Data clustering is a process of putting similar data into groups. Point-based clustering aggregation is applying aggregation algorithms to data points and then combining various clustering results. Applying clustering algorithms to data points increases the computational complexity and decreases the accuracy. Many existing clustering aggregation algorithms have a time complexity quadratic, cubic, or even exponential in the number of data points. Thus Data fragments are considered. A Data fragment is any subset of the data that is not split by any of the clustering results. Existing model gives high clustering error rate due to lack of preprocessing of outliers. In the proposed approach, data fragments are considered and Outlier detection techniques are employed for preprocessing of data.