PrefixSpan,: mining sequential patterns efficiently by prefix-projected pattern growth

By Jian Pei, Jiawei Han, Behzad Mortazavi-Asl, Helen Pinto, Qiming Chen, Umeshwar Dayal, Meichun Hsu. Proceedings / International Conference on Data Engineering, 2001

2,240 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics, Information Systems

View Paper: https://www.semanticscholar.org/paper/de20b12ebf9fe5c4c74a7bb75239e0b45c587b1f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computational Theory and Mathematics

In Information Systems

Citations in the corpus

H-mine: hyper-structure mining of frequent patterns in large databases (2001, background): “Its structure- and space-preserving mining methodology may have strong impact on the development of new, efficient and scalable data mining methods for mining other kinds of patterns, such as closed-itemsets [11], max-patterns [4], sequential patterns [14, 12 ], constraintbased mining [9, 10], etc.”
Activity Recognition on Streaming Sensor Data (2012, background): “There are also a number of unsupervised activity discovery methods that mine for frequent sensor sequences [35], or discontinuous activity patterns [36].”
BIDE: efficient mining of frequent closed sequences (2004, methodology): “general sequential pattern mining [13, 20, 9, 24, 17, 4], constraint-based sequential pattern mining [6, 18, 19], frequent episode mining [12], cyclic association rule mining [14], temporal relation mining [5], partial periodic pattern mining [7], and long sequential pattern mining in noisy environm”
Modelling input texts: from Tree Kernels to Deep Learning (2015, methodology): “The authors suggest that a similar method to the PrefixSpan algorithm [111] can be applied to tree kernels.”
Semantic trajectory mining for location prediction (2011, methodology): “However, it is clear to observe that the longer pattern we mine the more subsequences will be generated due to the downward closure property [10].”
Discriminative Frequent Pattern Analysis for Effective Classification (2007, background): “Frequent pattern mining has been a focused theme in data mining research with a large number of scalable methods proposed for mining various kinds of patterns including itemsets [2, 10, 27], sequences [3, 16, 26] and graphs [11, 22].”
Parameter-Free Probabilistic API Mining at GitHub Scale (2015, methodology): “The PrefixSpan algorithm [25] mines frequent sequences using the pattern-growth approach: growing a prefix pattern to”
Trajectory Data Mining (2015, methodology): “After the transformation, we can mine the sequential patterns from these sequences by using existing sequential pattern mining algorithms such as PreﬁxSpan [Pei et al. 2011] and CloseSpan [Yan et al. 2003], with time constraints.”
USpan: an efficient algorithm for mining high utility sequential patterns (2012, methodology): “Under this framework, the downward closure property (also known as Apriori property) [1] plays a fundamental role for varieties of algorithms designed to search for frequent sequential patterns [10, 14, 5].”
Parameter-free probabilistic API mining across GitHub (2015, methodology): “The problem was first introduced by Agrawal and Srikant [5] in the context of market basket analysis, which led to a number of other algorithms for frequent sequence mining, including GSP [35], PrefixSpan [29], SPADE [43] and SPAM [8].”
A survey of frequent subgraph mining algorithms (2012, methodology): “Chopper first uses a revised PrefixSpan (Pei et al. 2001) to mine frequent sequential patterns.”
A taxonomy of sequential pattern mining algorithms (2010, methodology): “Experimental re-sults show that for disk-based processing, it is better to use bilevel projection, while for main memory processing using pseudo-projection gives a better performance [Pei et al. 2001].”
Foundations and Advances in Data Mining (2005, background): “Of course, RKHS had been pioneered by Parzen and Wahba ([37, 53]) for applications closely related to learning, including data smoothing (for image processing and computer vision, see [4, 42]).”