Selected work

Representative Papers

A Persona-based Rate Action Index

Jul 29, 2026

This study proposes a novel approach based on digital personality modeling to predict Federal Open Market Committee (FOMC) interest rate decisions—specifically, rate hikes, holds, or cuts. By constructing individualized corpora for each FOMC member and integrating retrieval-augmented generation with a personalized response mechanism, the method dynamically captures the temporal evolution of their monetary policy stances. This work presents the first interpretable model of FOMC collective behavior and yields a predictive index that leads the policy rate by approximately three quarters. Evaluated over the 2022–2025 sample period, the index exhibits strong alignment with actual rate cycles (Kendall’s τ = 0.68) and achieves a classification accuracy of 0.69, significantly outperforming benchmark models (0.47).

0 citationsRead paper

Detecting Perspective Shifts in Multi-agent Systems

Dec 04, 2025

This study addresses the challenge of monitoring dynamic evolution of individual and collective behaviors in black-box multi-agent systems. We propose the Temporal Data Kernel Perspective Space (TDKPS) joint embedding framework, which employs low-dimensional representation learning and kernel methods to map agent response sequences across time steps into a unified, comparable feature space. Subsequently, we design novel hypothesis testing procedures tailored to detect behavioral changes at both agent-level and population-level granularities. To our knowledge, this constitutes the first principled, interpretable statistical inference paradigm for monitoring multi-agent behavioral dynamics. Experiments demonstrate robustness to hyperparameter choices; sensitivity and specificity are validated on simulated digital persona systems; and natural experiments confirm the framework’s ability to significantly detect behavioral anomalies strongly associated with real-world exogenous events.

0 citationsRead paper

Recent publications

Latest Papers

A Persona-based Rate Action Index

Jul 29, 2026

This study proposes a novel approach based on digital personality modeling to predict Federal Open Market Committee (FOMC) interest rate decisions—specifically, rate hikes, holds, or cuts. By constructing individualized corpora for each FOMC member and integrating retrieval-augmented generation with a personalized response mechanism, the method dynamically captures the temporal evolution of their monetary policy stances. This work presents the first interpretable model of FOMC collective behavior and yields a predictive index that leads the policy rate by approximately three quarters. Evaluated over the 2022–2025 sample period, the index exhibits strong alignment with actual rate cycles (Kendall’s τ = 0.68) and achieves a classification accuracy of 0.69, significantly outperforming benchmark models (0.47).

0 citationsRead paper

Detecting Perspective Shifts in Multi-agent Systems

Dec 04, 2025

This study addresses the challenge of monitoring dynamic evolution of individual and collective behaviors in black-box multi-agent systems. We propose the Temporal Data Kernel Perspective Space (TDKPS) joint embedding framework, which employs low-dimensional representation learning and kernel methods to map agent response sequences across time steps into a unified, comparable feature space. Subsequently, we design novel hypothesis testing procedures tailored to detect behavioral changes at both agent-level and population-level granularities. To our knowledge, this constitutes the first principled, interpretable statistical inference paradigm for monitoring multi-agent behavioral dynamics. Experiments demonstrate robustness to hyperparameter choices; sensitivity and specificity are validated on simulated digital persona systems; and natural experiments confirm the framework’s ability to significantly detect behavioral anomalies strongly associated with real-world exogenous events.

0 citationsRead paper