Showing papers on "Apriori algorithm published in 2003"

Mining high utility itemsets

Abstract: Traditional association rule mining algorithms only generate a large number of highly frequent rules, but these rules do not provide useful answers for what the high utility rules are. We develop a novel idea of top-K objective-directed data mining, which focuses on mining the top-K high utility closed patterns that directly support a given business objective. To association mining, we add the concept of utility to capture highly desirable statistical patterns and present a level-wise item-set mining algorithm. With both positive and negative utilities, the antimonotone pruning strategy in Apriori algorithm no longer holds. In response, we develop a new pruning strategy based on utilities that allow pruning of low utility itemsets to be done by means of a weaker but antimonotonic condition. Our experimental results show that our algorithm does not require a user specified minimum utility and hence is effective in practice.

Complete Mining of Frequent Patterns from Graphs: Mining Graph Data

Abstract: Basket Analysis, which is a standard method for data mining, derives frequent itemsets from database However, its mining ability is limited to transaction data consisting of items In reality, there are many applications where data are described in a more structural way, eg chemical compounds and Web browsing history There are a few approaches that can discover characteristic patterns from graph-structured data in the field of machine learning However, almost all of them are not suitable for such applications that require a complete search for all frequent subgraph patterns in the data In this paper, we propose a novel principle and its algorithm that derive the characteristic patterns which frequently appear in graph-structured data Our algorithm can derive all frequent induced subgraphs from both directed and undirected graph structured data having loops (including self-loops) with labeled or unlabeled nodes and links Its performance is evaluated through the applications to Web browsing pattern analysis and chemical carcinogenesis analysis

A fast apriori implementation

Abstract: The efficiency of frequent itemset mining algorithms is determined mainly by three factors: the way candidates are generated, the data structure that is used and the implementation details. Most papers focus on the first factor, some describe the underlying data structures, but implementation details are almost always neglected. In this paper we show that the effect of implementation can be more important than the selection of the algorithm. Ideas that seem to be quite promising, may turn out to be ineffective if we descend to the implementation level. We theoretically and experimentally analyze APRIORI which is the most established algorithm for frequent itemset mining. Several implementations of the algorithm have been put forward in the last decade. Although they are implementations of the very same algorithm, they display large differences in running time and memory need. In this paper we describe an implementation of APRIORI that outperforms all implementations known to us. We analyze, theoretically and experimentally, the principal data structure of our solution. This data structure is the main factor in the efficiency of our implementation. Moreover, we present a simple modification of APRIORI that appears to be faster than the original algorithm.

Discovering all most specific sentences

Abstract: Data mining can be viewed, in many instances, as the task of computing a representation of a theory of a model or a database, in particular by finding a set of maximally specific sentences satisfying some property. We prove some hardness results that rule out simple approaches to solving the problem.The a priori algorithm is an algorithm that has been successfully applied to many instances of the problem. We analyze this algorithm, and prove that is optimal when the maximally specific sentences are "small". We also point out its limitations.We then present a new algorithm, the Dualize and Advance algorithm, and prove worst-case complexity bounds that are favorable in the general case. Our results use the concept of hypergraph transversals. Our analysis shows that the a priori algorithm can solve the problem of enumerating the transversals of a hypergraph, improving on previously known results in a special case. On the other hand, using results for the general case of the hypergraph transversal enumeration problem, we can show that the Dualize and Advance algorithm has worst-case running time that is sub-exponential to the output size (i.e., the number of maximally specific sentences).We further show that the problem of finding maximally specific sentences is closely related to the problem of exact learning with membership queries studied in computational learning theory.

Discovering calendar-based temporal association rules

Abstract: We study the problem of mining association rules and related time intervals, where an association rule holds either in all or some of the intervals. To restrict to meaningful time intervals, we use calendar schemas and their calendar-based patterns. A calendar schema example is (year, month, day) and a calendar-based pattern within the schema is (*, 3, 15), which represents the set of time intervals each corresponding to the 15th day of a March. Our focus is finding efficient algorithms for this mining problem by extending the well-known Apriori algorithm with effective pruning techniques. We evaluate our techniques via experiments.

