mlsanityData to 7 Oct 2026

LLM-Powered Virtual Population for Demand Simulation and Pricing

arXiv 2606.16183 ↗First posted 15 Jun 2026cs.LG cs.AI cs.CLcited by 0

Not on the map. Why?

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 26 of its 46 references that are in the map. First posted on arXiv 15 Jun 2026.

Builds on

26 of 46 references.

References · 26

  1. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  2. 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,528
  3. 2025SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Featurescited by 1,127
  4. 2023Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedbackcited by 788
  5. 2022Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studiescited by 506
  6. 2020How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answeringcited by 439
  7. 2022Conformal Risk Controlcited by 290
  8. 2023Can Large Language Models Transform Computational Social Science?cited by 245
  9. 2023Large Language Models for Supply Chain Optimizationcited by 61
  10. 2023The Challenge of Using LLMs to Simulate Human Behavior: A Causal Inference Perspectivecited by 57
  11. 2025Mixture-of-Personas Language Models for Population Simulationcited by 20
  12. 2024Large Language Models for Market Research: A Data-augmentation Approachcited by 18
14 more
  1. 2025Gen-DFL: Decision-Focused Generative Learning for Robust Decision Makingcited by 18
  2. 2024Probabilities of Chat LLMs Are Miscalibrated but Still Predict Correctness on Multiple-Choice Q&Acited by 16
  3. 2025How Many Human Survey Respondents is a Large Language Model Worth? An Uncertainty Quantification Perspectivecited by 10
  4. 2024Calibrating Verbalized Probabilities for Large Language Modelscited by 9
  5. 2026AI Agents for Inventory Control: Human-LLM-OR Complementaritycited by 6
  6. 2025Large Language Newsvendor: Decision Biases and Cognitive Mechanismscited by 4
  7. 2026Optimal Decision-Making Based on Prediction Setscited by 4
  8. 2026Generative models for decision-making under distributional shiftcited by 4
  9. 2025Risk-averse Decision Making with Contextual Information: Model, Sample Average Approximation, and Kernelizationcited by 3
  10. 2025Ask, Clarify, Optimize: Human-LLM Agent Collaboration for Smarter Inventory Controlcited by 3
  11. 2025OMGPT: A Sequence Modeling Framework for Data-driven Operational Decision Makingcited by 2
  12. 2026SYN-DIGITS: A Synthetic Control Framework for Calibrated Digital Twin Simulationcited by 2
  13. 2026Generative Augmented Inference of LLM-generated Data for Market Research: Theory and Empirical Evidencecited by 2
  14. 2026Optimizing Service Operations via LLM-Powered Multi-Agent Simulationcited by 1

Built on by

Not cited yet.