Web Clickstream Research Articles

Efficient Utility Tree-Based Algorithm to Mine High Utility Patterns Having Strong Correlation

High Utility Itemset Mining (HUIM) is one of the most investigated tasks of data mining. It has broad applications in domains such as product recommendation, market basket analysis, e-learning, text mining, bioinformatics, and web click stream analysis. Insights from such pattern analysis provide numerous benefits, including cost cutting, improved competitive advantage, and increased revenue. However, HUIM methods may discover misleading patterns as they do not evaluate the correlation of extracted patterns. As a consequence, a number of algorithms have been proposed to mine correlated HUIs. These algorithms still suffer from the issue of the computational cost in terms of both time and memory consumption. This paper presents an algorithm, named Efficient Correlated High Utility Pattern Mining (ECoHUPM), to efficiently mine the high utility patterns having strong correlation items. A new data structure based on utility tree (UTtree) named CoUTlist is proposed to store sufficient information for mining the desired patterns. Three pruning properties are introduced to reduce the search space and improve the mining performance. Experiments on sparse, very sparse, dense, and very dense datasets indicate that the proposed ECoHUPM algorithm is efficient as compared to the state-of-the-art CoHUIM and CoHUI-Miner algorithms in terms of both time and memory consumption.

Investigating the PageRank and sequence prediction based approaches for next page prediction

Discovering unseen patterns from web clickstream is an upcoming research area. One of the meaningful approaches for making predictions is using sequence prediction that is typically the improved compact prediction tree (CPT+). However, to increase this method's effectiveness, combining it with at least other methods is necessary. This work investigates such PageRank-based methods related to sequence prediction as All-K-Markov, DG, Markov 1st, CPT, CPT+. The experimental results proved that the integration of CPT+ and PageRank is the right solution for next page prediction in terms of accuracy, which is more than a standard method of approximately 0.0621%. Still, the size of the newly created sequence database is reduced up to 35%. Furthermore, our proposed solution has an accuracy that is much higher than other ones. It is intriguing for the next phase (testing one) to make the next page prediction in terms of time performance.

Visual Causality Analysis of Event Sequence Data.

Causality is crucial to understanding the mechanisms behind complex systems and making decisions that lead to intended outcomes. Event sequence data is widely collected from many real-world processes, such as electronic health records, web clickstreams, and financial transactions, which transmit a great deal of information reflecting the causal relations among event types. Unfortunately, recovering causalities from observational event sequences is challenging, as the heterogeneous and high-dimensional event variables are often connected to rather complex underlying event excitation mechanisms that are hard to infer from limited observations. Many existing automated causal analysis techniques suffer from poor explainability and fail to include an adequate amount of human knowledge. In this paper, we introduce a visual analytics method for recovering causalities in event sequence data. We extend the Granger causality analysis algorithm on Hawkes processes to incorporate user feedback into causal model refinement. The visualization system includes an interactive causal analysis framework that supports bottom-up causal exploration, iterative causal verification and refinement, and causal comparison through a set of novel visualizations and interactions. We report two forms of evaluation: a quantitative evaluation of the model improvements resulting from the user-feedback mechanism, and a qualitative evaluation through case studies in different application domains to demonstrate the usefulness of the system.

A Survey of Correlated High Utility Pattern Mining

Pattern mining is an unsupervised data mining approach aims to find interesting patterns that can be used to support decision-making. High Utility Pattern Mining (HUPM) aims to extract patterns having high utility or importance which has broad applications in domains such as market basket analysis, product recommendation, bioinformatics, e-learning, text mining, and web click stream analysis. However, it has several limitations on real life scenarios; as a consequence, many extensions of HUPM appeared in the literature such as Correlated High Pattern Mining, Incremental Utility Mining, On-Shelf High Utility Pattern Mining, and Concise Representations of High Utility Patterns. The Correlated High Utility Pattern Mining aims to extract interesting high utility patterns by utilizing both Utility and Correlation measures. Several algorithms have been proposed to mine the correlated high utility patterns. These algorithms differ in the measures used to evaluate the interestingness of the patterns, data structures and pruning properties which they use to improve the mining performance. This paper presents a detailed survey on correlated high utility pattern mining, their methods, measures, data structures and pruning properties.