Discovering time-interval sequential patterns in sequence databases

Abstract: Sequential pattern mining, which discovers frequent subsequences as patterns in a sequence database, in an important data-mining problem with broad applications. Although conventional sequential patterns can reveal the order of items, the time between items is not determined; that is, a sequential pattern does not include time intervals between successive items. Accordingly, this work addresses sequential patterns that include time intervals, called time-interval sequential patterns. This work develops two efficient algorithms for mining time-interval sequential patterns. The first algorithm is based on the conventional Apriori algorithm, while the second one is based on the PrefixSpan algorithm. The latter algorithm outperforms the former, not only in computing time but also in scalability with respect to various parameters.

Pushing support constraints into association rules mining

Abstract: Interesting patterns often occur at varied levels of support. The classic association mining based on a uniform minimum support, such as Apriori, either misses interesting patterns of low support or suffers from the bottleneck of itemset generation caused by a low minimum support. A better solution lies in exploiting support constraints, which specify what minimum support is required for what itemsets, so that only the necessary itemsets are generated. We present a framework of frequent itemset mining in the presence of support constraints. Our approach is to "push" support constraints into the Apriori itemset generation so that the "best" minimum support is determined for each itemset at runtime to preserve the essence of Apriori. This strategy is called Adaptive Apriori. Experiments show that Adapative Apriori is highly effective in dealing with the bottleneck of itemset generation.

ExAMiner: optimized level-wise frequent pattern mining with monotone constraints

Abstract: The key point is that, in frequent pattern mining, the most appropriate way of exploiting monotone constraints in conjunction with frequency is to use them in order to reduce the problem input together with the search space. Following this intuition, we introduce ExAMiner, a level-wise algorithm which exploits the real synergy of antimonotone and monotone constraints: the total benefit is greater than the sum of the two individual benefits. ExAMiner generalizes the basic idea of the preprocessing algorithm ExAnte [F. Bonchi et al., (2003)], embedding such ideas at all levels of an Apriori-like computation. The resulting algorithm is the generalization of the Apriori algorithm when a conjunction of monotone constraints is conjoined to the frequency antimonotone constraint. Experimental results confirm that this is, so far, the most efficient way of attacking the computational problem in analysis.

Algorithms for association rules

Abstract: Association rules are "if-then rules" with two measures which quantify the support and confidence of the rule for a given data set. Having their origin in market basked analysis, association rules are now one of the most popular tools in data mining. This popularity is to a large part due to the availability of efficient algorithms following from the development of the Apriori algorithm.We will review the basic Apriori algorithm and discuss variants for distributed data, inclusion of constraints and data taxonomies. The review ends with an outlook on tools which have the potential to deal with long itemsets and considerably reduce the amount of (uninteresting) itemsets returned. The discussion will focus on the problem of finding frequent itemsets.

CT-ITL: efficient frequent item set mining using a compressed prefix tree with pattern growth

Abstract: Discovering association rules that identify relationships among sets of items is an important problem in data mining. Finding frequent item sets is computationally the most expensive step in association rule discovery and therefore it has attracted significant research attention. In this paper, we present a more efficient algorithm for mining complete sets of frequent item sets. In designing our algorithm, we have modified and synthesized a number of useful ideas that include prefix trees, pattern-growth, and tid-intersection. We extend the prefix-tree structure to store transaction groups and propose a new method to compress the tree. Transaction-id intersection is modified to include the count of transaction groups. We present performance comparisons of our algorithm against the fastest Apriori algorithm, Eclat and the latest extension of FP-Growth known as OpportuneProject. To study the trade-offs in compressing transactions in the prefix tree, we compare the performance of our algorithm with and without using the modified compressed prefix tree. We have tested all the algorithms using several widely used test datasets. The performance study shows that the new algorithm significantly reduces the processing time for mining frequent item sets from dense data sets that contain relatively long patterns. We discuss the performance results in detail and also the strengths and limitations of our algorithm.

