Optimizing Bitcoin Price Predictions Using Long Short-Term Memory Algorithm: A Deep Learning Approach


Ali Khumaidi(1*); Panji Kusmanto(2); Nur Hikmah(3);

(1) Universitas Krisnadwipayana
(2) Universitas Krisnadwipayana
(3) Universitas Krisnadwipayana
(*) Corresponding Author

  

Abstract


Currently bitcoin is considered an investment tools, the value of bitcoin itself is unstable so it is difficult to predict which can cause losses for bitcoin traders. Some previous research shows that Long Short-Term Memory (LSTM) which is a deep learning approach as an improvement of RNN has the best performance in predicting stocks and cryptocurrencies compared to Support Vector Machine (SVM), Exponential Moving Average (EMA), and Moving Average (MA), and Seasonal Autoregressive Integrated Moving Average (SARIMA). LSTM has the disadvantage that it is difficult to understand in determining the best parameters and to obtain good results it needs strict hyperparameter adjustment. This study aims to find the best parameters in LSTM by selecting the amount of data, training data composition, batch size, epoch and the amount of prediction time and analyzing prediction performance. In this study, data collection was carried out in real time and was able to provide predictions for the next few days. The test results of the LSTM algorithm have a performance with an average accuracy of 93.69% with the parameters of the amount of bitcoin price data used is 3 years, with a percentage of train data of 85%, using 10 batch sizes, with a number of epochs 125, and the highest average accuracy rate for 7 days of prediction.


Keywords


Bitcoin, Hyperparameter Tuning, LSTM, Prediction, Real Time Data.

  
  

Full Text:

PDF
  

Article Metrics

Abstract view: 234 times
PDF view: 109 times 		     

Digital Object Identifier

doi  https://doi.org/10.33096/ilkom.v16i1.1831.38-45 		  

Cite

How to cite item

References


J.-C. Yen and T. Wang, “Stock price relevance of voluntary disclosures about blockchain technology and cryptocurrencies,” Int. J. Account. Inf. Syst., vol. 40, p. 100499, Mar. 2021, doi: 10.1016/j.accinf.2021.100499.

A. Shoker, “Blockchain technology as a means of sustainable development,” One Earth, vol. 4, no. 6, pp. 795–800, Jun. 2021, doi: 10.1016/j.oneear.2021.05.014.

P. Modesti, S. F. Shahandashti, P. McCorry, and F. Hao, “Formal modelling and security analysis of Bitcoin’s payment protocol,” Comput. Secur., vol. 107, p. 102279, Aug. 2021, doi: 10.1016/j.cose.2021.102279.

I. R. Dewi, “Meledak, Investor Kripto RI Capai 12,4 Juta, Kalahkan Saham,” 2022.

Y. Zhang, W. Zhong, Y. Li, and L. Wen, “A deep learning prediction model of DenseNet-LSTM for concrete gravity dam deformation based on feature selection,” Eng. Struct., vol. 295, p. 116827, Nov. 2023, doi: 10.1016/j.engstruct.2023.116827.

M. J. Islam, R. Datta, and A. Iqbal, “Actual rating calculation of the zoom cloud meetings app using user reviews on google play store with sentiment annotation of BERT and hybridization of RNN and LSTM,” Expert Syst. Appl., vol. 223, p. 119919, Aug. 2023, doi: 10.1016/j.eswa.2023.119919.

T. Gao, Y. Chai, and Y. Liu, “Applying long short term momory neural networks for predicting stock closing price,” in 2017 8th IEEE International Conference on Software Engineering and Service Science (ICSESS), 2017, pp. 575–578, doi: 10.1109/ICSESS.2017.8342981.

J. Cheng, S. Tiwari, D. Khaled, M. Mahendru, and U. Shahzad, “Forecasting Bitcoin prices using artificial intelligence: Combination of ML, SARIMA, and Facebook Prophet models,” Technol. Forecast. Soc. Change, vol. 198, p. 122938, Jan. 2024, doi: 10.1016/j.techfore.2023.122938.

P. A. Riyantoko, T. M. Fahruddin, K. M. Hindrayani, and E. M. Safitri, “Analisis Prediksi Harga Saham Sektor Perbankan Menggunakan Algoritma Long Short Terms Memory (LSTM),” in Seminar Nasional Informatika 2020 (SEMNASIF 2020), 2020, pp. 427–435.

