, “Comparative Study of Bitcoin Price Prediction,” 2024, [Online]. Available: http://arxiv.org/abs/2405.08089
S. M. Raju and A. M. Tarif, “Real-Time Prediction of BITCOIN Price using Machine Learning Techniques and Public Sentiment Analysis,” 2020, [Online]. Available: http://arxiv.org/abs/2006.14473
W. Badar, S. Ramzan, A. Raza, N. L. Fitriyani, M. Syafrudin, and S. W. Lee, “Enhanced Interpretable Forecasting of Cryptocurrency Prices Using Autoencoder Features and a Hybrid CNN-LSTM Model,” Mathematics, vol. 13, no. 12, pp. 1–22, 2025, doi: 10.3390/math13121908.
R. S. Dwi Harjo, R. Anugrah, and J. Dharmawan, “Prediksi Coin Kripto Dengan Menggunakan Metode LSTM (Long Short-Term Memory),” J. Adv. Res. Informatics, vol. 3, no. 2, pp. 112–119, 2025, doi: 10.24929/jars.v3i2.4240.
M. O. Lee, D. Sitanggang, E. Indra, F. Sains, and D. Teknologi, “Prediksi Mata Uang Kripto Menggunakan Metode Algoritma Linear Regression,” J. TEKINKOM, vol. 6, no. 1, pp. 88–96, 2023, doi: 10.37600/tekinkom.v6i1.757.
P. S. T. P. Purnama, “Optimizing Bitcoin Price Prediction with LSTM: A Comprehensive Study on Feature Engineering and the April 2024 Halving Impact,” Elinvo (Electronics, Informatics, Vocat. Educ., vol. 9, no. 1, pp. 165–177, 2024, doi: 10.21831/elinvo.v9i1.72518.
E. Dewi, S. Mulyani, C. R. Hidayat, T. Mufizar, and S. S. Sundari, “Sentiment Analysis of Cooking Oil Prices in Indonesia Using the Long Short-Term Memory Method,” vol. 10, no. 1, pp. 78–87, 2025.
R. Bandlamuri, S. A. Jampala, J. Madadapu, and S. D. Meena, “Bitcoin price prediction using machine learning,” AIP Conf. Proc., vol. 2869, no. 1, 2023, doi: 10.1063/5.0168204.
R. Arifudin, S. Subhan, and Y. N. Ifriza, “Student Adaptability Level Optimization using GridsearchCV with Gaussian Naive Bayes and K-Nearest Neighbor Methods as an Effort to Improve Online Education Predictions,” J. Nas. Pendidik. Tek. Inform., vol. 14, no. 2, pp. 287–295, 2025, doi: 10.23887/janapati.v14i2.88972.
H. A. Parhusip, L. Lea, S. Trihandaru, D. B. Nugroho, P. P. Santosa, and A. H. Hariadi, “Learning Algorithms of SVR, DTR, RFR, and XGBoost (Case Study: Predictive Maintenance of Fuel Consumption),” J. Nas. Pendidik. Tek. Inform., vol. 14, no. 2, pp. 250–261, 2025, doi: 10.23887/janapati.v14i2.85657.
O. Bhattarai, R. Chaudhary, and G. Gupta, “Time-Series Real-Time Bitcoin price prediction using LSTM,” Int. J. Comput. Appl., vol. ICAIDSC202, no. 2, pp. 1–6, 2025, doi: 10.5120/icaidsc202411.
Z. I. Ramadhan and H. Widiputra, “Comparative Analysis of Recurrent Neural Network Models Performance in Predicting Bitcoin Prices,” J. RESTI, vol. 8, no. 3, pp. 377–388, 2024, doi: 10.29207/resti.v8i3.5810.
J. Chen, “Analysis of Bitcoin Price Prediction Using Machine Learning,” J. Risk Financ. Manag., vol. 16, no. 1, 2023, doi: 10.3390/jrfm16010051.
