System failure prediction through rare-events elastic-net logistic regression

Navarro González, José Manuel and Parada Gélvez, Hugo Alexer and Dueñas López, Juan Carlos (2014). System failure prediction through rare-events elastic-net logistic regression. In: "2nd International Conference on Artificial Intelligence, Modelling and Simulation (AIMS 2014)", 18/11/2014 - 20/11/2014, Madrid, Spain. pp. 120-125. https://doi.org/10.1109/AIMS.2014.19.

Description

Title: System failure prediction through rare-events elastic-net logistic regression
Author/s:
  • Navarro González, José Manuel
  • Parada Gélvez, Hugo Alexer
  • Dueñas López, Juan Carlos
Item Type: Presentation at Congress or Conference (Article)
Event Title: 2nd International Conference on Artificial Intelligence, Modelling and Simulation (AIMS 2014)
Event Dates: 18/11/2014 - 20/11/2014
Event Location: Madrid, Spain
Title of Book: 2nd International Conference on Artificial Intelligence, Modelling and Simulation (AIMS 2014)
Date: 2014
Subjects:
Freetext Keywords: Online Failure Prediction; Machine Learning; System Management; Automatic Feature Selection; Logistic Regression; Multivariable Prediction
Faculty: E.T.S.I. Telecomunicación (UPM)
Department: Ingeniería de Sistemas Telemáticos [hasta 2014]
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[img]
Preview
PDF - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (792kB) | Preview

Abstract

Predicting failures in a distributed system based on previous events through logistic regression is a standard approach in literature. This technique is not reliable, though, in two situations: in the prediction of rare events, which do not appear in enough proportion for the algorithm to capture, and in environments where there are too many variables, as logistic regression tends to overfit on this situations; while manually selecting a subset of variables to create the model is error- prone. On this paper, we solve an industrial research case that presented this situation with a combination of elastic net logistic regression, a method that allows us to automatically select useful variables, a process of cross-validation on top of it and the application of a rare events prediction technique to reduce computation time. This process provides two layers of cross- validation that automatically obtain the optimal model complexity and the optimal mode l parameters values, while ensuring even rare events will be correctly predicted with a low amount of training instances. We tested this method against real industrial data, obtaining a total of 60 out of 80 possible models with a 90% average model accuracy.

More information

Item ID: 36455
DC Identifier: http://oa.upm.es/36455/
OAI Identifier: oai:oa.upm.es:36455
DOI: 10.1109/AIMS.2014.19
Deposited by: Memoria Investigacion
Deposited on: 19 Jul 2015 09:10
Last Modified: 19 Jul 2015 09:10
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM