Efficient updating of discovered high-utility itemsets for transaction deletion in dynamic databases

Most algorithms related to association rule mining are designed to discover frequent itemsets from a binary database. Other factors such as profit, cost, or quantity are not concerned in binary databases. Utility mining was thus proposed to measure the utility values of purchased items for finding high-utility itemsets from a static database. In real-world applications, transactions are changed whether insertion or deletion in a dynamic database. An existing maintenance approach for handling high-utility itemsets in dynamic databases with transaction deletion must rescan the database when necessary. In this paper, an efficient algorithm, called PRE-HUI-DEL, for updating high-utility itemsets based on the pre-large concept for transaction deletion is proposed. The pre-large concept is used to partition transaction-weighted utilization itemsets into three sets with nine cases according to whether they have large (high), pre-large, or small transaction-weighted utilization in the original database and in the deleted transactions. Specific procedures are then applied to each case for maintaining and updating the discovered high-utility itemsets. Experimental results show that the proposed PRE-HUI-DEL algorithm outperforms a batch two-phase algorithm and a FUP2-based algorithm in maintaining high-utility itemsets.     

Fast and memory efficient mining of high-utility itemsets from data streams: with and without negative item profits

Mining utility itemsets from data steams is one of the most interesting research issues in data mining and knowledge discovery. In this paper, two efficient sliding window-based algorithms, MHUI-BIT (Mining High-Utility Itemsets based on BITvector) and MHUI-TID (Mining High-Utility Itemsets based on TIDlist), are proposed for mining high-utility itemsets from data streams. Based on the sliding window-based framework of the proposed approaches, two effective representations of item information, Bitvector and TIDlist, and a lexicographical tree-based summary data structure, LexTree-2HTU, are developed to improve the efficiency of discovering high-utility itemsets with positive profits from data streams. Experimental results show that the proposed algorithms outperform than the existing approaches for discovering high-utility itemsets from data streams over sliding windows. Beside, we also propose the adapted approaches of algorithms MHUI-BIT and MHUI-TID in order to handle the case when we are interested in mining utility itemsets with negative item profits. Experiments show that the variants of algorithms MHUI-BIT and MHUI-TID are efficient approaches for mining high-utility itemsets with negative item profits over stream transaction-sensitive sliding windows.     

一种基于后缀项表的并行闭频繁项集挖掘算法

对现有的基于MapReduce的并行频繁项集挖掘算法进行了研究, 提出一种基于后缀项表的并行闭频繁项集挖掘算法, 通过后缀项表的引入及以闭频繁项集挖掘的形式, 减少组分间的数据传送量, 提高挖掘效率。实验表明, 该算法可以有效缩短平均挖掘时间, 对于高维大数据具有较好的性能。     

Mining Maximal High Utility Itemsets on Dynamic Profit Databases

Abstract

To overcome the limitation of high-utility itemset mining, more compact, lossless, and concise representations of high utility itemsets (HUIs) have been proposed in previous works, such as closed HUIs (CHUIs) or maximal HUIs (MHUIs). Focusing into MHUI mining, in this article, we present efficient approaches to directly mine MHUIs from transactional databases without generating any candidates. The proposed algorithms, which all execute in one phase, utilize many efficient data structures and pruning techniques such as EUCP combined with EUCS, CUIP combined with FUCS, and the P-set structure to significantly reduce the search space and remove nonpromising itemsets, thus, increase the performance of the MHUI mining process. Furthermore, while previous works assumed that the unit profit of items is fixed, which is not practical in many real-world applications, our work resolved this issue by applying a new utility calculation into the mining process to reflect the true nature of real-world databases, thus, generating more accurate results.     

Updating high-utility pattern trees with transaction modification

Traditional association-rule mining only concerns the occurrence frequencies of the items in a binary database. In real-world applications, customers may buy several copies of the purchased items. Other factors such as profit, quantity, or price should be concerned to measure the utilities of the purchased items. High-utility itemsets mining was thus proposed to consider the factors of quantity and profit. Two-phase model was the most commonly way to keep the transaction-weighted utilization downward closure property, thus reducing the numerous candidates in utility mining. Most methods for finding high-utility itemsets are used to handle a static database. In practical applications, transactions are changed whether insertion, deletion, or modification. Some itemsets may arise as the new high-utility itemsets or become invalid knowledge in the updated database. In this paper, a maintenance Fast Updated High Utility Pattern tree for transaction MODification (FUP-HUP-tree-MOD) algorithm is thus proposed to effective maintain and update the built HUP tree for mining high-utility itemsets in dynamic databases without candidate generation. Experiments are conducted to show better performance of the proposed algorithm compared to the two-phase algorithm and the HUP tree algorithm in batch mode.     

HFIM: a Spark-based hybrid frequent itemset mining algorithm for big data processing

Frequent itemset mining is one of the data mining techniques applied to discover frequent patterns, used in prediction, association rule mining, classification, etc. Apriori algorithm is an iterative algorithm, which is used to find frequent itemsets from transactional dataset. It scans complete dataset in each iteration to generate the large frequent itemsets of different cardinality, which seems better for small data but not feasible for big data. The MapReduce framework provides the distributed environment to run the Apriori on big transactional data. However, MapReduce is not suitable for iterative process and declines the performance. We introduce a novel algorithm named Hybrid Frequent Itemset Mining (HFIM), which utilizes the vertical layout of dataset to solve the problem of scanning the dataset in each iteration. Vertical dataset carries information to find support of each itemsets. Moreover, we also include some enhancements to reduce number of candidate itemsets. The proposed algorithm is implemented over Spark framework, which incorporates the concept of resilient distributed datasets and performs in-memory processing to optimize the execution time of operation. We compare the performance of HFIM with another Spark-based implementation of Apriori algorithm for various datasets. Experimental results show that the HFIM performs better in terms of execution time and space consumption.     

Incrementally mining high utility patterns based on pre-large concept

In traditional association rule mining, most algorithms are designed to discover frequent itemsets from a binary database. Utility mining was thus proposed to measure the utility values of purchased items for revealing high utility itemsets from a quantitative database. In the past, a two-phase high utility mining algorithm was thus proposed for efficiently discovering high utility itemsets from a quantitative database. In dynamic data mining, transactions may be inserted, deleted, or modified from a database. In this case, a batch mining procedure must rescan the whole updated database to maintain the up-to-date information. Designing an efficient approach for handling dynamic databases is thus a critical research issue in utility mining. In this paper, an incremental mining algorithm is proposed for efficiently maintaining discovered high utility itemsets based on pre-large concepts. Itemsets are first partitioned into three parts according to whether they have large (high), pre-large, or small transaction-weighted utilization in the original database and in inserted transactions. Individual procedures are then executed for each part. Experimental results show that the proposed incremental high utility mining algorithm outperforms existing algorithms.     

基于DDMINER分布式数据库系统中频繁项目集的更新

给出了一种分布式数据挖掘系统的体系结构DDMINER，对分布式数据库系统中频繁项目集的更新问题进行探讨，既考虑了数据库中事务增加的情况，又考虑了事务删除的情况；提出了一种基于DDMINER的局部频繁项目集的更新算法ULF和全局频繁项目集的更新算法UGF．该算法能够产生较少数量的候选频繁项目集，在求解全局频繁项目集过程中，传送候选局部频繁项目集支持数的通信量为O(n)；将文章提出的算法用Java语言加以实现，并对算法性能进行了研究；实验结果表明这些算法是正确、可行的，并且具有较高的效率．     

时空轨迹大数据分布式蜂群模式挖掘算法

针对时空轨迹大数据的蜂群模式挖掘需求,提出了一种高效的基于MapReduce的分布式蜂群模式挖掘算法。首先,提出了基于最大移动目标集的对象集闭合蜂群模式概念,并利用最小时间支集优化了串行挖掘算法;其次,提出了蜂群模式的并行化挖掘模型,利用蜂群模式时间域无关性,并行化了聚类与子时间域上的蜂群模式挖掘过程;第三,设计了一个基于MapReduce链式架构的分布式并行挖掘算法,通过四个阶段快速地实现了蜂群模式的并行挖掘;最后,在Hadoop平台上,使用真实交通轨迹大数据集对分布式算法的有效性和高效性进行了验证与分析。     

CLAP: Collaborative pattern mining for distributed information systems

The purpose of data mining from distributed information systems is usually threefold: (1) identifying locally significant patterns in individual databases; (2) discovering emerging significant patterns after unifying distributed databases in a single view; and (3) finding patterns which follow special relationships across different data collections. While existing research has significantly advanced the techniques for mining local and global patterns (the first two goals), very little attempt has been made to discover patterns across distributed databases (the third goal). Moreover, no framework currently exists to support the mining of all three types of patterns. This paper proposes solutions to discover patterns from distributed databases. More specifically, we consider pattern mining as a query process where the purpose is to discover patterns from distributed databases with patterns' relationships satisfying user specified query constraints. We argue that existing self-contained mining frameworks are neither efficient, nor feasible to fulfill the objective, mainly because their pattern pruning is single-database oriented. To solve the problem, we advocate a cross-database pruning concept and propose a collaborative pattern (CLAP) mining framework with cross-database pruning mechanisms for distributed pattern mining. In CLAP, distributed databases collaboratively exchange pattern information between sites so that each site can leverage information from other sites to gain cross-database pruning. Experimental results show that CLAP fits a niche position, and demonstrate that CLAP not only outperforms its other peers with significant runtime performance gains, but also helps find patterns incapable of being discovered by others.     

