Abstract
This study explored the integration of artificial intelligence with blockchain technology to analyze and predict electoral activity in blockchain voting systems. The aim was to enhance the efficiency, transparency, and security of electronic voting by leveraging artificial intelligence 's predictive capabilities. The research focused on the application of machine learning algorithms to detect voting patterns, identify anomalies, and forecast voter turnout. By utilizing a combination of historical voting data and real-time blockchain records, the study demonstrated how artificial intelligence could provide valuable insights into voter behavior and election trends. The methodology included the use of an artificial intelligence model implemented on blockchain technology, the creation of synthetic data sets, data pre-processing, engineering functions and linear regression methods, machine learning models using random variables and neural networks. Model performance was evaluated using Mean Squared Error and R² Score. The implementation of artificial intelligence in blockchain voting systems was evaluated through a series of experimental simulations, highlighting the accuracy and reliability of predictions. The findings indicated that artificial intelligence -driven analysis could significantly improve the management and oversight of electronic elections, contributing to more robust and trustworthy voting processes. This paper presented a comprehensive methodology, discussed the results, and offered recommendations for future research and practical applications in the field of electoral technology.