Sequential Pattern Mining Research Paper

2 Sequential pattern mining

Mining useful information and helpful knowledge from large databases has evolved into an important research area. Sequential pattern mining is the mining of fre- quently occurring ordered events or sub sequences as patterns [2]. Example : \Cus- tomers who buy a Panasonic digital camera are likely to buy an Brother color printer within few days." For retail data, sequential patterns are useful for shelf placement and promotions [1]. Sequential patterns is used by number of industries, dierent business, telecommunication etc. for targeted marketing, customer retention, and many other tasks. Sequential patterns can be applied in other areas include Web access pattern analysis, prediction of weather, production processes, and network intrusion detection.

A sequence with length l is called an l-sequence. A sequence = ha1a2a3:::::::ani is called a subsequence of another sequence  = hb1b2b3:::::::bmi and is a super sequence of  denoted as a  v  if there exist integers 1

 j1 < j2 < j3::::: < jm  m such that a1  bj1; a2  bj2::::::an  bjn.

Dept. of Computer Engg. 2 DYPCOE, Akurdi, Pune

Business Intelligence and Data Mining Pattern Mining

If  = h(ab); di and  = h(abc); (de)i; where a, b, c, d, and e are items, then is a sub sequence of  and  is a super sequence of : A sequence database,

S, is a set of tuples, hSID; si where SID is a sequence ID and s is a sequence.

Customer Sequence : List of customer transactions ordered by increasing trans- action time. A Customer support a sequence if the sequence is contained in the customer-sequence Support for sequence : Fraction of Total Customers that sup- ports a sequence. Maximal Sequence : A sequence that is not contained in any other sequence Large sequence : Sequence that meets mini-support [1].

2.1 Example

Consider the sequence database, S, given in Figure 2.1. Let min sup = 2. The set of items in the database is a, b, c, d, e, f , g. The database contains four