scholarly journals Genetic Feature Selection Applied to KOSPI and Cryptocurrency Price Prediction

Mathematics ◽  
2021 ◽  
Vol 9 (20) ◽  
pp. 2574
Author(s):  
Dong-Hee Cho ◽  
Seung-Hyun Moon ◽  
Yong-Hyuk Kim
Keyword(s):  
Feature Selection ◽  
Selection Process ◽  
Fitness Function ◽  
Solution Space ◽  
Predictive Performance ◽  
Stock Market Index ◽  
Market Index ◽  
Genetic Feature ◽  
Input Variables ◽  
Genetic Feature Selection

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.

scholarly journals Soft computing and bioinspired computing techniques for stock market prediction-a comprehensive survey

2018 ◽  
Vol 7 (3) ◽  
pp. 1836
Author(s):  
Dr S. Kumar Chandar
Keyword(s):  
Stock Market ◽  
Soft Computing ◽  
Prediction Method ◽  
Stock Market Index ◽  
Stock Market Prediction ◽  
Market Index ◽  
Soft Computing Method ◽  
Minimum Number ◽  
Comprehensive Survey ◽  
Input Variables

Stock Market Prediction (SMP) is one of the most important and hottest topics in business and finance. The main goal of SMP is to develop an efficient technique to predict stock values and achieves accurate results with minimum number of input data. This research paper reviews currently available SMP techniques based on soft computing and bio inspired computing algorithms. Many issues in-volved in the SMP are identified and different techniques are studied along with their merits and demerits to find the most suitable one. This paper also analyses the performance of various techniques with respect to some metrics including MSE, RMSE, MAD, MAPE, AAE and Hit ratio. The reviewed papers are classified in terms of number of input variables, prediction method and evaluation parame-ters used. A tabular representation of all the SMP techniques is presented to facilitate the future comparison. From the reviewed paper, it is noticed that the integration of soft computing with the bio inspired algorithms has the potential to predict the stock market index with high accuracy and achieves best result than soft computing method alone.  

Improving the ranking quality of medical image retrieval using a genetic feature selection method

2011 ◽  
Vol 51 (4) ◽  
pp. 810-820 ◽  
Author(s):  
Sérgio Francisco da Silva ◽  
Marcela Xavier Ribeiro ◽  
João do E.S. Batista Neto ◽  
Caetano Traina-Jr. ◽  
Agma J.M. Traina
Keyword(s):  
Feature Selection ◽  
Image Retrieval ◽  
Medical Image ◽  
Feature Selection Method ◽  
Selection Method ◽  
Medical Image Retrieval ◽  
Genetic Feature ◽  
Genetic Feature Selection
Sign in / Sign up

Export Citation Format

Share Document