Application of decision system design based on improved association rules in rural social security

The establishment of rural social security decision-making system is crucial for people's social welfare. The Spark algorithm is employed to filter and segment data to prune frequent pattern trees, optimize parameters, and improve grouping strategies and association rule mining algorithms. An intelligent decision system is designed for index factor and knowledge base management. The optimization method reduces data set resource consumption by approximately 50% and improves execution time, scalability, acceleration performance, and accuracy. The optimization algorithm solves issues of data randomness and uncertainty. This study offers technical support for the rural social security system and aims to improve it further. When support is at 40, 60 and 80%, the optimization algorithm performs well in all iterative processes, and when support is at 70%, the execution time of the optimization algorithm is significantly lower after the seventh iteration. The optimization algorithm solves the problems of randomness and uncertainty of data, improves the execution time, scalability, acceleration performance and accuracy. It realizes the establishment of intelligent decision-making system. This study provides technical support for the establishment of the rural social security system, hoping to further improve the rural social security system.