Optimizated K-means algorithm and application in CRM system

So far, the K-means algorithm is the most widely used method for discovering clusters in data, and it has been used extensively in the commercial field, such as customer analysis. However, the efficiency of the algorithm needs to be improved when faced with large amounts of data. The improved algorithm avoids unnecessary calculations by using the triangle inequality. We applies the improved algorithm for customer classification. Experiments show that the optimizated algorithm take lower time overhead than the standard K-means algorithm, and the superiority of proposed method is more remarkable as the number of clusters increases.