Time-series forecasting of Bitcoin prices

This repository contains the code and datasets for creating the machine learning models in the research paper titled "Time-series forecasting of Bitcoin prices using high-dimensional features: a machine learning approach" with doi:10.1007/s00521-020-05129-6

Models considered:

• LSTM
• SVM
• SANN
• ANN

Feature selection process is based on Pearson correlation, random forest, and variance inflation factor.

New analysis is submitted to the dev and the main branches.

The original code is archived in the "research_paper" branch.