Pricing Heuristics Against Non-human Transaction Orchestration Mechanisms
Abstract
When you shop online, prices often change based on how much interest you show — the more you browse, the more the site learns about your intent and may raise prices accordingly. This works because stores assume that a curious, engaged shopper is more likely to buy. But AI assistants are now doing the shopping research on behalf of users: they browse in one session to gather price information and then let the user purchase in a fresh session at the lower, unadjusted price. The store never sees the connection between the two, so it never gets to factor in that genuine intent — and loses the revenue it would have earned.
PHANTOM studies this problem and builds defenses against it. We created a realistic fake store (in hotel and airline modes) where both real people and AI agents were given shopping tasks, and we recorded every click, scroll, and page visit. By comparing how humans and AI agents move through a site, we found clear patterns that tell them apart. We then used those patterns to build a smarter pricing system that can recognize when it is likely talking to an AI scout and adjust its strategy accordingly — protecting the store's margins without making things worse for genuine shoppers.
Project Scope
The current thesis revision extends both theory and implementation. The main research question is how a pricing system can preserve margin integrity when browsing and purchasing are increasingly orchestrated by AI agents.
- Formal contribution: a Cost of Information erosion theorem showing why price-query saturation can collapse dynamic pricing power.
- System contribution: a hybrid online/offline stack (Next.js storefront, pricing provider, Kafka event streams, Airflow ETL, Redis serving layer).
- Modeling contribution: class-specific transition kernels for human and agent behavior, with KL-divergence based separability scores.
- Control contribution: a contamination-aware DR-RL pricing policy trained under distributional uncertainty using Wasserstein-style robustness.
Controlled trials currently include balanced human and agent sessions with goal-driven tasks across hotel and airline interfaces. Early separability results are strong (Mann-Whitney U=2.0, p=0.0006), while robust pricing gains remain regime-dependent and are being calibrated in larger sweeps.
Defense Scenes
COI from first principles.
Behavioral kernel construction: learning how humans and agents differ.
Distributionally robust control loop.
Full Thesis
BibTeX
@thesis{Rosel2025PHANTOM,
title={Pricing Heuristics Against Non-human Transaction Orchestration Mechanisms},
author={Rösel, Daniel},
school={IE University},
year={2025},
address={Madrid, Spain},
type={Bachelor's Thesis},
note={Advisor: Alberto Mart{\'i}n Izquierdo}
}