Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Modular LLM Framework for Explainable Price Outlier Detection

Shadi Sartipi, John Wu, Sina Ghotbi, Nikhita Vedula, Shervin Malmasi

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.

A Modular LLM Framework for Explainable Price Outlier Detection

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.
Paper Structure (22 sections, 1 equation, 3 figures, 3 tables)

This paper contains 22 sections, 1 equation, 3 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Price Anomaly Detection
  4. Agentic LLM Architectures
  5. RAG for Structured Data
  6. Method
  7. Candidate Neighbor Product Generation
  8. Relevance Classification Agent
  9. Utility Assessment Agent
  10. Reasoning-Based Price Decision Agent
  11. Experiments and Results
  12. Dataset
  13. Results
  14. Baseline Comparisons
  15. Impact of Price Padding and Neighbors
  16. ...and 7 more sections

Figures (3)

  • Figure 1: Overview of our proposed agentic framework. We investigate four attribute selection configurations with the Utility Agent (Generic, Static, Dynamic, or W-Dynamic), detailed further in Section \ref{['ss:Relative_Utility_Assessment']}.
  • Figure 2: (a) The target 4-quadrant framework showing (left) the informative zones and (right) relevant products shown on uninformative zones along with utility trade-off padding. (b) The sample of the decision showing the (left) correct price, and (right) outlier price.
  • Figure 3: Example for the Utility Agent analysis.