Mining Local And Peak High Utility Itemsets

In the era of big data and mobile computing,massive amounts of data are generated by businesses,governments and individuals,at every moment of the day.Discovering useful knowledge in this data can support decision making and is thus important and necessary.To facilitate the discovery of useful patterns in this data,numerous data mining techniques have been proposed.High Utility Itemset Mining(HUIM)is a promising research area of data mining,which consist of finding the sets of items that yield a high utility(e.g.profit)or have a high importance in a database.It is an important task with many applications.However,a major limitation of traditional HUIM algorithms is that they do not consider that the utility of itemsets may vary over time.Thus,traditional HUIM algorithms cannot find itemsets that do not yield a high utility when considering the whole database,but still have a high utility during specific time periods.Discovering such itemsets is useful for instance in market basket analysis,as a product may sell exceptionally well during specific time periods(e.g.Chinese new year)but not during the rest of the year.This thesis addresses this limitation of HUIM by defining the problem of mining local high utility itemsets(LHUI),and an extension to mine peak high utility itemsets(PHUI),which consists of finding the time periods where an itemset generates a utility that is considerably higher than usual.Two efficient algorithms named LHUI-Miner and PHUI-Miner are proposed to mine these patterns.Moreover,because the set of PHUIs can be large,a third algorithm named NPHUI-Miner is proposed to discover a smaller set of patterns called the Nonredundant Peak High Utility Itemsets(NPHUIs).Experimental results show that the proposed algorithms are efficient and can find useful patterns not found by traditional HUIM algorithms.