Stock Selection Analysis Using Data Envelopment Analysis and Genetic Algorithm Based on Listed Companies' Fundamental Data

MATLAB 43K 231 views 0 downloads 1 credits
Tags:

Resource Overview

Implementing stock selection analysis by applying Data Envelopment Analysis (DEA) and Genetic Algorithm (GA) to fundamental data of listed companies. The genetic algorithm optimizes the selection of fundamental indicators, while DEA evaluates stock efficiency scores through mathematical programming techniques.

Detailed Documentation

In this article, we employ Data Envelopment Analysis (DEA) and Genetic Algorithm (GA) for stock selection analysis. DEA serves as a non-parametric method to evaluate corporate fundamental data by constructing an efficiency frontier through linear programming, where decision-making units (stocks) are ranked based on their relative efficiency. The genetic algorithm implements evolutionary optimization through selection, crossover, and mutation operations to identify the optimal combination of fundamental indicators that maximize discrimination power. This integrated analytical approach enables systematic efficiency assessment of stocks and identifies promising listed companies with strong fundamental characteristics. The implementation typically involves coding DEA models (such as CCR or BCC models) using optimization libraries and configuring GA parameters like population size and fitness functions for indicator selection.

You May Also Like