Clustering, a type of unsupervised learning, is a big challenge in machine learning. Current understanding and practical use of clustering are basic. The main problem is choosing the right clustering model. Different algorithms can give very different results, so picking the right one is crucial. But there's no clear way to choose the best algorithm for a specific task. Many practitioners don't consider the impact of their choices. Most theory papers focus on saving resources, not on matching clustering goals with outcomes. This gap needs to be addressed to improve clustering results.