Penerapan Metode Extreme Learning Machine untuk Peramalan Harga Cryptocurrency
Abstract
Cryptocurrency is in great demand as an investment medium to gain financial benefits. A common problem that is often faced is how to predict the movement of the value of electronic money in the future. Investors/traders usually only see price movements and buy/sell Cryptocurrency assets intuitively, so mistakes often occur in making transactions. To anticipate and minimize this, you can use an algorithm that can help predict Cryptocurrency price movements. Extreme Learning Machine (ELM) is a development method of a simple feedforward neural network using one hidden layer or commonly known as Single Hidden Layer Feedforward Neural NetworksTesting is done by doing several trials for each percentage value, namely 60%, 65%, 70%, 75%, 80%. Tests were carried out using the binary sigmoid activation function, the number of hidden neurons was 20 and the weight range was [-1,1]. The best prediction results using MAPE are generated on Bitcoin data with the smallest error value of 2.8590%
Keywords: Cryptocurrency; Investation; Extreme Learning Machine; Prediction
Abstrak
Cryptocurrency banyak diminati untuk menjadi media investasi dalam meraih keuntungan finansial. Masalah umum yang sering dihadapi adalah bagaimana meramalkan pergerakan nilai dari uang elektronik pada masa mendatan. Investor/trader biasanya hanya melihat pergerakan harga dan melakukan jual/beli aset Cryptocurrency secara intuitif, sehingga sering terjadi salah dalam melakukan transaksi. Untuk mengantisipasi dan meminimalisir hal tersebut maka dapat menggunakan sebuah algoritme yang dapat membantu dalam meramalkan pergerakan harga Cryptocurrency. Extreme Learning Machine (ELM) merupakan metode pengembangan dari jaringan syaraf tiruan feedforward sederhana dengan menggunakan satu hidden layer atau biasa dikenal dengan Single Hidden Layer Feedforward Neural Networks. Pengujian dilakukan dengan melakukan beberapa kali percobaan untuk setiap nilai persentase yaitu 60%, 65%, 70%, 75%, 80%. Pengujian dilakukan menggunakan fungsi aktivasi sigmoid biner, jumlah hidden neuron 20 serta rentang bobot [-1,1]. Hasil prediksi terbaik menggunakan MAPE dihasilkan pada data Bitcoin dengan nilai kesalahan terkecil yaitu 2.8590%
Kata Kunci: Cryptocurrency; Investasi; Extreme Learning Machine; Prediksi
References
N. Huda and R. Hambali, “Risiko dan Tingkat Keuntungan Investasi Cryptocurrency,” J. Manaj. dan Bisnis Performa, vol. 17, no. 1, pp. 72–84, 2020.
D. K. C. Lee, L. Guo, and Y. Wang, “Cryptocurrency: A new investment opportunity?,” J. Altern. Investments, vol. 20, no. 3, pp. 16–40, 2018, doi: 10.3905/jai.2018.20.3.016.
M. W. P. Aldi, Jondri, and A. Aditsania, “Analisis dan Implementasi Long Short Term Memory Neural Network untuk Prediksi Harga Bitcoin,” in e-Proceeding of Engineering, vol. V, no. 2, p. 3548, 20218.
R. Faizal, B. D. Setiawan, and I. Cholissodin, “Prediksi Nilai Cryptocurrency Bitcoin menggunakan Algoritme Extreme Learning Machine (ELM),” J. Pengemb. Teknol. Inf. dan Ilmu Komput., vol. III, no. 5, pp. 4226–4233, 2019.
“Crypto Research Reports | Gemini | Gemini.” https://www.gemini.com/state-of-crypto (accessed Jan. 13, 2023).
I. G. M. H. Pratama, I. W. Sumarjaya, and N. L. P. Suciptawati, “Peramalan Harga Bitcoin Dengan Metode Smooth Transition Autoregressive (Star),” E-Jurnal Mat., vol. XI, no. 2, p. 100, 2022.
