Agriculture Cyber Crime Fraud Detection System: A Machine Learning and Exploratory Data Analysis Framework
Author(s): Prof. Tagade R.O, Parth Sanjay Aote
Publication #: 2609012
Date of Publication: 12.10.2026
Country: India
Pages: 1-4
Published In: Volume 12 Issue 5 October-2026
Abstract
As digital banking, UPI services, and government subsidy portals become routine tools for farmers across rural India, online security has become a pressing concern. Limited cybersecurity awareness in farming communities has led to frequent financial scams, including fake fertilizer websites, deceptive SMS phishing links, OTP theft, and unauthorized payment transfers. This paper introduces a practical detection framework built to collect, clean, and analyze agricultural fraud incident records. By pairing structured data preprocessing in Python with machine learning classification models, the proposed system differentiates genuine agricultural transactions from fraudulent activity. In addition to flagging suspicious records, the framework compiles regional, bank-level, and attack-vector summaries, providing practical data that can help cybercrime investigators and rural banking institutions protect agricultural livelihoods.
Keywords: Agricultural Cybercrime, Fraud Detection, Machine Learning, Digital Farming Security, Phishing Mitigation, Data Analytics, Pandas
Download/View Count: 1
Share this Article