Abstract

Periodic Frequent patterns (PFPs) are an important class of regularities that exist in a transactional database. In the literature,pattern growth-based approaches to mine PFPs have be proposed by considering a single machine. In this paper, we propose a Map-Reduce framework to mine PFPs by considering multiple machines. We have proposed a parallel algorithm by including the step of distributing transactional identifiers among the machines. Further, the notion of partition summary has been proposed to reduce the amount of data shuffled among the machines. Experiments on Apache Spark’s distributed environment show that the proposed approach speeds up with the increase in number of machines and the notion of partition summary significantly reduces the amount of data shuffled among the machines.

Abstract

Utility mining has been emerging as an important area in data mining. While existing works on utility mining have primarily focused on the problem of finding high-utility itemsets from transactional databases, they implicitly assume that each item occupies only one slot. However, in many real-world scenarios, the number of slots consumed by different items typically varies. Hence, this pa-per considers that a given item may physically occupy any fixed (integer) number of slots. Thus, we address the problem of efficiently determining the top-utility itemsets when a given number of slots is specified as input. The key contributions of our work are three-fold. First, we present an efficient framework to determine the top-utility itemsets for different user-specified number of slots that need to be filled. Second, we propose a novel flexible and efficient index, designated as the STUI index, for facilitating quick retrieval of the top-utility itemsets for a given number of slots. Third, we conducted an extensive performance evaluation using real datasets to demonstrate the overall effectiveness of the proposed indexing scheme in terms of execution time and utility (net revenue) as compared to a recent existing scheme.

Abstract

Periodic-frequent patterns (or itemsets) are an important class of regularities that exist in a transactional database. Finding these patterns involves discovering all frequent patterns that satisfy the user specified maximum periodicity constraint. This constraint controls the maximum inter-arrival time of a pattern in a database. The time complexity to measure periodicity of a pattern is O(n), where n represents the number of timestamps at which the corresponding pattern has appeared in a database. As unusually represents a high value in voluminous databases, determining the periodicity of every candidate pattern in the itemset lattice makes the periodic-frequent pattern mining a computationally expensive process. This paper introduces a novel approach to address this problem. Our approach determines the periodic interestingness of a pattern by adopting greedy search. The basic idea of our approach is to discover all periodic-frequent patterns by eliminating a periodic patterns based on suboptimal solutions. The best and worst case time complexities of our approach to determine the periodic interestingness of a frequent pattern are O(1) and O(n), respectively. We introduce two pruning techniques and propose a pattern-growth algorithm to find these patterns efficiently. Experimental results show that our algorithm is runtime efficient and highly scalable as well.

Abstract

n the banner advertising scenario, an advertiser aims to reach the maximum number of potential visitors and a publisher tries to meet the requests of increased number of advertisers to maximize the revenue. In the literature, a model was introduced to extract the knowledge of coverage patterns from transactional database. In this paper, we propose an ad slots allocation approach by extending the notion of coverage patterns to select distinct sets of ad slots to meet the requests of multiple advertisers. The preliminary experimental results on a real world dataset show that the proposed approach meets the requests of increased number of advertisers when compared with the baseline approach of allocation.

Abstract

Community-driven Question Answering (Q&A) platforms are gaining popularity now-a-days and the number of posts on such platforms are increasing tremendously. Thus, the challenge to keep these platforms noise-free is attracting the interest of research community. Stack Overflow is one such popular computer programming related Q&A platform. The established users on Stack Overflow have learnt the accept-able format and scope of questions in due course. Even if their questions get closed, they are aware of the required ed-its, therefore the chances of their questions being reopened increases. On the other hand, non-established users have not adapted to the Stack Overflow system and find difficulty in editing their closed questions. In this work, we aim to identify features which help differentiate editing approaches of established and non-established users, and motivate the need of recommendation model. Such a recommendation model can assist every user to edit their closed questions leveraging the edit-style of the established users of the platform.

Abstract

Recommender system (RS) helps customers to select appropriate products from millions of products and has become a key component in e-commerce systems. Collaborative filtering (CF) based approaches are widely employed to build RSs. In CF, recommendation to the target user is computed after forming the corresponding neighbour-hood of users. Neighborhood of a target user is extracted based on the similarity between the product rating vector of the target user and the product rating vectors of individual users. In CF, the methodology employed for neighborhood formation influences the performance. In this paper, we have made an effort to improve the performance of CF by proposing a different approach to compute recommendations by considering two kinds of neighborhood. One is the neighborhood by considering the product ratings of the user as a single vector and the other is based on the neighborhood of the corresponding virtual users. For the target user,the virtual users are formed by dividing the ratings based on the category of products. We have proposed a combined approach to compute better recommendations by considering both kinds of neighborhoods.The experiments results on real world Movie Lens dataset show that the proposed approach improves the performance over CF.

Abstract

Building efficient search systems to extract relevant in-formation from a huge volume of legal judgments is a research is-sue. In the literature, efforts are being made to build efficient search systems in the legal domain by extending information retrieval approaches. We are making efforts to investigate improved approaches to extract relevant legal judgments for a given input judgment by exploiting text and citation information of legal judgments. Typically,legal judgments are very large text documents and contain several intricate legal concepts. In this paper, we analyze how the paragraph-level and citation information of the judgments could be exploited for retrieving relevant legal judgments for the given judgment. In this paper, we have proposed improved ranking approach to find the relevant legal judgments of a given judgment based on the similarity be-tween the paragraphs of the judgments by employing Okapi retrieval model and citation information. The user evaluation study on legal judgments data set delivered by Supreme Court of India shows that the proposed approach improves the ranking performance over the baseline approach. Overall, the analysis shows that there is a scope to exploit the paragraph-level and citation information of the judgments to improve the search performance.

Abstract

Periodic-frequent pattern mining involves finding all frequent patterns that have occurred at regular intervals in a transactional database. The basic model considers a pattern as periodic-frequent, if it satisfies the user-specified minimum support (min Sup) and maximum periodicity (maxP er) constraints. The usage of a single minSupandmaxP erfor an entire database leads to the are-item problem.When confronted with this problem in real-world applications, researchers have tried to address it using the item-specific minSupandmaxP er con-straints. It was observed that this extended model still generates a sig-nificant number of uninteresting patterns, and moreover, suffers from the issue of specifying item-specific minSupandmaxP er constraints.This paper proposes a novel model to address the rare-item problem in periodic-frequent pattern mining. The proposed model considers a pat-tern as interesting if its support and periodicity are close to that of its individual items. The al l-confidence is used as an interestingness measure to filter out uninteresting patterns in support dimension. In addition, anew interestingness measure, called periodic-al l-confidence, is being pro-posed to filter out uninteresting patterns in periodicity dimension. We have proposed a model by combining both measures and proposed a pattern-growth approach to resolve the rare-item problem and extract interesting periodic-frequent patterns. Experimental results show that the proposed model is efficient

Abstract

Periodic-frequent patterns are an important class of regularities which exists in a transactional database. A frequent pattern is called periodic-frequent if it appears at regular intervals in a transactional database. In the literature, a model of periodic-frequent patterns was proposed and pattern growth like approaches to extract patterns are being explored. In these approaches, a periodic-frequent pattern tree is built in which a transaction-id list is maintained at each path’s tail-node. As the typical size of transactional database is very huge in the modern e-commerce era, extraction of periodic-frequent patterns by maintaining transaction-ids in the tree requires more memory.In this paper, to reduce the memory requirements, we introduced a notion of period summary by capturing the periodicity of the patterns in a sequence of transaction-ids. While building the tree,the period summary of the transactions is computed and stored at the tail-node of the tree instead of the transaction-ids. We have also proposed a merging framework for period summaries for mining periodic-frequent patterns. The performance could be improved significantly as the memory required to store the period summaries is significantly less than the memory required to store the transaction-id list. Experimental results show that the pro-posed approach reduces the memory consumption significantly and also improves the runtime efficiency considerably over the existing approaches.

Abstract

The systems for weather observation and forecast are being operated to deal with adverse weather in general to mankind. Weather-based decision support systems (DSSs) are being build to improve the efficiency of the production systems in the domains of health, agriculture, livestock, transport, business, planing, governance and so on.The weather-based DSS provides appropriate suggestions based on the weather condition of the given period for the selected domain. In the literature, the notion of reuse is being employed in improving the efficiency of DSSs. In this paper, we have proposed a framework to identify similar weather conditions, which could help in improving the performance of weather-based DSSs with better reuse. In the proposed framework, the range of weather variable is divided into categories based on its influence on that domain. We form a weather condition for a period which is the combination of category values of weather variables. By comparing the daily/weekly weather conditions of a given year to weather conditions of subsequent years, the proposed framework identifies the extent of reuse.We have conducted the experiment by applying the proposed framework on 30 years of weather data of Rajendranagar, Hyderabad and using the categories employed by India Meteorological Department in Meteorology domain. The results show that there is a significant degree of similarity among daily and weekly weather conditions over the years. The results provide an opportunity to improve the efficiency of weather-based DSSs by improving the degree of reuse of the developed suggestions/knowledge for the corresponding weather conditions.