Scalable parallel algorithms for predictive modelling

P. Christen, M. Hegland, O. Nielsen, Stephen Roberts, I. Altas

Research output: Book chapter/Published conference paperConference paperpeer-review

2 Citations (Scopus)


Data Mining applications have to deal with increasingly large data sets and complexity. Only algorithms which scale linearly with data size are feasible. We present parallel regression algorithms which after a few initial scans of the data compute predictive models for data mining and do not require further access to the data. In addition, we describe various ways of dealing with the complexity (high dimensionality) of the data. Three methods are presented for three different ranges of attribute numbers. They use ideas from the finite element method and are based on penalised least squares fits using sparse grids and additive models for intermediate and very high dimensional data. Computational experiments confirm scalability both with respect to data size and number of processors.

Original languageEnglish
Title of host publicationSecond International Conference on Data Mining, Data Minig II
Number of pages10
Publication statusPublished - 2000
EventSecond International Conference on Data Mining, Data Minig II - Cambridge, United Kingdom
Duration: 05 Jul 200007 Jul 2000

Publication series

NameManagement Information Systems
ISSN (Print)1470-6326


ConferenceSecond International Conference on Data Mining, Data Minig II
Country/TerritoryUnited Kingdom


Dive into the research topics of 'Scalable parallel algorithms for predictive modelling'. Together they form a unique fingerprint.

Cite this