Crypto-Currency Price Prediction Using CNN and LSTM Models
Crypto-Currency Price Prediction Using CNN and LSTM Models
Crypto-Currency Price Prediction Using CNN and LSTM Models
https://doi.org/10.22214/ijraset.2021.33191
International Journal for Research in Applied Science & Engineering Technology (IJRASET)
ISSN: 2321-9653; IC Value: 45.98; SJ Impact Factor: 7.429
Volume 9 Issue III Mar 2021- Available at www.ijraset.com
Abstract: Growing demand in internet usage has bring up to the revolution in digital economy. From the past decade digital economy
is playing major role round the world. The physical assets are converted to digital assets, in which Bitcoin is the major crypto
currency for the investors. Bitcoin has the biggest market capital among all other crypto currencies. Bitocoin price prediction and
forecast has been one of the tedious tasks for long period. Existing works are attempted to go for accurate prediction and forecast
through machine learning models. The forecast can be useful work for the investors to know about the nature of price in future and
gives them directions for their investments. In this proposed work, Bitcoin price prediction is proposed through the deep learning
models such as Convolutional Neural Networks (CNN) and Long short term memory (LSTM) models. The aim of the work is to give
accurate predictions and forecast and bring the daily trend for crypto currency market. Experimental results shows that the proposed
system given better accuracy on predictions.
Keywords: Machine learning, Deep learning, Convolutional Neural Networks (CNN), Long short term memory (LSTM), Bitcoin,
Crypto-currency.
I. INTRODUCTION
Bitcoin is the popular crypto currency and has the highest market capital among all other crypto currencies. Thus investors are keen to
invest in Bitcoin rather than any other currencies, has attracted for further study on this Bitcoin price predictions. The growing demand in
digital economy and the valuations and profit earning ratio of bitcoin is extremely high and the reason its gaining more investor around
the world and this is not fixed for any specific country. Traders or investors all over the world can trade and invest in crypto currencies.
Bitcoin is simple to trade and there is no much regulations for trading or investing, which attracts many investors all over the world. The
digital currency is more secure through the blockchain implementation and decentralized. As it is traded around the world, the price
fluctuations are very high and more volatile than compared to stock investing, this is the main reason, that many investors seeks for the
better model for price understanding and price projections.
There are many automated model are available for stock price predictions based on mathematical and technical analysis. The same kind
of analysis can be applied for cryto currency too. However, the high volatility is one which open doors for the more analysis on deep
learning algorithms. The reason for the price fluctuations and high volatility is still not known. It is difficult to predict such uncertainty
markets through existing technical analysis. Thus more powerful methods needed for the study.
Bitcoin uses the smart transactions using blockchain technologies, which provides more secure transactions with private keys for every
transactions. The transactions once made cannot be edited by anyone as the chain is updated to every holders and decentralized way.
The above figure shows the machine learning architecture for handling bitcoin price prediction. Here the input data plays vital for every
machine learning processes. The data collected in real time will enhance the power of learning and upto date data will add much
advantages.
The trained model is tested agians part of dataset and can be evaluated for self analysis and to improve the learning system.
The objective of proposed system is to find more effective model for price prediction and price forecast thorough deep learning models.
The main objective is to arrive the price prediction with high accurate values, which can aid the investors on making their decision on
investments. Similarly small time frame price projects may helpful for trader trading the crypto currency market.
The remainder of this paper is organized in such a way that chapter 2 discussed about the literature survey and related works carried out
for Bitcoin predictions. Chapter 3 discuss about methodology and modules involved in the project. Chapter 4 is the column for results
and analysis. chapter 5 is discussing about concluded with future works.
The below figure shows the overall architecture of the proposed system.
Bitcoin Price forecast using CNN model is shown in the below figure. The number of days for price projection can be increased, however
to show the optimal results, five days are projected here.
Bitcoin Price forecast using LSTM model is shown in the below figure. The number of days for price projection can be increased,
however to show the optimal results, five days are projected here.
REFERENCES
[1] P. V. Rane and S. N. Dhage, "Systematic Erudition of Bitcoin Price Prediction using Machine Learning Techniques," 2019 5th International Conference on Advanced
Computing & Communication Systems (ICACCS), Coimbatore, India, 2019, pp. 594-598, doi: 10.1109/ICACCS.2019.8728424.
[2] F. 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," 2019 International Conference on Electrical Engineering and Computer Science (ICECOS), Batam Island, Indonesia, 2019, pp. 206-210, doi:
10.1109/ICECOS47637.2019.8984499.
[3] D. Singh, L. Kumar and S. Jain, "User Reputation Analysis for effective Trading on Bitcoin Network," 2019 Twelfth International Conference on Contemporary
Computing (IC3), Noida, India, 2019, pp. 1-5, doi: 10.1109/IC3.2019.8844874.
[4] G. Serafini et al., "Sentiment-Driven Price Prediction of the Bitcoin based on Statistical and Deep Learning Approaches," 2020 International Joint Conference on
Neural Networks (IJCNN), Glasgow, United Kingdom, 2020, pp. 1-8, doi: 10.1109/IJCNN48605.2020.9206704.
[5] W. Yao, K. Xu and Q. Li, "Exploring the Influence of News Articles on Bitcoin Price with Machine Learning," 2019 IEEE Symposium on Computers and
Communications (ISCC), Barcelona, Spain, 2019, pp. 1-6, doi: 10.1109/ISCC47284.2019.8969596.
[6] A. M. Balfagih and V. Keselj, "Evaluating Sentiment C1assifiers for Bitcoin Tweets in Price Prediction Task," 2019 IEEE International Conference on Big Data (Big
Data), Los Angeles, CA, USA, 2019, pp. 5499-5506, doi: 10.1109/BigData47090.2019.9006140.
[7] I. M. Wirawan, T. Widiyaningtyas and M. M. Hasan, "Short Term Prediction on Bitcoin Price Using ARIMA Method," 2019 International Seminar on Application
for Technology of Information and Communication (iSemantic), Semarang, Indonesia, 2019, pp. 260-265, doi: 10.1109/ISEMANTIC.2019.8884257.
[8] T. I. Adegboruwa, S. A. Adeshina and M. M. Boukar, "Time Series Analysis and prediction of bitcoin using Long Short Term Memory Neural Network," 2019 15th
International Conference on Electronics, Computer and Computation (ICECCO), Abuja, Nigeria, 2019, pp. 1-5, doi: 10.1109/ICECCO48375.2019.9043229.