Dynamic- Radius Species-Conserving Genetic Algorithm for the Financial Forecasting of Cryptocurrencies

This research uses a Niche Genetic Algorithm (NGA) called Dynamic-radius Species-conserving Genetic Algorithm (DSGA) to select cryptocurrencies to purchase from a publicly available dataset. DSGA uses a set of training data to produce a set of rules. These rules are then used to predict cryptocurrency prices in test data by constructing weekly portfolios. DSGA is an NGA that uses a clustering algorithm enhanced by a tabu list and radius variations. DSGA also uses a shared fitness algorithm to investigate different areas of the domain. The DSGA algorithm did very well in predicting cryptocurrency movements. The weekly portfolios generated by DSGA produced a return nearly double that of investing in an equal number of cryptocurrencies.