arXiv subjects

Euncheol Shin

Publications and source records attributed to Euncheol Shin.

3 recordsLinked to original sources

arXiv2026

Do People Follow AI Advice? Evidence from a Pension Portfolio Choice Experiment

We study how differences in AI-generated financial recommendations are transmitted into individual portfolio choices. In an experiment with 400 employed adults enrolled in workplace defined contribution pension plans in South Korea, participants allocate a hypothetical pension balance across eleven products and may revise it after receiving one of two fixed AI-generated recommendations. A $2 \times 2$ design randomizes recommendation content and whether the recommendation includes a short rationale. Approximately 37$\%$ of the experimentally induced difference between the aggressive and conservative recommendations passes through to final portfolios. This causal contrast changes expected portfolio return, volatility, allocations across risk grades, and the number of products held, but produces no detectable difference in computed Sharpe ratios. 81$\%$ of participants revise. Among revisers, 95$\%$ move toward the assigned recommendation and implement about half of the suggested adjustment. Rationales do not detectably alter pass-through. These results show that users partially and selectively transmit recommendation content into economically meaningful differences in risk exposure while retaining substantial weight on their initial choices.

econ.GN↗

arXiv2026

Can an LLM Learn Preferences from Choice Data?

Can large language models (LLMs) learn a decision maker's preferences from observed choices and generate preference-consistent recommendations in new situations? We propose a portable Simulate-Recommend-Evaluate framework that tests preference learning from revealed-choice data by comparing LLM recommendations with optimal choices implied by known preference primitives. We apply the framework to choice under uncertainty using the disappointment aversion model. Recommendation accuracy improves as models observe more choices, but learning is heterogeneous across preference types and LLMs: GPT learns risk aversion better than disappointment aversion, Gemini performs best in high disappointment-aversion regions, and Claude shows the broadest effective learning across parameter regions.

econ.GN↗

arXiv2025

Robust Intervention in Networks

In economic settings such as learning, social behavior, and financial contagion, agents interact through interdependent networks. This paper examines how a decision maker (DM) can design an optimal intervention strategy under network uncertainty, modeled as a zero-sum game against an adversarial ``Nature'' that reconfigures the network within an uncertainty set. Using duality, we characterize the DM's unique robust intervention and identify the worst-case network structure, which exhibits a rank-1 property, concentrating risk along the intervention strategy. We analyze the costs of robustness, distinguishing between global and local uncertainty, and examine the role of higher-order uncertainties in shaping intervention outcomes. Our findings highlight key trade-offs between maximizing influence and mitigating uncertainty, offering insights into robust decision-making. This framework has applications in policy design, economic regulation, and strategic interventions in dynamic networks, ensuring their resilience against uncertainty in network structures.

econ.TH↗