DEVELOPMENT OF A DECENTRALIZED VOTING SYSTEM UTILIZING BLOCKCHAIN AND MACHINE LEARNING

Abstract

This paper presents the conceptual framework and development strategy for a decentralized voting system that integrates blockchain technology with machine learning (ML). While blockchain serves as a transparent and immutable ledger ensuring the integrity of cast votes, machine learning algorithms are utilized to provide a proactive security layer for anomaly detection. The study addresses critical challenges in electronic governance, such as identity theft, Sybil attacks, and coercive voting patterns. By applying ML models to analyze transaction behaviors and network metadata, the system can distinguish between legitimate human participation and automated malicious activities. The findings suggest that a hybrid approach significantly enhances the reliability and security of digital democratic processes