Bitcoin Analysis with Deep Learning

Python Bitcoin is widely used cryptocurrency for digital market. It is decentralised that means it is not own by government or any other company.Transactions are simple and easy as it doesn’t belong to any country.Records data are stored in Blockchain.Bitcoin price is variable and it is widely used so it is important to predict the price of it for making any investment.This project focuses on the accurate prediction of cryptocurrencies price using neural networks. We’re implementing a Long Short Term Memory (LSTM) model using keras; it’s a particular type of deep learning model that is well suited to time series data (or any data with temporal/spatial/structural order e.g. movies, sentences, etc.).We have used different activation function for analysing the efficiency of the system.Instead of historical data we are using live streaming data for better accuracy.

In this video, I used the opening values between 2011 and 19/04/2021. I carried out the project on the last opening day and at the end of the project, the next day (April 20) bitcoin opening rate was estimated with the future forecast method. This project is not investment advice. In this project, I wanted to show my work in time series on a topic that has become popular recently.