Description

Crypto-currency Price Prediction

ABSTRACT Crypto-currency such as Bitcoin are more popular these days among investors. In the proposed work, it is attempted to predict the Bitcoin price accurately taking into consideration various parameters that affect the Bitcoin value. For the first phase of investigation, it is aimed to understand and identify daily trends in the Bitcoin market while gaining insight into optimal features surrounding Bitcoin price. The data set consists of various features relating to the Bitcoin price and payment network over the course of time, recorded daily. For the second phase of investigation, using the available information, we will predict the sign of the daily price change with highest possible accuracy
AIM
The aim of this work is to ascertain with what accuracy can the price of Bitcoin be predicted using different machine learning algorithm and compare their accuracy.
o Implement more than one machine learning to predict the value.
o Accuracy compared to show best algorithm for prediction.
The execution is carried out with following steps
a. Dataset collection from quandl.com
b. Dataset pre-processing
c. Split dataset as train and test set
d. Apply Machine learning Decision tree and linear regression
e. Train the model
f. Give test set and predict values
g. Price forecast for five days
Bitcoin dataset collected live and stored as bitcoin.csv file is considered as dataset, which is split into train set and test set. We have considered 80% of data as training input for our machine learning algorithm model to train the model. The remaining 20% of data is considered as test for result prediction. We exploited Lasso and Regression to predict the price trend for 20% test input and the predicted values to plotted and compared for accuracy.