Temporal Association Rule Mining in Large Databases

Over the last couple of years, data mining technology has been successfully employed to various business domains and scientific areas. One of the main unresolved problems that arise during the data mining process is treating data that contains temporal information. A thorough understanding of this concept requires that the data should be viewed as a sequence of events. Temporal sequences exist extensively in different areas that include economics, finance, communication, engineering, medicine, weather forecast and so on. This chapter proposes a technique that is developed to explore frequent temporal itemsets in the database. The basic idea of this technique is to first partition the database into sub-databases in light of either common starting time or common ending time. Then for each partition, the proposed technique is used progressively to accumulate the number of occurrences of each candidate 2-itemsets. A Directed graph is built using the support of these candidate 2-itemsets (combined from all the sub-databases) as a result of generating all candidate temporal k- itemsets in the database. The above technique may help researchers not only to understand about generating frequent large temporal itemsets but also helps in understanding of finding temporal association rules among transactions within relational databases.