Comparative Analysis of Prediction Models for Cryptocurrency Price Prediction (May 2022)
Harshvardhan Sinha1, Sangle Gaurav Keshavrao2, Pulkit Verma3

1Harshvardhan Sinha*, Department of Computer Science, VIT University, Vellore (Tamil Nadu), India. 
2Sangle Gaurav Keshavrao, Department of Computer Science, VIT University, Vellore (Tamil Nadu), India. 
3Pulkit Verma, Department of Computer Science, VIT University, Vellore (Tamil Nadu), India. 
Manuscript received on 26 May 2022. | Revised Manuscript received on 18 June 2022. | Manuscript published on 30 June 2022. | PP: 19-23 | Volume-8 Issue-10, June 2022. | Retrieval Number: 100.1/ijmh.J14970681022 | DOI: 10.35940/ijmh.J1497.0681022
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: The decentralization of cryptocurrencies has greatly reduced the level of central control over them, impacting international relations and trade. Further, wide fluctuations in cryptocurrency price indicate an urgent need for an accurate way to forecast this price. This project proposes a method to predict fluctuations in the prices of cryptocurrencies, which are increasingly used for online transactions worldwide. This project proposes a novel method to compare the efficiency of five different models predicting the cryptocurrency price by considering various factors such as market cap, volume, circulating supply, and maximum supply based on deep learning techniques such as the Linear Regression, Support vector regression (SVR), Auto Regressive Integrated Moving Average (ARIMA), Long Short-Term Memory (LSTM) and a hybrid model of ARIMA and LSTM which are effective learning models for training data. The hybrid model outperforms the LSTM and ARIMA model after comparing RMSE values. The proposed approach is implemented in Python and validated for benchmark datasets. 
Keywords: Index Terms: Bitcoin, Cryptocurrencies, Predictive Model, Regression, ARIMA, LSTM, RMSE.
Scope of the Article: Cryptocurrency