BROWSE
Detail
Conference Paper
A Study on Feature Selection Using Random Forest for Stock Prediction
Cited - time in 
Share 
Share
- Authors
- Ji Sung Lee, Hyeon Sung Cho, Kyo Il Chung, Ji Sang Park
- Issue Date
- 2019-10
- Citation
- International Conference on Control, Automation and Systems (ICCAS) 2019, pp.1-3
- Publisher
- IEEE
- Language
- English
- Type
- Conference Paper
- Abstract
- Recently, many studies have been actively conducted to predict stock prices using machine learning technology. The factors affecting the stock price are very diverse and vast. Collecting and analyzing all of these data are costly and time consuming. In addition, stock prediction models require frequent data analysis and updates. For this reason, it is vital to select and analyze only the key data that affect the stock price. In this study, among the various feature selection techniques available, we apply the random forest method to extract the key indicators of each stock.
- KSP Keywords
- Data analysis, Feature selection(FS), Key indicators, Random forest, Stock prices, feature selection techniques, learning technology, machine Learning, prediction model, stock prediction