Research on Interpretable Confidence Rule Base Modeling Method Integrating Data-Driven and Constrained K-Means Optimization

With the advancement of data science and machine learning technologies, many industries have adopted data-driven modeling techniques. This study designed an interpretable confidence rule base (BRB) model based on data-driven and constrained K-means algorithm optimization. This technique combines the strengths of the K-means clustering algorithm and the BRB model. Based on cluster analysis results, this method automatically generates rules and maintains consistency between rules and data during BRB inference. The data used in this experiment is a US crime rate dataset. Using K-means clustering, state-level security levels are classified to form an interpretable BRB rule set. The research data shows that this method significantly improves rule interpretability and model accuracy. This method performs well in processing complex multidimensional data. This research brings innovative research concepts and implementation methods to the fields of intelligent decision-making systems, risk assessment, and social security.