MINING SEQUENTIAL RULES FROM UNCERTAIN SEQUENCES DATABASE

Abstract

Since the amount of data has become a vital fuel to powering many real-world applications, many issues arise in data mining regarding storage and real-time aspects. Indeed, mining association rules is one of the strategies used to find associations and relationship rules among large sets of data items. However, this data does not always have precise values due to the fact that it may be either incomplete or uncertain, which is a challenging problem when applying mining algorithms. To deal with these issues, we propose a new approach for mining sequential rules from uncertain sequence databases that consists of two main steps: The first one is to extract the set of probabilistic rules, and the second one is to filter this set using the sequential information in the data.