Research Paper Review: Bitcoin Forecasting Method Based on CNN-LSTM Hybrid Neural Network Model

I have been working on developing models to predict the prices of bitcoins and found a research paper on the internet that explained the idea to using a CNN-LSTM hybrid neural network to make those predictions. The research paper can be found here:- https://ietresearch.onlinelibrary.wiley.com/doi/full/10.1049/joe.2019.1203

This research paper was very well written and included mathematical formulas in it to demonstrate what methods were used to preprocess the data, to build the model, and to calculate error in the predictions.

I thought that since predicting on bitcoin prices is one thing that many people are interested in achieving, it would be a good idea to review this research paper, titled ‘Bitcoin Forecasting Method Based on CNN-LSTM Hybrid Neural Network Model’.

Abstract

It is proposed to use a hybrid neural network of a convolutional neural network (CNN) and long short term memory (LSTM) is used to predict the price of bitcoin.

The transaction data of bitcoin and external information are used as input to the model.

The CNN is used for feature extraction . feature vectors are input into the LSTM for training and forecasting the short term price of…