Complexity analysis of depth first and FP-growth implementations of APRIORI

Abstract: We examine the complexity of Depth First and FP-growth implementations of Apriori, two of the fastest known data mining algorithms to find frequent itemsets in large databases. We describe the algorithms in a similar style, derive theoretical formulas, and provide experiments on both synthetic and real life data to illustrate the theory.

A fast association rule algorithm based on bitmap and granular computing

Abstract: Mining association rules from databases is a time-consuming process. Finding the large item set fast is the crucial step in the association rule algorithm. In this paper we present a fast association rule algorithm (Bit-AssoRule) based on granular computing. Our Bit-AssocRule doesn't follow the generation-and-test strategy of Apriori algorithm and adopts the divide-and-conquer strategy, thus avoids the time-consuming table scan to rind and prune the itemsets, all the operations of finding large itemsets from the datasets are the fast bit operations based on its corresponding granular. The experimental result of our Bit-AssocRule algorithm with Apriori, AprioriTid and AprioirHybrid algorithms shows Bit-AssocRule is 2 to 3 orders of magnitudes faster. Our research indicates that bitmap and granular computing can greatly improve the performance of association rule algorithm, and are very promising for data mining applications.

Fast algorithm for mining multilevel association rules

Abstract: We present two algorithms, AprioriNewMulti and AprioriNewSingle, for data mining multilevel and single level association rules, respectively, in large databases. The database consists of following fields, transaction ID and items purchased in the transaction. The algorithms introduce a new concept called multi minimum support i.e. minimum support varying for different lengths of the item set. Unlike other algorithms, AprioriNewMulti does not depend on the number of levels in the concept hierarchy, i.e., it does not scan the database for each level of abstraction for finding association rules. Scale up experiments show that both of these algorithms have scale linear with the number of customer transactions.

Mining frequent itemsets with category-based constraints

Abstract: The discovery of frequent itemsets is a fundamental task of association rule mining. The challenge is the computational complexity of the itemset search space. One of the solutions for this is to use constraints to focus on some specific itemsets. In this paper, we propose a specific type of constraints called category-based as well as the associated algorithm for constrained rule mining based on Apriori. The Category-based Apriori algorithm reduces the computational complexity of the mining process by bypassing most of the subsets of the final itemsets. An experiment has been conducted to show the efficiency of the proposed technique.

Evaluation of Common Counting Method for Concurrent Data Mining Queries

Abstract: Data mining queries are often submitted concurrently to the data mining system. The data mining system should take advantage of overlapping of the mined datasets. In this paper we focus on frequent itemset mining and we discuss and experimentally evaluate the implementation of the Common Counting method on top of the Apriori algorithm. The general idea of Common Counting is to reduce the number of times the common parts of the source datasets are scanned during the processing of the set of frequent pattern queries.

Bitmap techniques for optimizing decision support queries and association rule algorithms

Abstract: In this paper, we discuss some new bitmap techniques for optimizing decision support queries and association rule algorithm. We first show how to use a new type of predefined bitmap join index (prejoin/spl I.bar/bitmap/spl I.bar/index) to efficiently execute complex decision support queries with multiple outer join operations involved and push the outer join operations from the data flow level to the bitmap level and achieve significant performance gain. Then we discuss a bitmap based association rule algorithm. Our bitmap based association rule algorithm Bit-AssocRule doesn't follow the generation-and-test strategy of a priori algorithm and adopts the divide-and-conquer strategy, thus avoids the time-consuming table scan to find and prune the item sets, all the operations of finding large item sets from the datasets are the fast bit operations. The experimental results show Bit-AssocRule is 2 to 3 orders of magnitude faster than a priori and a priori hybrid algorithms. Our results indicate that bitmap techniques can greatly improve the performance of decision support queries and association rule algorithm, and bitmap techniques are very promising for the decision support query optimization and data mining applications.

