A Modular LLM Framework for Explainable Price Outlier Detection

TL;DR

This paper introduces a modular LLM-based framework for explainable price outlier detection in retail, leveraging reasoning over product similarities and attributes to improve accuracy and interpretability.

Contribution

It presents a novel agentic LLM framework that performs multi-stage reasoning for price outlier detection, outperforming existing zero-shot and retrieval-based methods.

Findings

Achieves over 75% agreement with human auditors.

Outperforms baseline zero-shot and retrieval-based LLM techniques.

Demonstrates flexibility and sensitivity to hyper-parameters.

Abstract

Detecting product price outliers is important for retail and e-commerce stores as erroneous or unexpectedly high prices adversely affect competitiveness, revenue, and consumer trust. Classical techniques offer simple thresholds while ignoring the rich semantic relationships among product attributes. We propose an agentic Large Language Model (LLM) framework that treats outlier price flagging as a reasoning task grounded in related product detection and comparison. The system processes the prices of target products in three stages: (i) relevance classification selects price-relevant similar products using product descriptions and attributes; (ii) relative utility assessment evaluates the target product against each similar product along price influencing dimensions (e.g., brand, size, features); (iii) reasoning-based decision aggregates these justifications into an explainable price outlier judgment. The framework attains over 75% agreement with human auditors on a test dataset, and outperforms zero-shot and retrieval based LLM techniques. Ablation studies show the sensitivity of the method to key hyper-parameters and testify on its flexibility to be applied to cases with different accuracy requirement and auditor agreements.