N. Parvini, M. Abdollahi, S. Seifollahi, and D. Ahmadian, “Forecasting Bitcoin returns with long short-term memory networks and wavelet decomposition: A comparison of several market determinants,” Appl. Soft Comput., vol. 121, p. 108707, May 2022, doi: 10.1016/j.asoc.2022.108707.

R. K. Rathore et al., “Real-world model for bitcoin price prediction,” Inf. Process. Manag., vol. 59, no. 4, p. 102968, Jul. 2022, doi: 10.1016/j.ipm.2022.102968.

S. Rajabi, P. Roozkhosh, and N. M. Farimani, “MLP-based Learnable Window Size for Bitcoin price prediction,” Appl. Soft Comput., vol. 129, p. 109584, Nov. 2022, doi: 10.1016/j.asoc.2022.109584.

W. Herwanto, A. Khumaidi, and H. P. Putro, “Feature Extraction and Classification of Tissue Mammograms Based on Grayscale and Gray Level Co-occurrence Matrix,” in 2021 International Seminar on Machine Learning, Optimization, and Data Science (ISMODE), 2022, pp. 131–134, doi: 10.1109/ISMODE53584.2022.9743131.

A. Khumaidi, I. A. Nirmala, and H. Herwanto, “Forecasting of Sales Based on Long Short Term Memory Algorithm with Hyperparameter,” in 2021 International Seminar on Machine Learning, Optimization, and Data Science (ISMODE), 2022, pp. 201–206, doi: 10.1109/ISMODE53584.2022.9743079.

S. L. Bergquist, T. J. Layton, T. G. McGuire, and S. Rose, “Data transformations to improve the performance of health plan payment methods,” J. Health Econ., vol. 66, pp. 195–207, Jul. 2019, doi: 10.1016/j.jhealeco.2019.05.005.

M. Yousefi, E. J. M. Carranza, O. P. Kreuzer, V. Nykänen, J. M. A. Hronsky, and M. J. Mihalasky, “Data analysis methods for prospectivity modelling as applied to mineral exploration targeting: State-of-the-art and outlook,” J. Geochemical Explor., vol. 229, p. 106839, Oct. 2021, doi: 10.1016/j.gexplo.2021.106839.

X. Huang et al., “Time series forecasting for hourly photovoltaic power using conditional generative adversarial network and Bi-LSTM,” Energy, vol. 246, p. 123403, May 2022, doi: 10.1016/j.energy.2022.123403.

A. Khumaidi, R. Raafi’udin, and I. P. Solihin, “Pengujian Algoritma Long Short Term Memory untuk Prediksi Kualitas Udara dan Suhu Kota Bandung,” Telematika, vol. 15, no. 1, pp. 13–18, 2020.

S. Yousuf, S. A. Khan, and S. Khursheed, “Remaining useful life (RUL) regression using Long–Short Term Memory (LSTM) networks,” Microelectron. Reliab., vol. 139, p. 114772, Dec. 2022, doi: 10.1016/j.microrel.2022.114772.

E. Koo and G. Kim, “Prediction of Bitcoin price based on manipulating distribution strategy,” Appl. Soft Comput., vol. 110, p. 107738, Oct. 2021, doi: 10.1016/j.asoc.2021.107738.

P. Ghosh, A. Neufeld, and J. K. Sahoo, “Forecasting directional movements of stock prices for intraday trading using LSTM and random forests,” Financ. Res. Lett., vol. 46, p. 102280, May 2022, doi: 10.1016/j.frl.2021.102280.

Y. He, M. Zhao, T. Xu, S. Li, H. Tian, and W. Li, “Novel cross LSTM for predicting the changes of complementary pelvic angles between standing and sitting,” J. Biomed. Inform., vol. 128, p. 104036, Apr. 2022, doi: 10.1016/j.jbi.2022.104036.

S. Mirzaei, J.-L. Kang, and K.-Y. Chu, “A comparative study on long short-term memory and gated recurrent unit neural networks in fault diagnosis for chemical processes using visualization,” J. Taiwan Inst. Chem. Eng., vol. 130, p. 104028, Jan. 2022, doi: 10.1016/j.jtice.2021.08.016.


Refbacks

  • There are currently no refbacks.


Copyright (c) 2024 Ali Khumaidi, Panji Kusmanto, Nur Hikmah.

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.