P. H. Padhila, I. Cholissodin, and P. P. Adikara, “Prediksi Harga Bitcoin berdasarkan Data Historis Harian dan Google Trend Index menggunakan Algoritme Extreme Learning Machine,” J. Pengemb. Teknol. Inf. dan Ilmu Komput., vol. XI, no. 7, pp. 3515–3524, 2022.
S. Y. Xu, “Stock price forecasting using information from Yahoo finance and Google Trend,” pp. 1–22, 2014, [Online]. Available: https://www.econ.berkeley.edu/sites/ default/files/Selene Yue Xu.pdf
A. Jain, S. Tripathi, H. Dhardwivedi, and P. Saxena, “Forecasting Price of Cryptocurrencies Using Tweets Sentiment Analysis,” Proc. 2018 11th Int. Conf. Contemp. Comput., vol. I, no. 2, pp. 29–34, 2018.
J. Abraham et al., “Cryptocurrency Price Prediction Using Tweet Volumes and Sentiment Analysis Cryptocurrency Price Prediction Using Tweet Volumes and Sentiment Analysis,” SMU Data Sci. Rev., vol. I, no. 3, pp. 1–21, 2018.
R. Parlika, S. I. Pradika, A. M. Hakim, and K. R. N M, “Analisis Sentimen Twitter Terhadap Bitcoin Dan Cryptocurrency Berbasis Python Textblob,” J. Ilm. Teknol. Inf. dan Robot., vol. II, no. 2, pp. 33–37, 2020.
G. Bin Huang, Q. Y. Zhu, and C. K. Siew, “Extreme learning machine: A new learning scheme of feedforward neural networks,” IEEE Int. Conf. Neural Networks - Conf. Proc., vol. II, no. 1, pp. 985–990, 2014.
G. Ariwanda, I. Cholissodin, and Tibyani, “Prediksi Harga Cabai Rawit di Kota Malang Menggunakan Algoritme Extreme Learning Machine ( ELM ),” J. Pengemb. Teknol. Inf. dan Ilmu Komput., vol. III, no. 6, pp. 5291–5298, 2019.
H. Fu, Y. Wang, and Z. Hongmei, “Ship rolling motion prediction based on extreme learning machine,” Proc. 34th Chinese Control Conf., vol. XXXIV, no. 28, pp. 3468–3472, 2015.
Y. L. D. Pradipta, D. Arisandi, and T. Sutrisno, “Analisis Fluktuasi Harga Saham Blue Chips Dengan Menggunakan Algoritma C4.5,” J. Ilmu Komput. dan Sist. Inf., vol. X, no. 1, pp. 1–6, 2022.
S. C. Nayak, B. Satyanarayana, B. P. Kar, and J. Karthik, “An Extreme Learning Machine-Based Model for Cryptocurrencies Prediction,” Smart Innov. Syst. Technol., vol. CCXXV, no. 1, pp. 127–136, 2021, doi: 10.1007/978-981-16-0878-0_13/COVER.
Irwan, “10 Mata Uang Kripto Terbesar di Dunia Pada September 2022.” https://voi.id/teknologi/208114/10-mata-uang-kripto-terbesar-di-dunia-pada-september-2022 (accessed Jan. 01, 2023).
M. Z. Alfikri, “Analisis Sentimen Twitter terhadap Kartu Prakerja di tengah Pandemi COVID-19 menggunakan Algoritma Pencocokan String dan library TextBlob,” pp. 1–5, 2020, [Online]. Available: https://informatika.stei.itb.ac.id/~rinaldi.munir/Stmik/2019-2020/Makalah/Makalah-Stima-2020-031.pdf
R. Fatwa, I. Cholissodin, and Y. A. Sari, “Penerapan Metode Extreme Learning Machine Untuk Prediksi Konsumsi Penerapan Metode Extreme Learning Machine Untuk Prediksi Konsumsi Batubara Sektor Pembangkit Listrik Tenaga Uap,” J. Pengemb. Teknol. Inf. dan Ilmu Komput., vol. III, no. 11, pp. 10749–10755, 2019.
How To Cite This :
Refbacks
- There are currently no refbacks.
