Marrying Pricing and Advertising with LLMs

Key points

• The seller aims to maximize revenue under an unknown product demand that depends on both decisions, while observing only whether each offer leads to a purchase.1
• We propose an online actor-critic algorithm that combines low-rank adaptation (LoRA) of a pretrained LLM with a demand model fitted to available data.1
• At each round, the actor generates an advertisement, and the critic estimates purchase probabilities to guide price selection.1
• To evaluate our approach, we develop an evaluation framework with three synthetic demand models and a demand simulator built from real-world marketplace data.1

Sources (1)

• [1]Marrying Pricing and Advertising with LLMs
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 7, 12:50 PM

  We study a sequential pricing problem in which a seller jointly posts a price and an advertisement generated by a large language model (LLM).

  The seller aims to maximize revenue under an unknown product demand that depends on both decisions, while observing only whether each offer leads to a purchase.

Extractive summary: sentences quoted from the sources.