Analysis of Web Access Sequence Based on the Improved Prefix Span Algorithm

PrefixSpan is an important algorithm for sequential pattern mining algorithm, but it's projected database cost more redundant memory and scan-time, so this paper present an improved PrefixSpan algorithm(IPS) which is based on PrefixSpan. IPS decreases the redundant memory and scan-time by abnegating the non-frequent items and projection database which sequential number is lower than minimum support. This paper applied IPS to web access sequence mining, by mining the web access records database to find frequent access sequence to provide reasonable suggestions for Web building. ' ' 2 ' 1 , , m