A Comparative Analysis and Prediction over Bitcoin Price Using Machine Learning Technique

Abstract

Bitcoin is one of the primary computerized monetary forms to utilize peer innovation to work with moment installments. The free people and organizations who own the overseeing figuring control and take part in the bitcoin network—bitcoin miners— are accountable for preparing the exchanges on the blockchain and are persuaded by remunerations (the arrival of new bitcoin) and exchange charges paid in bitcoin. These excavators can be considered as the decentralized authority implementing the believability of the bitcoin network. New bitcoin is delivered to the excavators at a fixed yet occasionally declining rate. There is just 21 million bitcoin that can be mine altogether. As of January 30, 2021, there are around 18,614,806 bitcoin in presence and 2,385,193 bitcoin left to be mined. This paper will predict the nature of bitcoin price because, according to the reports of the past few years. The year 2020-present appeared to be a good time for bitcoin because, in this time duration, bitcoin has seen huge ups and downs. This paper will use various Machine Learning Techniques for the predictive analysis of bitcoin to accurately predict the price's nature. As the price of bitcoin depends upon various factors and these factors directly affect the price, i.e., multiple factors of bitcoin are dependent on each other. After analyzing the results from multiple research papers and review papers, we discovered each algorithm has its advantages and disadvantages while predicting the bitcoin value. Keeping in mind all the findings, we will find algorithms that predict the bitcoin price accurately and without fewer disadvantages. So, if we go as per assumptions, regression would be the best choice for predicting the bitcoin value, but there are others algorithms also. So, in this paper, we will see the results of the multiple algorithms and then choose the correct algorithm after analyzing the results of all the implemented algorithms. This paper also includes the implementation of the comparison charts with each algorithm so that it will be easy to analyze the findings of each algorithm.