Simulating and Analysing Human Survey Responses with Large Language Models: A Case Study in Energy Stated Preference

Abstract: Survey research plays a crucial role in studies by capturing consumer preferences and informing policy decisions. Stated preference (SP) surveys help researchers understand how individuals make trade-offs in hypothetical, potentially futuristic, scenarios. However, traditional methods are costly, time-consuming, and affected by respondent fatigue and ethical constraints. LLMs have shown remarkable capabilities in generating human-like responses, prompting interest in their use in survey research. This study investigates LLMs for simulating consumer choices in energy-related SP surveys and explores their integration into data collection and analysis workflows. Test scenarios were designed to assess the simulation performance of several LLMs (LLaMA 3.1, Mistral, GPT-3.5, DeepSeek-R1) at individual and aggregated levels, considering prompt design, in-context learning (ICL), chain-of-thought (CoT) reasoning, model types, integration with traditional choice models, and potential biases. While LLMs achieve accuracy above random guessing, performance remains insufficient for practical simulation use. Cloud-based LLMs do not consistently outperform smaller local models. DeepSeek-R1 achieves the highest average accuracy (77%) and outperforms non-reasoning LLMs in accuracy, factor identification, and choice distribution alignment. Previous SP choices are the most effective input; longer prompts with more factors reduce accuracy. Mixed logit models can support LLM prompt refinement. Reasoning LLMs show potential in data analysis by indicating factor significance, offering a qualitative complement to statistical models. Despite limitations, pre-trained LLMs offer scalability and require minimal historical data. Future work should refine prompts, further explore CoT reasoning, and investigate fine-tuning techniques.