Analysis Model of Efficiency and Accuracy in Big Data Based on Clustering Algorithm K-means

With the continuous growth of big data, traditional data processing and analysis methods have faced great challenges. The K-means algorithm, as a classic representative of clustering technology, is of great significance for processing these large-scale datasets. This article delves into the efficiency and accuracy of K-means based clustering algorithms in big data environments. Firstly, we introduced the core principles and mathematical foundations of the K-means algorithm. Then, the main challenges of the algorithm in the big data environment were discussed in detail, such as computational complexity, randomness of initial center point selection, and convergence speed. To address these challenges, this article proposes a series of optimization strategies and verifies their effectiveness through experimental evaluation. The research results show that the improved algorithm has relatively stable final results and higher accuracy than traditional methods, with accuracy rates of 86.21% and 73.09%, respectively. This confirms that the improved algorithm is effective, with a more stable level of results and better results. These studies provide strong theoretical support and practical guidance for the further application of K-means in big data analysis.