A genetic-based stock selection model using investor sentiment indicators

In this paper, we present a study of stock selection using genetic algorithms (GA). We first devise a stock scoring model using indicators of investor sentiment arising from behavioral finance literature. The scores are then used to obtain the relative rankings of stocks. Top-ranked stocks can be se...

Full description

Saved in:
Bibliographic Details
Main Authors: Chien-Feng Huang, Chih-Hsiang Chang, Bao Rong Chang, Tsung-Nan Hsieh
Format: Conference Proceeding
Language:English
Subjects:
Behavioral finance
Benchmark testing
Computational modeling
Encoding
Finance
Genetic algorithms
investor sentiment
model validation
Optimization
Portfolios
stock selection
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, we present a study of stock selection using genetic algorithms (GA). We first devise a stock scoring model using indicators of investor sentiment arising from behavioral finance literature. The scores are then used to obtain the relative rankings of stocks. Top-ranked stocks can be selected to form a portfolio. Furthermore, we employ GA for optimization of model parameters and feature selection for input variables to the stock scoring model. We will show that the investment returns provided by our proposed methodology significantly outperform the benchmark returns. Based upon the promising results obtained, we expect this GA-based methodology to advance the research in soft computing for behavioral finance and provide an effective solution to stock selection in practice.
DOI:10.1109/GRC.2011.6122605