A. Azi, “Journal of Computer Networks , Architecture and High Performance Computing Rainfall Prediction in Jayapura City Area Using Long Short-Term Memory Journal of Computer Networks , Architecture and High Performance Computing,” vol. 7, no. 2, pp. 433–439, 2025.
M. Ahmed, S. A. Suha, F. H. Mahi, and F. U. Ahmed, “Evaluating the Performance of Bitcoin Price Forecasting Using Machine Learning Techniques on Historical Data,” Inform. Autom. Pomiary w Gospod. i Ochr. Sr., vol. 14, no. 2, pp. 101–108, 2024, doi: 10.35784/iapgos.5657.
Ferdiansyah, S. H. Othman, R. Zahilah Raja Md Radzi, D. Stiawan, Y. Sazaki, and U. Ependi, “A LSTM-Method for Bitcoin Price Prediction: A Case Study Yahoo Finance Stock Market,” ICECOS 2019 - 3rd Int. Conf. Electr. Eng. Comput. Sci. Proceeding, no. June, pp. 206–210, 2019, doi: 10.1109/ICECOS47637.2019.8984499.
J. Wu, X. Zhang, F. Huang, H. Zhou, and R. Chandra, “Review of deep learning models for crypto price prediction: implementation and evaluation,” 2024, [Online]. Available: http://arxiv.org/abs/2405.11431
M. F. Ramadhan, D. Lestari, and U. Khaira, “Prediksi Harga Bitcoin Menggunakan Metode Long Short Term Memory,” J. Pepadun, vol. 5, no. 2, pp. 104–112, 2024, doi: 10.23960/pepadun.v5i2.193.
F. Febriansyah, A. Sujjada, and F. Sembiring, “Prediksi Harga Bitcoin Menggunakan Algoritma Long Short Term Memory (LSTM),” INOVTEK Polbeng - Seri Inform., vol. 9, no. 1, pp. 55–65, 2024, doi: 10.35314/isi.v9i1.4247.
R. Dubey and D. Enke, “Bitcoin price direction prediction using on-chain data and feature selection,” Mach. Learn. with Appl., vol. 20, no. May, p. 100674, 2025, doi: 10.1016/j.mlwa.2025.100674.
U. B. Trivedi, T. V. S. Somvanshi, and S. P. J, “Gold prices prediction: Comparative study of multiple forecasting models,” YMER Digit., vol. 21, no. 07, pp. 745–764, 2022, doi: 10.37896/ymer21.07/60.
H. Nanda, G. Khetan, and V. Ratnam Kancherla, “Predicting Cryptocurrency Prices with Machine Learning Algorithms: A Comparative Analysis,” no. June, 2023, [Online]. Available: https://urn.kb.se/resolve?urn=urn:nbn:se:bth-25077
M. F. Rizkilloh and S. Widyanesti, “Cryptocurrency Price Prediction Using Long Short Term Memory (LSTM) Algorith,” J. RESTI (Rekayasa Sist. dan Teknol. Informasi), vol. 6, no. 1, pp. 25–31, 2022.
M. C. L. Kumari, “Bitcoin Price Prediction Using LSTM,” Int. J. Res. Appl. Sci. Eng. Technol., vol. 11, no. 6, pp. 2339–2342, 2023, doi: 10.22214/ijraset.2023.54038.
Y. S. David Wibowo and R. Somya, “Penerapan Data Mining Untuk Memprediksi Harga Cryptocurrency Ethereum Menggunakan Metode Backpropagation Neural Network,” J. Tek. Inform. dan Sist. Inf., vol. 10, no. 1, p. 273, 2023, [Online]. Available: http://jurnal.mdp.ac.id
A. A. Corrs, A. Syam, and V. Aris, “Analisis Sentimen Tren Cryptocurrency Menggunakan Machine Learning,” RIGGS J. Artif. Intell. Digit. Bus., vol. 3, no. 4, pp. 59–66, 2025, doi: 10.31004/riggs.v3i4.486.
