Simulation Optimization of Data Mining Model Based on Fuzzy Improved Clustering Algorithm

The goal of data mining (DM) is to find some important patterns and trends from the complicated data. How to select useful information quickly, efficiently and accurately from the vast amount of data has become an urgent problem. Clustering algorithm refers to the algorithm process of grouping a large quantity of data objects with similarity and proximity, so as to cluster approximate data information and facilitate DM calculation. This paper mainly studies the fuzzy improved clustering algorithm of DM model in big data and analyzes the incremental fuzzy clustering algorithm (FCA) of DM model in big data. The experimental results show that the accuracy of data mining model will be improved when the quantity of samples reaches a certain level. Compared with the traditional K-Means algorithm, the accuracy of this algorithm has obvious advantages, up to 97.88%. The method in this paper not only has good prediction ability, but also provides a more concise rule base, which provides a better tool for analyzing the nature of the problem and discovering the hidden knowledge in the data.