Prediction of Crypto Currency by Multiple Linear Regressions using Anaconda Software
European Journal of Molecular & Clinical Medicine,
2020, Volume 7, Issue 4, Pages 76-81
AbstractFinancial instruments traded in the stock markets attract various categories of investors across the world. The major objective of investment strategy is to minimize the risk and maximize the return and this can be achieved by choosing the right security at an appropriate time will result in loss reduction. The modern day investment alternative across the globe is crypto currency. A crypto currency is digital asset designed to work as a medium of exchange that uses strong cryptography to secure financial transactions, control the creation of additional units, and verify the transfer of assets. However, cryptocurrency are highly volatile due to their supply and demand factors as they are been designed to have a high degree of non availability. Hence, it is important to have a bitcoins price prediction model that can predict the bitcoins total supply value. In this paper, a multiple linear regression model for predicting the bitcoins total supply is proposed. The change in bitcoins total supply for definite time intervals like total supply per an hour, a day and a week were input for developing the linear regression model using the software package ANACONDA. This is significant improvement in comparison to traditional models. In the present scenario there is no such method of predicting the price of bitcoins. The proposed model can be used a decision making technique during the intense situations of bitcoins trading, where human predictions will not make appropriate price predictions. This paper comprises of various sections where the first section describes the introduction to Bitcoins, their importance followed by methodology and the strategy of algorithm applied. The third section describes the processing steps and implementation of algorithm and followed by validation of the project accuracy and efficiency checker.
- Article View: 253
- PDF Download: 2,411