[2063-2065]

Duplicate detection is a non-trivial task in which duplicates are not exactly equal due to error in the data and objects. The existing system uses a method called XMLDup. It considers only the XML data files to detect duplicate and non duplicate files. This method uses Bayesian network model to determine the probability of two XML elements being duplicate. It also uses network pruning algorithm to increase the BN evaluation time. This algorithm achieve high precision and recall scores in terms of both efficiency and effectiveness. In the proposed work aimed to extend the BN evaluation time using machine learning algorithm