Association Rule Mining Algorithms for Set-Valued Data

Abstract: This paper presents an association rule mining system that is capable of handling set-valued attributes. Our previous research has exposed us to a variety of real-world biological datasets that contain attributes whose values are sets of elements, instead of just individual elements. However, very few data mining tools accept datasets that contain these set-valued attributes, and none of them allow the mining of association rules directly from this type of data. We introduce in this paper two algorithms for mining (classification) association rules directly from set-valued data and compare their performance. We have implemented a system based on one of these algorithms and have applied it to a number of biological datasets. We describe here our system and highlight its merits by means of comparing the results achieved with it and the failed attempts to mine association rules from those datasets using standard tools. Our system makes the creation of input files containing set-valued data much easier, and makes the mining of association rules directly from these data possible.

A distributed and mobile data mining system

Abstract: Most of the popular data mining algorithms are designed to work for centralized data and they often do not pay attention to the resource constraints of distributed and mobile environments. In support of the third generation of data mining systems on distributed and massive data, we proposed an efficient distributed and mobile algorithm for global association rule mining, which does not need to ship all of local data to one site thereby not causing excessive network communication cost. The algorithm is implemented in PL/SQL for coupling association rule mining with relational database system, well-used in organizations and communities. The experiments show that this algorithm implemented in PL/SQL beats classic Apriori algorithm for large problem sizes, by factors ranging from 2 to more than 20, and this gap grows wider when the volume of transactions further grows up.

Parallel association rule mining with minimum inter-processor communication

Abstract: Existing parallel association rule mining algorithms suffer from many problems when mining massive transactional datasets. One major problem is that most of the parallel algorithms for a shared nothing environment are Apriori-based algorithms. Apriori-based algorithms are proven to be not scalable due to many reasons, mainly: (1) the repetitive I/O disk scans, (2) the huge computation and communication involved during the candidacy generation. This paper proposes a new disk-based parallel association rule mining algorithm called Inverted Matrix, which achieves its efficiency by applying three new ideas. First, transactional data is converted into a new database layout called Inverted Matrix that prevents multiple scanning of the database during the mining phase, in which finding globally frequent patterns could be achieved in less than a full scan with random access. This data structure is replicated among the parallel nodes. Second, for each frequent item assigned to a parallel node, a relatively small independent tree is built summarizing co-occurrences. Finally, a simple and non-recursive mining process reduces the memory requirements as minimum candidacy generation and counting is needed, and no communication between nodes is required to generate all globally frequent patterns.

Generalized closed itemsets for association rule mining

Abstract: The output of Boolean association rule mining algorithms is often too large for manual examination. For dense datasets, it is often impractical to even generate all frequent itemsets. The closed itemset approach handles this information overload by pruning "uninteresting" rules following the observation that most rules can be derived from other rules. We propose a new framework, namely, the generalized closed (or g-closed) itemset framework. By allowing for a small tolerance in the accuracy of itemset supports, we show that the number of such redundant rules is far more than what was previously estimated. Our scheme can be integrated into both levelwise algorithms (Apriori) and two-pass algorithms (ARMOR). We evaluate its performance by measuring the reduction in output size as well as in response time. Our experiments show that incorporating g-closed itemsets provides significant performance improvements on a variety of databases.

Fuzzy rule extraction based on the mining generalized association rules

Abstract: In data mining, the quantitative attributes should be appropriately dealt with as well as the Boolean attributes. This paper describes a fuzzy rule extraction method based on mining generalized association rules from database. The objectives of the method are to improve the computational time of mining and the accuracy of the extracted rules for the actual application. In our approach, we construct a hierarchical taxonomic fuzzy sets structure in each attribute. Two algorithms are shown based on the structure and the Apriori algorithm. We propose a multistage fuzzy rule extraction algorithm and a multiscan algorithm. From the results of numerical experiments, our methods are found to be effective in terms of computational time.

Fast Frequent Itemset Mining using Compressed Data Representation.

