Stock Market Investment Decisions: The Role of Personal Traits vs. Macroeconomic Fundamentals in an Explainable Machine Learning Framework

• Project/Area Number: 25K05174
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Review Section: Basic Section 07060:Money and finance-related
• Research Institution: Musashi University
• Principal Investigator: Lin Ching 武蔵大学, 国際教養学部, 教授 (70582287)
• Co-Investigator(Kenkyū-buntansha): 柿中 真 立命館大学, 経済学部, 教授 (40421234)
• Project Period (FY): 2025-04-01 – 2028-03-31
• Project Status: Granted (Fiscal Year 2025)
• Budget Amount: ¥4,550,000 (Direct Cost: ¥3,500,000、Indirect Cost: ¥1,050,000); Fiscal Year 2027: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000); Fiscal Year 2026: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000); Fiscal Year 2025: ¥2,210,000 (Direct Cost: ¥1,700,000、Indirect Cost: ¥510,000)
• Keywords: machine learning / portfolio choice / asset allocation / investor behavior

Outline of Research at the Start

This study uses interpretable machine learning to analyze how macroeconomic conditions and personal traits influence stock market investment decisions. Using SCF data, we apply models like neural networks and KAN, followed by SHAP and ALE to identify key drivers and relationships.