NTP-Miner: Nonoverlapping Three-Way Sequential Pattern Mining

Abstract

Nonoverlapping sequential pattern mining is an important type of sequential pattern mining (SPM) with gap constraints, which not only can reveal interesting patterns to users but also can effectively reduce the search space using the Apriori (anti-monotonicity) property. However, the existing algorithms do not focus on attributes of interest to users, meaning that existing methods may discover many frequent patterns that are redundant. To solve this problem, this article proposes a task called nonoverlapping three-way sequential pattern (NTP) mining, where attributes are categorized according to three levels of interest: strong, medium, and weak interest. NTP mining can effectively avoid mining redundant patterns since the NTPs are composed of strong and medium interest items. Moreover, NTPs can avoid serious deviations (the occurrence is significantly different from its pattern) since gap constraints cannot match with strong interest patterns. To mine NTPs, an effective algorithm is put forward, called NTP-Miner, which applies two main steps: support (frequency occurrence) calculation and candidate pattern generation. To calculate the support of an NTP, depth-first and backtracking strategies are adopted, which do not require creating a whole Nettree structure, meaning that many redundant nodes and parent–child relationships do not need to be created. Hence, time and space efficiency is improved. To generate candidate patterns while reducing their number, NTP-Miner employs a pattern join strategy and only mines patterns of strong and medium interest. Experimental results on stock market and protein datasets show that NTP-Miner not only is more efficient than other competitive approaches but can also help users find more valuable patterns. More importantly, NTP mining has achieved better performance than other competitive methods in clustering tasks. Algorithms and data are available at: https://github.com/wuc567/Pattern-Mining/tree/master/NTP-Miner .

OPP-Miner: Order-preserving sequential pattern mining

“…However, this assumption cannot be applied to all situations. Thus, many types of patterns and mining methods have been proposed, such as tri-pattern mining [28], [29], high utility pattern mining [30], contrast pattern mining [31], rare pattern mining [32] and co-location pattern mining [33]. Furthermore, sequential pattern mining refers to discovering information from sequential data.…”

One-off Negative Sequential Pattern Mining

“…To compress frequent patterns, Top-k SPM (28,29), closed SPM (30), and maximal SPM (31,32) were investigated. With the development of SPM, various SPM methods have been investigated for different mining tasks, such as three-way SPM (33,34), weak-gap SPM (35,36), high utility SPM (37,38), spatial co-location pattern mining (11), order-preserving SPM (16), and contrast SPM (12,14). For example, threeway SPM can effectively improve the mining speed and avoid large deviations by dividing the characters into three types: strong, medium, and weak.…”

US-Rule: Discovering Utility-driven Sequential Rules

“…Since Agrawal and Srikant [1] proposed the sequential pattern mining (SPM) to discover all frequent sequential patterns, a growing number of researchers are focusing on this area. There are many algorithms about SPM [11,16], such as GSP [26], PrefixSpan [19], SPADE [35], SPAM [5], and non-overlapping SPM [33]. GSP is a relatively violent method that generates longer sequential patterns by continuously merging sub-sequential patterns.…”