Research on complex financial decision making driven by geometric aggregation and intelligent optimization of...

Area of Science:

• Decision Sciences
• Artificial Intelligence
• Financial Mathematics

Background:

• Multi-attribute group decision-making (MAGDM) in finance faces challenges like high-dimensional data, uncertainty, and heterogeneous information.
• Existing methods struggle with complex fuzzy information integration and preference modeling.

Purpose of the Study:

• To propose a novel high-dimensional intelligent aggregation framework for MAGDM in finance.
• To integrate Picture Fuzzy Z-numbers with the Plant Growth Simulation Algorithm (PGSA) for enhanced decision support.

Main Methods:

• Developed a framework using Picture Fuzzy Z-numbers and PGSA with a biomimetic phototaxis search mechanism.
• Applied the method to the Ashraf financial decision-making dataset.
• Compared performance against seven mainstream aggregation techniques.

Main Results:

• Achieved a Hamming distance of 0.0928, weight cosine similarity of 0.9793, information energy of 0.1138, and Pearson correlation coefficient of 0.9277.
• Demonstrated superior aggregation accuracy compared to most existing methods.
• Validated the framework's effectiveness in high-dimensional financial decision scenarios.

Conclusions:

• The proposed framework offers a robust solution for fuzzy information integration in complex financial MAGDM.
• It provides an effective tool for high-dimensional group preference modeling and aggregation optimization.
• This research advances fuzzy set theory applications in financial decision support systems.