Abstract: Discovering association rules by identifying relationships among sets of items in a transaction database is an important problem in Data Mining. Finding frequent itemsets is computationally the most expensive step in association rule discovery and therefore it has attracted significant research attention. In this paper, we describe a more efficient algorithm for mining complete frequent itemsets from typical data sets. We use a compressed prefix tree and our algorithm extracts the frequent itemsets directly from the tree. We present performance comparisons of our algorithm against the fastest Apriori algorithm, Eclat, and FP-Growth. These results show that our algorithm outperforms other algorithms on several widely used test data sets.

A compress-based association mining algorithm for large dataset

Abstract: The association mining is one of the primary sub-areas in the field of data mining. This technique had been used in numerous practical applications, including consumer market basket analysis, inferring patterns from web page access logs, network intrusion detection and pattern discovery in biological applications. Most of the traditional association-mining algorithms assume that whole dataset can be loaded in the main memory. Hence, problem arise when such algorithms is applied in large dataset. In this paper we present a new algorithm for association mining. Our algorithm is efficient when the size of dataset is huge that cannot be load in the main memory. The proposed algorithm also reduces the frequent itemsets search space, by eliminating non-frequent 1- itemsets after the first pass. Our performance evaluation shows algorithm out-performs Apriori algorithm in different datasets.

Mining conditional hybrid-dimension association rules on the basis of multi-dimensional transaction database

Abstract: In this paper, we present such an idea of mining hybrid-dimension association rules which meet the definite condition on the basis of multidimensional transaction database. First, we simply introduce the general algorithm for mining association rules. Second, we give a brief analysis about the classical algorithm for mining single-dimensional association rules. Based on the analysis, we stress on the discussion about how to expand and improve the algorithm, and then design an algorithm for mining hybrid-dimension association rules which meet the definite condition from multidimensional transaction database. Last we give a simple example to explain the implement of the algorithm.

An enhanced a priori algorithm for mining multidimensional association rules

Abstract: Two concepts from different research areas are brought together, namely functional dependencies which are a class of integrity constraints that have gained fundamental importance for relational database design and association rules which are a class of patterns, which has been studied rigorously in data mining. It is shown that functional dependencies may be used to logically infer new association rules from given ones. This observation will then be employed to propose a new variant of the best known algorithm for association rule mining, the so-called a priori algorithm.

****draft**** algorithms for association rules

Abstract: Association rules are ”if-then rules” with two measures which quantify the support and confidence of the rule for a given data set. Having their origin in market basked analysis, association rules are now one of the most popular tools in data mining. This popularity is to a large part due to the availability of efficient algorithms following from the development of the Apriori algorithm. In these lectures we will introduce basic concepts of association rule discovery including support, confidence, interestingness, the apriori property, and hierarchical and quantitative association rules. The core of the lectures consists of a review of the most important algorithms for association rule discovery. Some familiarity with concepts like predicates, probability, expectation and random variables is assumed.

Temporal Feature Extraction from Temporal Information Systems

Abstract: We present a framework for new feature extraction from temporal information systems. Such systems provide information about behaviour of object(s) in time and state of an object is described by some attributes. We propose a modification of Apriori algorithm for frequent episode detection across many series. The episodes are built from events being temporal patterns found in temporal information system.

An Optimized Apriori Algorithm for Mining Association Rules

Abstract: An optimized Apriori algorithm is provided based on study of the principle and efficiency of the algorithm of literature[ 1 ] and Apriori algorithm, which is more efficient than the algorithm of literature

Mining WWW access sequence by matrix clustering

Abstract: Sequence pattern mining is one of the most important methods for mining WWW access log. The Apriori algorithm is well known as a typical algorithm for sequence pattern mining. However, it suffers from inherent difficulties in finding long sequential patterns and in extracting interesting patterns among a huge amount of results. This article proposes a new method for finding generalized sequence pattern by matrix clustering. This method decomposes a sequence into a set of sequence elements, each of which corresponds to an ordered pair of items. Then matrix clustering is applied to extract a cluster of similar sequences. The resulting sequence elements are composed into a generalized sequence. Our method is evaluated with practical WWW access log, which shows that it is practically useful in finding long sequences and in presenting the generalized sequence in a graph.