DEEP LEARNING BERBASIS ATTENTION NETWORK UNTUK PREDIKSI HARGA BITCOIN

• TETRA WIDIANTO
• 14002461

---

ABSTRAK

 

ABSTRAK
Nama : Tetra Widianto
NIM : 14002461
Program Studi : Ilmu Komputer
Fakultas : Teknologi Informasi
Jenjang : Strata Dua (S2)
Konsentrasi : Data Mining
Judul : Deep Learning Berbasis Attention Network untuk Prediksi
Harga Bitcoin
Dalam investasi jangka pendek atau trading dibutuhkan analisis teknikal untuk
membantu melihat arah pergerakan harga agar tepat mengambil langkah dalam
berinvestasi sehingga tidak mengalami kerugian. Pendekatan yang dapat
digunakan adalah machine learning dengan tahap penggunaan deep learning,
attention network dan variabel baru dari analisis sentimen, tren pencarian atau
indikator trading. Pada penelitian sebelumnya, digunakan arsitektur RNN
sederhana untuk menyelesaikan permasalahan prediksi menggunakan Bi-LSTM.
Penelitian ini mengeksplorasi penggunaan arsitektur RNN sederhana dalam model
berbasis attention dimana metode yang akan digunakan adalah LSTM, Bi-LSTM
dan GRU dengan variabel baru yaitu Crypto Fear & Greed Index (FGI). Hasil
penelitian menunjukkan Bi-LSTM berbasis attention (Bi-LSTM-Att) cocok
digunakan dalam arsitektur RNN sederhana karena menunjukkan peningkatan
performa dibandingkan dengan tanpa attention, sedangkan LSTM-Att dan GRUAtt menunjukkan hasil yang sebaliknya. Penggunaan FGI sebagai variabel baru
mampu meningkatkan performa model, terlihat dari peningkatan performa BiLSTM-Att dengan nilai MAPE antara 4,38% - 5,68% menjadi 4,25% - 5,19%.
Kata kunci: Pediksi, Bitcoin, Crypto Fear & Greed Index, LSTM, GRU, Bi-LSTM,
Attention Network
 

KATA KUNCI

Deep Learning,ATTENTION NETWORK

---

DAFTAR PUSTAKA

 

