AI-Powered Exception Management in Retail Planning Systems

View at publisher Summarise with VIRAT
Authors: Lukesh Singla, Manthan Lad
Cited by: 0
References: 13

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

The intricate interdependencies of contemporary supply chain dynamics are difficult for conventional rule-based systems to handle, which is a major issue in retail planning systems. In this study, we investigate the impact of AI methods for root cause attribution and exception detection in retail planning settings. In terms of exception identification, machine learning algorithms perform better than traditional threshold methods, according to an analysis of 5,200 retail planning situations. Support Vector Machines had an exception detection accuracy of 99.04 %. Additionally, mathematical models for anomaly scoring were created, and we used a variety of predicted features, including supplier performance metrics, inventory fluctuation, and demand variance, as proof. The findings demonstrate that AI-based techniques can use ensemble methods to detect exceptions with a sensitivity of$\mathbf{9 8. 5 6 \%}$and minimize false positive rates by$\mathbf{7 3 \%}$.

Fields of Study & Subjects

Anomaly Detection Techniques and Applications Supply Chain and Inventory Management Impact of AI and Big Data on Business and Society

Publication details

Journal / source
International Conference on Communication, Computing and Electronics Systems (ICCCES)
Pages
1236–1241
Publication date
21 January 2026
Language
EN