Closed constrained gradient mining in retail databases

Incorporating constraints into frequent itemset mining not only improves data mining efficiency, but also leads to concise and meaningful results. In this paper, a framework for closed constrained gradient itemset mining in retail databases is proposed by introducing the concept of gradient constraint into closed itemset mining. A tailored version of CLOSET+, LCLOSET, is first briefly introduced, which is designed for efficient closed itemset mining from sparse databases. Then, a newly proposed weaker but antimonotone measure, top-X average measure, is proposed and can be adopted to prune search space effectively. Experiments show that a combination of LCLOSET and the top-X average pruning provides an efficient approach to mining frequent closed gradient itemsets.     

一种基于最大加权频繁项目集的数据库相似性判别算法

在引入最大加权频繁项目集之后，给出一种新的数据库相似性度量模型，并提出基于最大加权频繁项目集的数据库相似性度量算法．该算法可有效地改进基于最大频繁项目集的数据库相似性度量方法，提高数据库相似性度量准确性．在实际应用中，改进模型为分布多库环境下数据挖掘的数据准备提供有效的框架，因而具有重要的使用价值．     

A fast updated algorithm to maintain the discovered high-utility itemsets for transaction modification

High-utility itemsets mining (HUIM) is a critical issue which concerns not only the occurrence frequencies of itemsets in association-rule mining (ARM), but also the factors of quantity and profit in real-life applications. Many algorithms have been developed to efficiently mine high-utility itemsets (HUIs) from a static database. Discovered HUIs may become invalid or new HUIs may arise when transactions are inserted, deleted or modified. Existing approaches are required to re-process the updated database and re-mine HUIs each time, as previously discovered HUIs are not maintained. Previously, a pre-large concept was proposed to efficiently maintain and update the discovered information in ARM, which cannot be directly applied into HUIM. In this paper, a maintenance (PRE-HUI-MOD) algorithm with transaction modification based on a new pre-large strategy is presented to efficiently maintain and update the discovered HUIs. When the transactions are consequentially modified from the original database, the discovered information is divided into three parts with nine cases. A specific procedure is then performed to maintain and update the discovered information for each case. Based on the designed PRE-HUI-MOD algorithm, it is unnecessary to rescan original database until the accumulative total utility of the modified transactions achieves the designed safety bound, which can greatly reduce the computations of multiple database scans when compared to the batch-mode approaches.     

Utility-based association rule mining: A marketing solution for cross-selling

Recently, a utility-based mining approach has emerged as an alternative mechanism to frequency-based mining in an attempt to reflect not only the statistical correlation but also the semantic significance (e.g., price and quantity) of items. However, existing mining trajectories utilizing high-utility itemsets may not offer firms sufficient business insights unless they can precisely assess the value of association rules, which may vary substantially depending on many business parameters included in the assessment. In this study, we propose a utility-based association-rule mining method that valuates association rules by measuring their specific business benefits accruing to firms. Based on previous studies, three key elements (opportunity, effectiveness, and probability) are identified to define and operationalize a users’ preference as a utility function. To apply the utility-based mechanism to the processing of large transaction databases, we constructed functional algorithms, with heightened attention paid to their pruning strategies, and evaluated them based on real-world databases. Experimental results show that the proposed approach can provide users with greater business benefits than the high-utility itemset mining approach, suggesting several important strategic implications for both research and practice.     

Maintaining the discovered high-utility itemsets with transaction modification

Most approaches for discovering frequent itemsets derive association rules from a binary database. Profit, cost, and quantity are not considered in traditional association-rule mining. Utility mining was proposed to measure the utilities of purchase products to derive highutility itemsets (HUIs). Many algorithms have been proposed to efficiently find HUIs from a static database. In real-world applications, transactions are inserted, deleted, or modified in dynamic situations. Existing batch approaches have to re-process the updated database since previously discovered HUIs are not maintained. In this paper, a Fast UPdated (FUP) strategy with utility measure and a maintenance algorithm, called FUP-HUI-MOD, are developed to efficiently maintain and update discovered HUIs. When transactions are modified, the proposed algorithm partitions the transactions before and after the modification into two parts, creating four cases. Each case is maintained using a specific procedure to update the discovered HUIs. Based on the designed FUP-HUI-MOD algorithm, the original database is not required to be rescanned each time compared to the state-of-the-art high-utility itemset mining algorithms in batch mode. Experiments are conducted to show that the proposed algorithm outperforms batch algorithms in maintaining HUIs.     