DAFTAR REFERENSI
[1] D. Güler, “The Impact of Investor Sentiment on Bitcoin Returns and
Conditional Volatilities during the Era of Covid-19,” J. Behav. Financ.,
2021, doi: 10.1080/15427560.2021.1975285.
[2] “Kajian Stabilitas Keuangan Nomor 37, September 2021.”
https://www.bi.go.id/KSK37/default.aspx (accessed Jun. 21, 2022).
[3] “Mata Uang Kripto Semakin Diminati di Indonesia: Simak Pengertian, Cara
Kerja, Jenis, Manfaat, dan Risikonya.”
https://www.inews.id/finance/keuangan/mata-uang-kripto-semakindiminati-di-indonesia-simak-pengertian-cara-kerja-jenis-manfaat-danrisikonya (accessed Jun. 21, 2022).
[4] “Belajar dari Bahaya FOMO yang Timpa Emak-emak di Token ASIX.”
https://finance.detik.com/fintech/d-5940955/belajar-dari-bahaya-fomoyang-timpa-emak-emak-di-token-asix (accessed Jun. 21, 2022).
[5] “Bappebti Website - SK/ Kep. Kepala Bappebti.”
https://bappebti.go.id/pbk/sk_kep_kepala_bappebti/detail/6655 (accessed
Jun. 25, 2022).
[6] “5 Crypto Terbaik Dengan Fundamental Bagus - Coinvestasi.”
https://coinvestasi.com/beli-bitcoin/panduan/pemula/5-crypto-terbaikdengan-fundamental-bagus (accessed Jun. 22, 2022).
[7] “Mereka yang Melirik Bitcoin Demi Cuan.”
https://www.cnbcindonesia.com/tech/20200904201754-37-184529/merekayang-melirik-bitcoin-demi-cuan (accessed Jun. 22, 2022).
[8] J. Z. Huang, W. Huang, and J. Ni, “Predicting bitcoin returns using highdimensional technical indicators,” J. Financ. Data Sci., vol. 5, no. 3, 2019,
doi: 10.1016/j.jfds.2018.10.001.
[9] F. Shahid, A. Zameer, and M. Muneeb, “Predictions for COVID-19 with
deep learning models of LSTM, GRU and Bi-LSTM,” Chaos, Solitons and
Fractals, vol. 140, 2020, doi: 10.1016/j.chaos.2020.110212.
[10] K. E. ArunKumar, D. V. Kalaga, C. Mohan Sai Kumar, M. Kawaji, and T.
M. Brenza, “Comparative analysis of Gated Recurrent Units (GRU), long
Short-Term memory (LSTM) cells, autoregressive Integrated moving
average (ARIMA), seasonal autoregressive Integrated moving average
(SARIMA) for forecasting COVID-19 trends,” Alexandria Eng. J., vol. 61,
no. 10, 2022, doi: 10.1016/j.aej.2022.01.011.
[11] D. Bahdanau, K. H. Cho, and Y. Bengio, “Neural machine translation by
jointly learning to align and translate,” 2015.
[12] L. Fu and F. Zhao, “Prediction of Hot Topics of Agricultural Public Opinion
Based on Attention Mechanism LSTM Model,” Int. J. Agric. Environ. Inf.
Syst., vol. 12, no. 4, pp. 1–16, Oct. 2021, doi: 10.4018/IJAEIS.289429.
[13] J. Du, Y. Cheng, Q. Zhou, J. Zhang, X. Zhang, and G. Li, “Power Load
Forecasting Using BiLSTM-Attention,” in IOP Conference Series: Earth
and Environmental Science, 2020, vol. 440, no. 3. doi: 10.1088/1755-
56
Program Studi Ilmu Komputer (S2) Nusa Mandiri
1315/440/3/032115.
[14] G. Xue, J. Song, X. Kong, Y. Pan, C. Qi, and H. Li, “Prediction of Natural
Gas Consumption for City-Level DHS Based on Attention GRU: A Case
Study for a Northern Chinese City,” IEEE Access, vol. 7, pp. 130685–
130699, 2019, doi: 10.1109/ACCESS.2019.2940210.
[15] “Crypto Fear & Greed Index - Bitcoin Sentiment - Alternative.me.”
https://alternative.me/crypto/fear-and-greed-index/ (accessed Jun. 22, 2022).
[16] S. B. Akbar, K. Thanupillai, and V. Govindarajan, “Forecasting Bitcoin price
using time opinion mining and bi-directional GRU,” J. Intell. Fuzzy Syst.,
vol. 42, no. 3, 2022, doi: 10.3233/JIFS-211217.
[17] A. Mittal, V. Dhiman, A. Singh, and C. Prakash, “Short-Term Bitcoin Price
Fluctuation Prediction Using Social Media and Web Search Data,” 2019.
doi: 10.1109/IC3.2019.8844899.
[18] S. A. Ahamed and C. Ravi, “Novel deep learning model for bitcoin price
prediction by multiplicative LSTM with attention mechanism and technical
indicators,” Int. J. Eng. Syst. Model. Simul., vol. 1, no. 1, 2021, doi:
10.1504/ijesms.2021.10042401.
[19] C. Janiesch, P. Zschech, and K. Heinrich, “Machine learning and deep
learning,” Electron. Mark., vol. 31, no. 3, 2021, doi: 10.1007/s12525-021-
00475-2.
[20] P. Bhavsar, I. Safro, N. Bouaynaya, R. Polikar, and D. Dera, “Machine
Learning in Transportation Data Analytics,” Data Anal. Intell. Transp. Syst.,
pp. 283–307, Jan. 2017, doi: 10.1016/B978-0-12-809715-1.00012-2.
[21] A. L. Samuel, “Some studies in machine learning using the game of
checkers,” IBM J. Res. Dev., vol. 44, no. 1–2, pp. 207–219, 2000, doi:
10.1147/RD.441.0206.
[22] G. Wiederhold and J. McCarthy, “Arthur Samuel: Pioneer in Machine
Learning,” IBM J. Res. Dev., vol. 36, no. 3, pp. 329–331, Apr. 2010, doi:
10.1147/RD.363.0329.
[23] A. Kalali, S. Richerson, E. Ouzunova, R. Westphal, and B. Miller, “Digital
Biomarkers in Clinical Drug Development,” Handb. Behav. Neurosci., vol.
29, pp. 229–238, Jan. 2019, doi: 10.1016/B978-0-12-803161-2.00016-3.
[24] V. C. Broaddus et al., “Murray & Nadel’s textbook of respiratory medicine”.
[25] M. Algren, W. Fisher, and A. E. Landis, “Machine learning in life cycle
