Mining Association Rules in a Transactional Database Using the Lift Ratio

Association rule is a method for discovering interesting relationships between the items in large databases. For analyzing the students’ behaviour, the systems accumulate a large volume of valuable information. Since the student database includes more number of attributes it is difficult for processing. The goal of the Multidimensional Quantitative Rule Generation is to generate association rules that satisfy the minimum confidence threshold. But in some cases measuring confidence alone is not sufficient for decision making. Therefore, the Confidence measure for continuous data can be derived that agrees with the standard confidence measure while applying to binary data also. Besides we have taken one more add-on factor `Lift Ratio' which is to validate the generated Association rules that are strong enough to infer useful information. This proposed approach aims to put together the above points to generate an efficient algorithm to offer useful rules in an effective manner.