# LLM-Powered Virtual Population for Demand Simulation and Pricing

arXiv: https://arxiv.org/abs/2606.16183 · HTML: https://mlsanity.com/paper/2606.16183/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 46 references that are in the map.
- First posted on arXiv 15 Jun 2026.

## Builds on (most cited first, 26 of 26)

- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://mlsanity.com/paper/2106.01345/) (2021)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback](https://mlsanity.com/paper/2305.14975/) (2023)
- [Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies](https://mlsanity.com/paper/2208.10264/) (2022)
- [How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answering](https://mlsanity.com/paper/2012.00955/) (2020)
- [Conformal Risk Control](https://mlsanity.com/paper/2208.02814/) (2022)
- [Can Large Language Models Transform Computational Social Science?](https://mlsanity.com/paper/2305.03514/) (2023)
- [Large Language Models for Supply Chain Optimization](https://mlsanity.com/paper/2307.03875/) (2023)
- [The Challenge of Using LLMs to Simulate Human Behavior: A Causal Inference Perspective](https://mlsanity.com/paper/2312.15524/) (2023)
- [Large Language Models for Market Research: A Data-augmentation Approach](https://mlsanity.com/paper/2412.19363/) (2024)
- [Mixture-of-Personas Language Models for Population Simulation](https://mlsanity.com/paper/2504.05019/) (2025)
- [Gen-DFL: Decision-Focused Generative Learning for Robust Decision Making](https://mlsanity.com/paper/2502.05468/) (2025)
- [Probabilities of Chat LLMs Are Miscalibrated but Still Predict Correctness on Multiple-Choice Q&A](https://mlsanity.com/paper/2402.13213/) (2024)
- [How Many Human Survey Respondents is a Large Language Model Worth? An Uncertainty Quantification Perspective](https://mlsanity.com/paper/2502.17773/) (2025)
- [Calibrating Verbalized Probabilities for Large Language Models](https://mlsanity.com/paper/2410.06707/) (2024)
- [AI Agents for Inventory Control: Human-LLM-OR Complementarity](https://mlsanity.com/paper/2602.12631/) (2026)
- [Large Language Newsvendor: Decision Biases and Cognitive Mechanisms](https://mlsanity.com/paper/2512.12552/) (2025)
- [Ask, Clarify, Optimize: Human-LLM Agent Collaboration for Smarter Inventory Control](https://mlsanity.com/paper/2601.00121/) (2025)
- [Optimal Decision-Making Based on Prediction Sets](https://mlsanity.com/paper/2602.00989/) (2026)
- [Generative models for decision-making under distributional shift](https://mlsanity.com/paper/2604.04342/) (2026)
- [Risk-averse Decision Making with Contextual Information: Model, Sample Average Approximation, and Kernelization](https://mlsanity.com/paper/2502.16607/) (2025)
- [OMGPT: A Sequence Modeling Framework for Data-driven Operational Decision Making](https://mlsanity.com/paper/2505.13580/) (2025)
- [SYN-DIGITS: A Synthetic Control Framework for Calibrated Digital Twin Simulation](https://mlsanity.com/paper/2604.07513/) (2026)
- [Generative Augmented Inference of LLM-generated Data for Market Research: Theory and Empirical Evidence](https://mlsanity.com/paper/2604.14575/) (2026)
- [Optimizing Service Operations via LLM-Powered Multi-Agent Simulation](https://mlsanity.com/paper/2604.04383/) (2026)

## Abstract (arXiv)

We develop an LLM-powered virtual population model that simulates demand for pricing decisions, in settings where products are described by rich unstructured information, such as text descriptions and images, and where decision makers need not only mean-demand predictions but also uncertainty estimates for counterfactual prices. Our model represents exposed customers as draws from a finite mixture of customer personas. For each persona, product, and candidate price, an LLM elicits a persona-level purchase probability using both structured persona information and unstructured product information. These probabilities are aggregated through calibrated mixture weights to form a predictive distribution of aggregate demand. The resulting simulator can evaluate counterfactual prices under various pricing objectives, including expected revenue and risk-aware criteria such as conditional value at risk. We test the framework on an online H&M fashion dataset with product descriptions and images. The calibrated LLM-based simulator achieves the best overall predictive performance among the models considered, and supports sample-efficient pricing decisions. Our framework provides a practical way to use LLMs as demand simulators for products with limited historical demand data but rich product information. By producing a full predictive demand distribution rather than only a point forecast, it enables managers to compare candidate prices, quantify demand uncertainty, and choose prices that target either average-case revenue or risk-aware objectives.