Record deduplication[1] is the task of identifying, in a data storage, records that refer to the same real entity or any object in spite of spelling mistakes, typing errors, different writing styles or even different schema representations or data types. In the existing system aims at providing Unsupervised Duplication Detection method which can be used to identify and remove the duplicate records from different data storge. UDD, which for a given query, can effectively identify duplicates from the query result records of different web databases. After removing the same source duplicates, the supposed” non duplicate records from the same data storage can be used as training examples alleviating the trouble of users having to manually labeled training examples. Starting from the non duplicate reocord set, the two different classifiers, a Weighted Component Similarity Summing Classifier (WCSS) is used to knowing the duplicate records from the non duplicate record and presently a genetic programming (GP) approach to record deduplication. The approach joins several different pieces of attribute with similarity function extracted from the data content to produce a deduplication function that is able to identify whether two or more entries in a repository are replicas or not. Since record deduplication is a time taking task even for small repositories, the aim is to foster a method that finds a proper combination of the proper pieces of attribute with similarity function, thus yielding a deduplication function that maximizes performance using a small representative portion of the corresponding data for training purposes. But the optimization of result is less . The proposed system has to develop new method, modified bat algorithm for record duplication. The aim behind is to create a flexible and effective method that uses Data Mining algorithms. The system shares many similarities function with generational computation techniques such as Genetic programming approach