A CNN Integrated Blockchain Framework for Reliable Data Validation in Grocery-Retail Supply Chain Management

Samarth Bhosale, Jerin Chirackal, Komal Mahale, Amrutha Hippalgaonkar () and Saroj Dhake
Additional contact information
Samarth Bhosale: K. K. Wagh Institute of Engineering Education and Research, Department of Management Studies
Jerin Chirackal: K. K. Wagh Institute of Engineering Education and Research, Department of Management Studies
Komal Mahale: K. K. Wagh Institute of Engineering Education and Research, Department of Management Studies
Amrutha Hippalgaonkar: ShreeNidhi Traders
Saroj Dhake: K. K. Wagh Institute of Engineering Education and Research, Department of Management Studies

A chapter in Proceedings of the International Conference on Operations & Supply Chain Management 2025 (ICOSCM 2025), 2025, pp 18-32 from Springer

Abstract: Abstract Digital supply chain is a unified system for companies to optimise the data among partners. Grocery supply chains are yet struggling with the innovative solutions for data management across all stages. Blockchain is the standard for transparency and traceability in grocery supply chains. It enhances traceability, supply chain visibility, authenticity and ethical sourcing. This paper assisted local grocery retailers in implementing blockchain to increase their adaptability and benefit the company. However, its effectiveness is dependent on the quality of the input data. The classic “Garbage in, garbage out” dilemma remains a major hurdle for any blockchain project. Errors from IoT devices, inaccurate inventory logs, or even simple human mistakes get permanently recorded on the ledger. This undermines trust and can create major operational headaches. So, this paper has addressed this problem with a novel approach to integrate Convolutional Neural Networks (CNN) with blockchain for effective supply chain management. This paper outlines a framework for Intelligent Data Validation Layer (IDVL) that utilizes CNNs to evaluate data before it is uploaded to the blockchain. The model analyses multi-dimensional data streams such as temperature readings, inventory quantities, pricing, and shipment tracking to identify anomalies. It combines IoT device cross validation and smart contract-based integrity scores to confirm the data’s authenticity and reliability. Compared to RNNs (Recurrent Neural Networks) and more traditional validation techniques, CNNs detect a higher rate of inconsistencies, especially with data coming from diverse sources. The outcome is improved data quality, streamlined operations, and increased consumer trust throughout retail and grocery sectors.

Date: 2025
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:advbcp:978-94-6463-914-8_3

Ordering information: This item can be ordered from
http://www.springer.com/9789464639148

DOI: 10.2991/978-94-6463-914-8_3

Access Statistics for this chapter

More chapters in Advances in Economics, Business and Management Research from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().