快速挖掘全局最大频繁项目集

挖掘最大频繁项目集是多种数据挖掘应用中的关键问题.现行可用的最大频繁项目集挖掘算法大多基于单机环境,针对分布式环境下的全局最大频繁项目集挖掘尚不多见.若将基于单机环境的最大频繁项目集挖掘算法运用于分布式环境,或运用分布式环境下的全局频繁项目集挖掘算法来挖掘全局最大频繁项目集,均会产生大量的候选频繁项目集,且网络通信代价高.为此,提出了快速挖掘全局最大频繁项目集算法FMGMFI(fast mining global maximum frequent itemsets),该算法采用FP-tree存储结构,可方便地从各局部FP-tree的相关路径中得到项目集的频度,同时采用自顶向下和自底向上的双向搜索策略,可有效地降低网络通信代价.实验结果表明,FMGMF算法是有效、可行的.     

A security framework in G-Hadoop for big data computing across distributed Cloud data centres

MapReduce is regarded as an adequate programming model for large-scale data-intensive applications. The Hadoop framework is a well-known MapReduce implementation that runs the MapReduce tasks on a cluster system. G-Hadoop is an extension of the Hadoop MapReduce framework with the functionality of allowing the MapReduce tasks to run on multiple clusters. However, G-Hadoop simply reuses the user authentication and job submission mechanism of Hadoop, which is designed for a single cluster. This work proposes a new security model for G-Hadoop. The security model is based on several security solutions such as public key cryptography and the SSL protocol, and is dedicatedly designed for distributed environments. This security framework simplifies the users authentication and job submission process of the current G-Hadoop implementation with a single-sign-on approach. In addition, the designed security framework provides a number of different security mechanisms to protect the G-Hadoop system from traditional attacks.     

A fast high average-utility itemset mining with efficient tighter upper bounds and novel list structure

High-utility itemset mining is a prominent data-mining technique where the profit or weight of itemsets plays a crucial role in defining meaningful patterns. High average-utility itemset (HAUI) mining is an advancement over high-utility itemset mining, which introduces an unbiased measure called average utility to associate the utility of itemsets with their length. Several existing HAUI mining algorithms use various upper bounds such as average-utility upper bound, revised tighter upper bound, and looser upper bound to preserve pruning methods. However, these upper bounds overestimate the average-utility of itemsets and slow down the mining process. This paper presents a fast high average-utility itemset miner (FHAIM) algorithm, which uses two improved upper bounds and several efficient pruning strategies to avoid the processing of unpromising candidate itemsets. Moreover, a novel list structure named recommended average-utility list (RAUL) is presented to store the average-utility and the required information for pruning. The RAUL for an itemset can be constructed by joining the RAULs of its subsets to avoid excessive database scans. We have performed substantial experiments on various benchmark datasets to evaluate the performance of the FHAIM in comparison with two existing HAUI mining algorithms. Experimental results show that FHAIM outperforms the existing HAUI mining algorithms in terms of runtime, memory usage, join counts, and scalability.

     

OHUQI: Mining on-shelf high-utility quantitative itemsets

Mobile edge computing has brought fresh opportunities and challenges to data science. Utility-driven mining, a recently emerging branch of utility-based data science, has been widely applied because it considers both the utility factor and the quantity characteristic with ranges of patterns. However, most existing utility-mining algorithms assume that patterns always appear regardless of the period. For instance, some products may sell well at certain times of the year. Considering the rich information in the database, such as quantity and time, we propose an effective and efficient approach, namely OHUQI, for discovering on-shelf high-utility quantitative itemsets. To avoid scanning the database multiple times, we adopt a data structure to maintain some necessary information, and thus OHUQI only accesses the database twice. Several pruning strategies are also designed to prune a large number of unpromising itemsets in advance to shrink the search space. Finally, the subsequent experimental results show that OHUQI performs well on several real-world datasets.

     

最小支持度变化时分布式数据库中频繁项目集更新

讨论分布式数据库系统中最小支持度变化时频繁项目集如何高效更新问题，提出了一种基于最小支持度变化的局部频繁项目集的更新算法ULFS和全局频繁项目集的更新算法UGFS．该算法能够充分利用已挖掘的结果．并且产生较少数量的候选频繁项目集，在求解全局频繁项目集过程中．候选局部频繁项目集支持数的通信量为O(n)．将文章提出的算法用Java加以实现．并时算法性能进行了研究．实验结果表明这些算法是可行、有效的．并且具有较快的速度．