Abstract :

The Rapid Advancement Of Blockchain Networks And Digital Transaction Platforms Has Increased The Demand For Intelligent And Reliable Fraud Detection Mechanisms, Particularly In Decentralized Environments Such As Ethereum. Traditional Verification Approaches, Which Rely On Manual Inspection And Rule-based Systems, Are Inadequate For Processing Large-scale And Complex Transactional Data, Leading To Inefficiencies, Low Accuracy, And Poor Adaptability To Evolving Fraud Patterns. To Overcome These Challenges, This Research Proposes A Hybrid Fraud Detection Framework That Integrates Multiple Machine Learning (ML) Techniques, Including Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF), Extreme Gradient Boosting (XGBoost), And Light Gradient Boosting Model (LGBM), Along With A Deep Learning (DL)-based Convolutional Neural Network (CNN2D). Feature Selection Is Performed Using Analysis Of Variance (ANOVA), And Normalization Techniques Are Applied To Enhance Model Performance And Stability. All Models Are Developed And Evaluated In A Jupyter Environment, Where CNN2D Demonstrates Superior Performance And Is Selected For Deployment. The System Is Implemented Using The Django Framework, Providing Role-based Access Where Buyers Can Register, Authenticate, And Upload Land Transaction Data, While Sellers Can Review And Approve Or Reject Requests Based On Artificial Intelligence (AI)-driven Fraud Predictions. The Deployed CNN2D Model Enables Real-time Prediction Of Fraudulent Activities. Furthermore, Transaction Data Is Stored In The InterPlanetary File System (IPFS), Generating Unique Hash Values, While Transaction Records And Prediction Outcomes Are Securely Recorded On The Ethereum Blockchain Using Smart Contracts (SC), Ensuring Immutability, Transparency, And Traceability. The Proposed Framework Enhances Fraud Detection Accuracy, Ensures Secure Data Storage, And Provides A Scalable And Trustworthy Solution For Digital Land Transaction Systems.

Published:

24-4-1-2026

Issue:

Vol. 26 No. 4-1 (2026)

Page Nos:

781-789

Section:

Articles

License:

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

How to Cite