Pre-Order Post-Order Coded Aggregate Tree based Algorithm for Mining Sequential Patterns

Sequential pattern mining is a data mining approach; aims to discover common interesting patterns in sequence datasets, which attracted a significant research interest due to its real world applications in various fields such as web click stream mining, retail business, stock market and bio-informatics. Each sequence in sequence dataset is composed of time ordered events and each event is an item set. It discovers all frequent subsequences having frequency greater than the given minimum support threshold. Discovering sequential patterns is expensive with respect to mining time as well as the amount of memory used, because of aggressive search space growth due to generation of explosive number of frequent subsequences with the sequence length as well as count of distinct items and large volume of sequence dataset. So, research in this domain aims at developing effective data structures which address frequency counting and large search space as well as scalable algorithms to reduce the execution time and the amount of memory utilized. We propose two efficient data structures called Pre-order Post-order Coded Aggregate Tree (PPCA-Tree) for compact representation of the sequence dataset and Root-node List of First-Occurrence Sub Trees Map (RLFOST-Map) for efficient representation of projected databases. We also developed an efficient Partially ordered Sequential PAttern Mining algorithm called PSPAM and Parallel implementation of Partially ordered Sequential PAttern Mining algorithm called PAPSPAM based on PPCA-Tree using RLFOST-Map which eliminates reconstruction of the projected databases. Experimental analysis done on various synthetic datasets proves that our algorithms PSPAM and PAPSPAM outperform prefixspan and other conventional & state-of-the-art algorithms over dense datasets with better scalability.

SSRDVis: Interactive visualization for event sequences summarization and rare detection

This paper presents SSRDVis, a visual approach to effectively summarize event sequences and interactively detect rare behaviors. SSRDVis is mainly composed of three components: (1) a sequence embedding module for learning effective feature vectors of sequences, (2) a sequence grouping and summarization module to find representative clusters and patterns in the dataset, (3) a rare detection module to discover and explain the rare cases. The sequences are embedded into vector space via “mixed-ngram2vec,” which is adapted from “word2vec.” Then, unsupervised learning models could be applied to group similar sequences and detect anomalies in the vector space. Furthermore, sequential pattern graphs are built to provide a compact and semantic summarization of sequences. These components work together to present both overall sequential patterns and abnormal behaviors in one visual interface. We have demonstrated the feasibility of our approach by applying it to analyze Web clickstreams. Experimental results have shown that our approach could help identify noticeable patterns from a large number of event sequences, especially for rare behaviors.

Data Stream Clustering Techniques, Applications, and Models: Comparative Analysis and Discussion

Data growth in today’s world is exponential, many applications generate huge amount of data streams at very high speed such as smart grids, sensor networks, video surveillance, financial systems, medical science data, web click streams, network data, etc. In the case of traditional data mining, the data set is generally static in nature and available many times for processing and analysis. However, data stream mining has to satisfy constraints related to real-time response, bounded and limited memory, single-pass, and concept-drift detection. The main problem is identifying the hidden pattern and knowledge for understanding the context for identifying trends from continuous data streams. In this paper, various data stream methods and algorithms are reviewed and evaluated on standard synthetic data streams and real-life data streams. Density-micro clustering and density-grid-based clustering algorithms are discussed and comparative analysis in terms of various internal and external clustering evaluation methods is performed. It was observed that a single algorithm cannot satisfy all the performance measures. The performance of these data stream clustering algorithms is domain-specific and requires many parameters for density and noise thresholds.

Knowledge-maximized ensemble algorithm for different types of concept drift

Knowledge extraction from data streams has attracted attention in recent years due to its wide range of applications, including sensor networks, web clickstreams, and user interest analysis. Concept drift is one of the most important research topics in data stream mining. Many algorithms that can adapt to concept drift have been proposed. However, most of them specialize in only one type of concept drift and can rarely be used in the environments with a large number of unavailable sample labels. In this study, we propose a new data stream classifier called knowledge-maximized ensemble (KME). First, supervised and unsupervised knowledge are leveraged to detect concept drift, recognize recurrent concepts, and evaluate the weights of ensemble members. Second, the preserved labelled instances in past blocks can be reused to enhance the recognition ability of the candidate member. The final decision for an incoming observation is derived from all the prediction results of the component classifiers. Accordingly, the maximum utilization of the relevant information in a data stream can be achieved, which is critical to models with limited training data. Third, KME can react to multiple types of concept drift by combining the mechanisms of online and chunk-based ensembles. Finally, we compare KME with eight state-of-the-art classifiers on several synthetic and real-world datasets. The comparison demonstrates the effectiveness of KME in various types of concept drift scenarios.

A survey of itemset mining

Itemset mining is an important subfield of data mining, which consists of discovering interesting and useful patterns in transaction databases. The traditional task of frequent itemset mining is to discover groups of items (itemsets) that appear frequently together in transactions made by customers. Although itemset mining was designed for market basket analysis, it can be viewed more generally as the task of discovering groups of attribute values frequently cooccurring in databases. Because of its numerous applications in domains such as bioinformatics, text mining, product recommendation, e‐learning, and web click stream analysis, itemset mining has become a popular research area. This study provides an up‐to‐date survey that can serve both as an introduction and as a guide to recent advances and opportunities in the field. The problem of frequent itemset mining and its applications are described. Moreover, main approaches and strategies to solve itemset mining problems are presented, as well as their characteristics are provided. Limitations of traditional frequent itemset mining approaches are also highlighted, and extensions of the task of itemset mining are presented such as high‐utility itemset mining, rare itemset mining, fuzzy itemset mining, and uncertain itemset mining. This study also discusses research opportunities and the relationship to other popular pattern mining problems, such as sequential pattern mining, episode mining, subgraph mining, and association rule mining. Main open‐source libraries of itemset mining implementations are also briefly presented.WIREs Data Mining Knowl Discov2017, 7:e1207. doi: 10.1002/widm.1207This article is categorized under:Algorithmic Development > Association RulesTechnologies > Association Rules

Memory-adaptive high utility sequential pattern mining over data streams

High utility sequential pattern (HUSP) mining has emerged as an important topic in data mining. A number of studies have been conducted on mining HUSPs, but they are mainly intended for non-streaming data and thus do not take data stream characteristics into consideration. Streaming data are fast changing, continuously generated unbounded in quantity. Such data can easily exhaust computer resources (e.g., memory) unless a proper resource-aware mining is performed. In this study, we explore the fundamental problem of how limited memory can be best utilized to produce high quality HUSPs over a data stream. We design an approximation algorithm, called MAHUSP, that employs memory adaptive mechanisms to use a bounded portion of memory, in order to efficiently discover HUSPs over data streams. An efficient tree structure, called MAS-Tree, is proposed to store potential HUSPs over a data stream. MAHUSP guarantees that all HUSPs are discovered in certain circumstances. Our experimental study shows that our algorithm can not only discover HUSPs over data streams efficiently, but also adapt to memory allocation with limited sacrifices in the quality of discovered HUSPs. Furthermore, in order to show the effectiveness and efficiency of MAHUSP in real-life applications, we apply our proposed algorithm to a web clickstream dataset obtained from a Canadian news portal to showcase users' reading behavior, and to a real biosequence database to identify disease-related gene regulation sequential patterns. The results show that MAHUSP effectively discovers useful and meaningful patterns in both cases.

Patterns and Sequences: Interactive Exploration of Clickstreams to Understand Common Visitor Paths.

Modern web clickstream data consists of long, high-dimensional sequences of multivariate events, making it difficult to analyze. Following the overarching principle that the visual interface should provide information about the dataset at multiple levels of granularity and allow users to easily navigate across these levels, we identify four levels of granularity in clickstream analysis: patterns, segments, sequences and events. We present an analytic pipeline consisting of three stages: pattern mining, pattern pruning and coordinated exploration between patterns and sequences. Based on this approach, we discuss properties of maximal sequential patterns, propose methods to reduce the number of patterns and describe design considerations for visualizing the extracted sequential patterns and the corresponding raw sequences. We demonstrate the viability of our approach through an analysis scenario and discuss the strengths and limitations of the methods based on user feedback.

Discovering Time-Interval Sequential Patterns by a Pattern Growth Approach with Confidence Constraints

Sequential pattern mining is to discover frequent sequential patterns in a sequence database. The technique is applied to fields such as web click-stream mining, failure forecast, and traf- fic analysis. Conventional sequential pattern-mining approaches generally focus only the orders of items; however, the time interval between two consecutive events can be a valuable information when the time of the occurrence of an event is concerned. This study extends the concept of the well-known pattern growth approach, PrefixSpan algorithm, to propose a novel sequential pattern mining approach for sequential patterns with time intervals. Unlike the other time-interval sequential pattern-mining algorithms, the approach concerns the time for the next event to occur more than the timing information with its precedent events. To obtain a more reliable sequential pattern, a new measure of the confidence of a sequential pattern is defined. Experiments are conducted to evaluate the performance of the proposed approach.

웹 클릭 스트림에서 고유용 과거 정보 탐색

Abstract Web-based services are used widely in many computer application fields due to the increasing use of PCsand mobile devices. Accordingly, topics on the analysis of access logs generated in the application fields have been researched actively to support personalized services in the field, and analyzing techniques based on the weight differentiation of information in access logs have been proposed. This paper outlines an analysis technique for web-click streams, which is useful for finding high utility old item sets in web-click streams, whose data elementsare generated at a rapid rate. Using the technique, interesting information can be found, which is difficult to find inconventional techniques for analyzing web-click streams and is used effectively in target marketing. The proposed technique can be adapted widely to analyzing the data generated in a range of computing application fields, such asIoT environments, bio-informatics, etc., which generated data as a form of data streams.

Survey on Outlier Detection in Data Stream

mining provides a way for finding hidden and useful knowledge from the large amount of data .usually we find any information by finding normal trends or distribution of data .But sometimes rare event or data object may provide information which is very interesting to us .Outlier detection is one of the task of data mining .It finds abnormal data point or sequence hidden in the dataset .Data stream is unbounded sequence of data with explicit or implicit temporal context .Data stream is uncertain and dynamic in nature. Traditional outlier detection techniques for static data which require whole dataset for modelling is not suitable for data stream because whole data stream cannot be stored. Network intrusion detection ,web click stream analysis ,fraud detection ,fault detection in machines ,sensor data analysis are some of the applications of data stream outlier detection .In this paper, we have described several issues in data stream outlier detection and usual approaches or techniques for finding outlier in data stream .

An Efficient Algorithm for Mining Weighted Frequent Itemsets Using Adaptive Weights

Weighted frequent itemset mining is more practical than traditional frequent itemset mining, because it can consider different semantic significance (weight) of items. Many models and algorithms for mining weighted frequent itemsets have been proposed. These models assume that each item has a fixed weight. But in real world scenarios, the weight (price or significance) of the items may vary with time. Therefore, reflecting these changes in item weight is necessary in several mining applications, such as retail market data analysis and web click stream analysis. Recently, Chowdhury F. A. et al. have introduced a novel concept of adaptive weight for each item and propose an algorithm AWFPM (Adaptive Weighted Frequent Pattern Mining). AWFPM can handle the situation where the weight (price or significance) of an item may vary with time. In this paper, we present an improved algorithm named AWFIMiner. Experimental computations show that our AWFIMiner is more efficient and scalable for mining weighted frequent itemsets using adaptive weights. Moreover, because it only requires one single database scan, the AWFIMiner is applicable for mining these itemsets on data streams.

Incrementally updating the discovered sequential patterns based on pre-large concept

Mining useful information from large databases has become an important research area in recent years. Among the classes of knowledge derived, sequential pattern can be applied in many domains, such as market analysis, web click streams, and biological data. The fast updated sequential pattern tree (FUSP-tree) algorithm was proposed to update discovered sequential patterns in incremental mining. However, it must rescan the original database for maintaining discovered sequential patterns. This study proposes the PreFUSP-TREE-INS algorithm based on the pre-large concept for maintaining discovered sequential patterns without rescanning the original database until the cumulative number of newly added customer sequences exceeds a safety bound. The execution time for reconstructing the tree when old or new customer sequences are added into the original database is reduced by using pre-large sequences. The pre-large sequences are defined by lower and upper support thresholds that prevent the movement of sequences directly from large to small and vice versa. Experiments are conducted to show the performance of the proposed algorithm for various minimum support thresholds and ratios of inserted sequences.

A pattern based predictor for event streams

Recently, new emerging applications, such as web click-stream mining, failure forecast and traffic analysis, introduced a new challenging data model referred to as data streams. Mining such data can reveal up-to-date patterns, which are useful for predicting future events. Consequently, pattern mining in data streams is a popular field in data mining that presents unique challenges. The data is large and endlessly keeps on coming, making it impossible to store it, or to re-analyse historical data once it has been discarded. To solve this, we first present a novel method for mining sequential patterns from a data stream, in which we maximise memory usage in order to achieve higher accuracy in terms of results. In a second step, we use the discovered patterns in order to try to predict future events. We propose a number of ways to assign a score to each pattern in order to generate predictions. The prediction performance of these scoring strategies is then extensively experimentally evaluated. The predictor offers an opportunity for a faster detection and response to an important, though perhaps unexpected, event, which will occur in the future.

A Robust and Extensible Tool for Data Integration Using Data Type Models

Integrating heterogeneous data sets has been a significant barrier to many analytics tasks, due to the variety in structure and level of cleanliness of raw data sets requiring one-off ETL code. We propose HiperFuse, which significantly automates the data integration process by providing a declarative interface, robust type inference, extensible domain-specific data models, and a data integration planner which optimizes for plan completion time. The proposed tool is designed for schema-less data querying, code reuse within specific domains, and robustness in the face of messy unstructured data. To demonstrate the tool and its reference implementation, we show the requirements and execution steps for a use case in which IP addresses from a web clickstream log are joined with census data to obtain average income for particular site visitors (IPs), and offer preliminary performance results and qualitative comparisons to existing data integration and ETL tools.

A survey on data stream clustering and classification

Nowadays, with the advance of technology, many applications generate huge amounts of data streams at very high speed. Examples include network traffic, web click streams, video surveillance, and sensor networks. Data stream mining has become a hot research topic. Its goal is to extract hidden knowledge/patterns from continuous data streams. Unlike traditional data mining where the dataset is static and can be repeatedly read many times, data stream mining algorithms face many challenges and have to satisfy constraints such as bounded memory, single-pass, real-time response, and concept-drift detection. This paper presents a comprehensive survey of the state-of-the-art data stream mining algorithms with a focus on clustering and classification because of their ubiquitous usage. It identifies mining constraints, proposes a general model for data stream mining, and depicts the relationship between traditional data mining and data stream mining. Furthermore, it analyzes the advantages as well as limitations of data stream algorithms and suggests potential areas for future research.

Web Log Mining to Enhance Surfing Experience

Analyzing navigation history of a web site and that of a user reported in log files and web click stream helps in determining the components that shall be needed in the near future and fetch them in advance. Identifying the frequently visited websites from such data enhances the process. Processing and analyzing the vast amounts of click stream data and web logs that are generated at very high rates in a smart and cost-efficient way is a daunting challenge to the data mining community. Mining frequent itemsets plays an important role in analyzing such data streams. In spite of the existence of many such mining algorithms, more time and space efficient algorithms for mining frequent patterns are the need of the hour and are attracting wide attention in web click-stream analysis in recent years. In this paper an effective algorithm for mining frequent itemsets from a time-sensitive sliding window is proposed. It is a one-pass algorithm that uses a circular queue to implement the sliding window. The time-sensitive sliding window stores the web click stream data of various sessions of the web users. The proposed one-pass algorithm, FIM_CQTimeSWin has three phases: representation of time unit, maintenance of the sliding window and generation of frequent itemsets in the current sliding window.