Weak ratio rules between nonnegative real-valued data in transactional database

This paper deals with the problem of weak ratio rules between nonnegative real-valued data in transactional database. Such weak ratio rule is a weaker form than Flip Korn's ratio rule and has such a reasoning meaning that if the dollar amounts spent by a customer on bread are 2, then the dollar amounts spent by the customer on butter is at least 3. Through discussing the mathematical model of weak ratio rules problem, we come to that the weak ratio rules problem is a generalization of Boolean association rules problem and every weak ratio rule is supported by a Boolean association rule. We propose an algorithm for mining an important subset of weak ratio rules and construct a weak ratio rule uncertainty reasoning model. Finally an example is given to show how to apply weak ratio rules to reconstructing lost data, forecasting and outlier detection.