PREDICTIVE MODELLING OF SELECT CRYPTOCURRENCIES AND IDENTIFYING THE BEST SUITABLE MODEL - WITH REFERENCE TO ARIMA AND ANNS

Prof. Reepu, Prof.bijesh Dhyani, Ms. Ayushi, Dr. Sudhi Sharma and Dr. Manish Kumar
Additional contact information
Prof. Reepu: CHANDIGARH UNIVERSITY
Prof.bijesh Dhyani: FACULTY, MANAGEMENT STUDIES, GRAPHIC ERA DEEMED TO BE UNIVERSITY DEHRADUN, INDIA
Ms. Ayushi: STUDENT, FIIB, NEW DELHI
Dr. Sudhi Sharma: ASSISTANT PROFESSOR, FIIB, NEW DELHI
Dr. Manish Kumar: ASSOCIATE PROFESSOR, MANAGEMENT STUDIES, GRAPHIC ERA DEEMED TO BE UNIVERSITY DEHRADUN, INDIA

Annals - Economy Series, 2022, vol. 6, 11-19

Abstract: In the 4th Industrial revolution, cryptocurrencies emerged as a technology-based financial asset. The digital currency market is the repercussion of the financial crisis of 2008, thus creating disruption in the whole financial market. Investors are fascinated by the crypto market to get the benefit of abnormal returns. Taking into consideration of active trading in digital currency, the paper identifies the best predictable model of select cryptocurrencies i.e. Bitcoin, Ethereum, and Tether by applying ARIMA and ANNs. Finally, the robustness of models has been found by using the criteria i.e. MSE and MASE. It has been found that ANNs are the most suitable model among the two to predict the future prices of cryptocurrencies. The results of the study comprise that the best fit model of ARIMA for Bitcoin is (4,1,1), for Tether (1,1,2), and for Ethereum (1,1,1). Results of ANNs show that for Bitcoin, Tether, and Ethereum, the best suited ANN models are NNAR(1,1); NNAR(16,8), and NNAR(7,4), respectively. The study is of great importance to investors who are looking for investments in the most traded cryptocurrencies. Finally, from the results of various parameters i.e. RMSE, MAE, MPE, and MAPE, for Bitcoin ARIMA is the best-suited model and for Tether and Ethereum, ANNs are the best-suited or robust models for predicting the stock prices.

Keywords: Cryptocurrency; Prediction; ARIMA; ANNs; MSE; MASE (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.utgjiu.ro/revista/ec/pdf/2022-06/02_Reepu.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:cbu:jrnlec:y:2022:v:6:p:11-19

Access Statistics for this article

More articles in Annals - Economy Series from Constantin Brancusi University, Faculty of Economics Contact information at EDIRC.
Bibliographic data for series maintained by Ecobici Nicolae ( this e-mail address is bad, please contact ).