Combining multiple feature selection methods for stock prediction: Union, intersection, and multi-intersection approaches

By Chih-Fong Tsai, Yu-Chieh Hsiao. Decision Support Systems, 2010

382 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Electrical and Electronic Engineering, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/34f3955cb11db849789f7fbc78eb3cb347dd573d

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Electrical and Electronic Engineering

In Management Science and Operations Research

Citations in the corpus

A Survey of Forex and Stock Price Prediction Using Deep Learning (2021, background): “People hope that the progress made in big data, especially in the deep learning field, can help them analyze stock information [1].”
A Double-Layer Neural Network Framework for High-Frequency Forecasting (2017, methodology): “…methods in ﬁnance belong roughly to two categories: the time series models [Chen et al. 2007; Hassan et al. 2007; Hsu et al. 2009; Pai and Lin 2005; Tsai and Hsiao 2010], and the machine learning-based approaches [Kara et al. 2011; Patel et al. 2015; Ar´evalo et al. 2016; Pai and Lin 2005; Hsu et…”
Short-term stock market price trend prediction using a comprehensive deep learning system (2020, background): “Tsai and Hsiao in [42] proposed a solution as a combination of different feature selection methods for prediction of stocks.”
Restricted Boltzmann machine based stock market trend prediction (2017, background): “For feature engineering, traditional feature selection (e.g., ReliefF [4], Information Gain [5], OneR [6], etc.) is widely used in stock market prediction.”
Developing an approach to evaluate stocks by forecasting effective features with data mining methods (2015, background): “Furthermore, many studies have claimed and verified that feature selection (FS) is the key process in stock prediction modeling (Tsai & Hsiao, 2010).”
A review of unsupervised feature learning and deep learning for time-series modeling (2014, methodology): “According to the Efficient Market Hypothesis (EMH) [30], stock market prices follow a random walk pattern, meaning that a stock has the same probability to go up as it has to go down, resulting in that predictions can not have more than 50% accuracy [121].”
Ranking and combining multiple predictors without labeled data (2013, neutral): “π = sensitivity+ specificity 2 = 1 2 ðψ + ηÞ; [1]”