Genetic Feature Selection Applied to KOSPI and Cryptocurrency Price Prediction

Feature selection reduces the dimension of input variables by eliminating irrelevant features. We propose feature selection techniques based on a genetic algorithm, which is a metaheuristic inspired by a natural selection process. We compare two types of feature selection for predicting a stock mark...

Full description

Saved in:
Bibliographic Details
Published inMathematics (Basel) Vol. 9; no. 20; p. 2574
Main Authors Cho, Dong-Hee, Moon, Seung-Hyun, Kim, Yong-Hyuk
Format Journal Article
LanguageEnglish
Published Basel MDPI AG 01.10.2021
Subjects
Chromosomes
cryptocurrency price prediction
Digital currencies
feature selection
Food science
genetic algorithm
Genetic algorithms
Heuristic methods
Mutation
Neural networks
Performance prediction
Redundancy
Regression models
Solution space
Stock exchanges
stock prediction
Online AccessGet full text

Cover

More Information
Summary:Feature selection reduces the dimension of input variables by eliminating irrelevant features. We propose feature selection techniques based on a genetic algorithm, which is a metaheuristic inspired by a natural selection process. We compare two types of feature selection for predicting a stock market index and cryptocurrency price. The first method is a newly devised genetic filter involving a fitness function designed to increase the relevance between the target and the selected features and decrease the redundancy between the selected features. The second method is a genetic wrapper, whereby we can find the better feature subsets related to KOPSI by exploring the solution space more thoroughly. Both genetic feature selection methods improved the predictive performance of various regression functions. Our best model was applied to predict the KOSPI, cryptocurrency price, and their respective trends after COVID-19.
ISSN:2227-7390
2227-7390
DOI:10.3390/math9202574