HANDLING PARTIAL INFORMATION IN RELATIONAL DATABASE

Most real-world databases have at least some missing data. Today, users of such databases are “on their own� in terms of how they manage the incompleteness. The existing system deals with the general concept of partial information policy (PIP) operator to handle incompleteness in relational databases. PIP operators build upon preference frameworks for incomplete information, but accommodate different types of incomplete data (e.g., a value exists but is not known; a value does not exist; a value may or may not exist). Different users in the real world have different ways to handle incompleteness - PIP operators allow them to specify a policy that matches their attitude to risk and their knowledge of the application and how the data was collected. It results in longer time for updating and incompleteness cannot be eliminated completely. The proposed system with the help of Expectation Maximization Algorithm and Multiple Imputation Algorithms eliminates the incompleteness and predicts the missing values without the user interaction by relating the missing attributes with the supporting tables. The proposed method is evaluated with a large particular database and the result demonstrates that the proposed approach is better than the existing algorithms and root mean square error (RMSE) at different missing ratios.