assessment,” Data Sci. Appl. to Sustain. Anal., pp. 167–190, Jan. 2021, doi:
10.1016/B978-0-12-817976-5.00009-7.
[26] G. Shobha and S. Rangaswamy, “Machine Learning,” Handb. Stat., vol. 38,
pp. 197–228, Jan. 2018, doi: 10.1016/BS.HOST.2018.07.004.
[27] D. D. Luxton, “An Introduction to Artificial Intelligence in Behavioral and
Mental Health Care,” Artif. Intell. Behav. Ment. Heal. Care, pp. 1–26, Jan.
2016, doi: 10.1016/B978-0-12-420248-1.00001-5.
[28] C. M. Bishop, Pattern Recognition and Machine Learning (Information
Science and Statistics). 2006.
[29] Y. Chen, “Voltages prediction algorithm based on LSTM recurrent neural
network,” Optik (Stuttg)., vol. 220, p. 164869, Oct. 2020, doi:
57
Program Studi Ilmu Komputer (S2) Nusa Mandiri
10.1016/J.IJLEO.2020.164869.
[30] D. Javaheri, P. Lalbakhsh, and M. Hosseinzadeh, “A Novel Method for
Detecting Future Generations of Targeted and Metamorphic Malware Based
on Genetic Algorithm,” IEEE Access, vol. 9, 2021, doi:
10.1109/ACCESS.2021.3077295.
[31] Z. C. Lipton, J. Berkowitz, and C. Elkan, “A Critical Review of Recurrent
Neural Networks for Sequence Learning,” May 2015, doi:
10.48550/arxiv.1506.00019.
[32] I. Goodfellow, Y. Bengio, and A. Courville, Deep learning An MIT Press
Book, vol. 29, no. 7553. 2016.
[33] M. H. Rahman, S. Yuan, C. Xie, and Z. Sha, “Predicting human design
decisions with deep recurrent neural network combining static and dynamic
data,” Des. Sci., 2020, doi: 10.1017/dsj.2020.12.
[34] Y. Bengio, P. Simard, and P. Frasconi, “Learning Long-Term Dependencies
with Gradient Descent is Difficult,” IEEE Trans. Neural Networks, vol. 5,
no. 2, 1994, doi: 10.1109/72.279181.
[35] D. Britz, “Recurrent Neural Networks Tutorial,” Wildml.Com. 2015.
[36] S. Mikhailov and A. Kashevnik, “Car tourist trajectory prediction based on
bidirectional lstm neural network,” Electron., vol. 10, no. 12, 2021, doi:
10.3390/electronics10121390.
[37] S. Siami-Namini, N. Tavakoli, and A. Siami Namin, “A Comparison of
ARIMA and LSTM in Forecasting Time Series,” 2019. doi:
10.1109/ICMLA.2018.00227.
[38] K. Cho et al., “Learning phrase representations using RNN encoder-decoder
for statistical machine translation,” 2014. doi: 10.3115/v1/d14-1179.
[39] S. Nakamoto, “A Peer-to-Peer Electronic Cash System,” Journal for General
Philosophy of Science, vol. 39, no. 1. 2008.
[40] U. Jaitley, “Why Data Normalization is necessary for Machine Learning
models,” Medium Machine Learning, 2018.
[41] S. Lu, Q. Zhang, G. Chen, and D. Seng, “A combined method for short-term
traffic flow prediction based on recurrent neural network,” Alexandria Eng.
J., vol. 60, no. 1, 2021, doi: 10.1016/j.aej.2020.06.008.
[42] 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, 2021, doi: 10.3390/ai2040030.
[43] M. M. Patel, S. Tanwar, R. Gupta, and N. Kumar, “A Deep Learning-based
Cryptocurrency Price Prediction Scheme for Financial Institutions,” J. Inf.
Secur. Appl., vol. 55, 2020, doi: 10.1016/j.jisa.2020.102583.
[44] H. Kilimci, M. Yildirim, and Z. H. Kilimci, “The Prediction of Short-Term
Bitcoin Dollar Rate (BTC/USDT) using Deep and Hybrid Deep Learning
Techniques,” 2021. doi: 10.1109/ISMSIT52890.2021.9604741.
[45] M. Ortu, N. Uras, C. Conversano, S. Bartolucci, and G. Destefanis, “On
technical trading and social media indicators for cryptocurrency price
classification through deep learning,” Expert Syst. Appl., vol. 198, 2022, doi:
10.1016/j.eswa.2022.116804.
58
Program Studi Ilmu Komputer (S2) Nusa Mandiri
[46] S. Tanwar, N. P. Patel, S. N. Patel, J. R. Patel, G. Sharma, and I. E. Davidson,
“Deep Learning-Based Cryptocurrency Price Prediction Scheme with InterDependent Relations,” IEEE Access, vol. 9, pp. 138633–138646, 2021, doi:
10.1109/ACCESS.2021.3117848.
[47] P. Mohanty, D. Patel, P. Patel, and S. Roy, “Predicting Fluctuations in
Cryptocurrencies’ Price using users’ Comments and Real-time Prices,”
2018. doi: 10.1109/ICRITO.2018.8748792.
[48] A. Aggarwal, I. Gupta, N. Garg, and A. Goel, “Deep Learning Approach to
Determine the Impact of Socio Economic Factors on Bitcoin Price
Prediction,” 2019. doi: 10.1109/IC3.2019.8844928.
[49] Y. Li, Z. Zheng, and H. N. Dai, “Enhancing bitcoin price fluctuation
prediction using attentive LSTM and embedding network,” Appl. Sci., vol.
10, no. 14, Jul. 2020, doi: 10.3390/app10144872.
[50] D. R. Pant, P. Neupane, A. Poudel, A. K. Pokhrel, and B. K. Lama,
“Recurrent Neural Network Based Bitcoin Price Prediction by Twitter
Sentiment Analysis,” in Proceedings on 2018 IEEE 3rd International
Conference on Computing, Communication and Security, ICCCS 2018,
2018, pp. 128–132. doi: 10.1109/CCCS.2018.8586824.
[51] “Bitcoin USD (BTC-USD) Price, Value, News & History - Yahoo Finance.”
https://finance.yahoo.com/quote/BTC-USD (accessed Jun. 24, 2022).