Abstract :

The Public Distribution System (PDS) In India Serves As A Critical Welfare Mechanism For Distributing Subsidized Food Grains To Millions Of Citizens, Yet It Remains Vulnerable To Systematic Fraud, Including Diversion Of Stock, Ghost Beneficiaries, And Quantity Manipulation At Ration Shops. This Paper Proposes An AI-powered Fraud Detection Framework That Integrates RFID-based Smart Cards For Beneficiary Authentication, GSMbased OTP Verification To Confirm Transactions In Real Time, And IoT-enabled Inventory Tracking To Monitor Stock Movement Across The Supply Chain. A Blockchain-backed Ledger Ensures Tamper-proof Recording Of All Transactions, Providing Transparency And Traceability From Warehouse To End User. At The Core Of The System, A Random Forest Classifier Analyzes Transaction Patterns, Beneficiary Behavior, And Inventory Discrepancies To Flag Anomalies Indicative Of Fraudulent Activity. The Proposed Architecture Combines Hardware-based Authentication, Distributed Ledger Technology, And Machine Learning To Create A Multi-layered Defense Against Corruption In Food Grain Distribution. Experimental Evaluation Demonstrates That The Integrated Approach Improves Detection Accuracy Over Traditional Manual Auditing Methods While Reducing Leakage And Diversion. This Framework Offers A Scalable, Technology-driven Solution To Strengthen Accountability An. KEYWORDS: Fraud Detection, Machine Learning, Random Forest Classifier, Predictive Analytics, Flask, Framework.

Published:

05-8-2026

Issue:

Vol. 26 No. 8 (2026)

Page Nos:

639 - 645

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite