223 research outputs found
A Parallel Algorithm for Approximate Frequent Itemset Mining using MapReduce
No full textRecently, several algorithms based on the MapReduce framework have been proposed for frequent pattern mining in Big Data. However, the proposed solutions come with their own technical challenges, such as inter-communication costs, in-process synchronizations, balanced data distribution and input parameters tuning, which negatively affect the computation time. In this paper we present MrAdam, a novel parallel, distributed algorithm which addresses these problems. The key principle underlying the design of MrAdam is that one can make reasonable decisions in the absence of perfect answers. Indeed, given the classical threshold for minimum support and a user-specified error bound, MrAdam exploits the Chernoff bound to mine "approximate" frequent itemsets with statistical error guarantees on their actual supports. These itemsets are generated in parallel and independently from subsets of the input dataset, by exploiting the MapReduce parallel computation framework. The result collections of frequent itemsets from each subset are aggregated and filtered by using a novel technique to provide a single collection in output.
MrAdam can scale well on gigabytes of data and tens of machines, as experimentally proven on real datasets. In the experiments we also show that the proposed algorithm returns a good statistically bounded approximation of the exact results
A KDD Platform based on the Application Service Provider Paradigm
No full textNowadays, Small and Medium Enterprises (SMEs) are forced to compete on a global market and to make strategic decisions in short periods of time. In order to allow SMEs access to information technologies which can support their competition on a global scale, public administrations are fostering the setting up of Digital Districts. In this paper, we describe a distributed collaborative data mining platform, named KD-ASP, developed for a Digital District. It is based on the application service provider (ASP) paradigm, which allows SMEs accessing to data mining services over a network and to cut down costs for their acquisition, upgrading and maintenance. KD-ASP allows the users to collaborate on the design of a knowledge discovery process whose execution is then demanded to a workflow engine. Tasks involved in a process are classified as data selection, pre-processing, data transformation, data mining and data visualization, and are made available as Web services
Proceedings of the Second Workshop on MIning DAta for financial applicationS (MIDAS '17), co-located with the 2017 European Conference on Machine Learning and Principles and Practice of Knowledge Discovery (ECML-PKDD '17)
No full textMetodologia di ottimizzazione delle prestazioni di un propulsore ibrido di tipo parallelo
No full textProceedings of the First Workshop on MIning DAta for financial applicationS (MIDAS 2016) co-located with the 2016 European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD 2016), Riva del Garda, Italy, September 19-23, 2016
No full text
- …
