Machine-Learning Inference and Optimal Control of Social Systems

• Project/Area Number: 25K03185
• Research Category: Grant-in-Aid for Scientific Research (B)
• Allocation Type: Multi-year Fund
• Section: 一般
• Review Section: Basic Section 61030:Intelligent informatics-related; Basic Section 60030:Statistical science-related; Sections That Are Subject to Joint Review: Basic Section60030:Statistical science-related , Basic Section61030:Intelligent informatics-related
• Research Institution: Kyoto University
• Principal Investigator: MOLINA JOHN 京都大学, 工学研究科, 助教 (20727581)
• Project Period (FY): 2025-04-01 – 2029-03-31
• Project Status: Granted (Fiscal Year 2025)
• Budget Amount: ¥16,120,000 (Direct Cost: ¥12,400,000、Indirect Cost: ¥3,720,000); Fiscal Year 2028: ¥3,380,000 (Direct Cost: ¥2,600,000、Indirect Cost: ¥780,000); Fiscal Year 2027: ¥4,940,000 (Direct Cost: ¥3,800,000、Indirect Cost: ¥1,140,000); Fiscal Year 2026: ¥3,380,000 (Direct Cost: ¥2,600,000、Indirect Cost: ¥780,000); Fiscal Year 2025: ¥4,420,000 (Direct Cost: ¥3,400,000、Indirect Cost: ¥1,020,000)
• Keywords: Machine Learning / Optimal Control / Social Systems / Behavior / Epidemic

Outline of Research at the Start

We will build a Machine-Learning (ML) framework to infer, predict, and control the behavior of interacting rational agents. For this, we will develop a Game-Theory Informed ML method that can be trained on behavioral data, and use it to infer the hidden utility functions that govern the decision-making of the agents. In particular, we focus on the societal response to a pandemic (e.g., COVID-19). We will first validate our method on synthetic data, before applying it to real-world data.