FAILURE PREDICTION USING THE COX PROPORTIONAL HAZARD MODEL

Pekka Abrahamsson, Ilenia Fronza, Jelena Vlasenko

2011

Abstract

Crashes of software systems may have disruptive, and sometimes tragic effects on users. Being able to forecast such failures is extremely important, even when the failures are inevitable – at least recovery or rescue actions can be taken. In this paper we present a technique to predict the failure of running software systems. We propose to use log messages to predict failures running devices that read log files of running application and warns about the likely failure of the system; the prediction is based on the Cox Proportional Hazards (PH) model that has been applied successfully in various fields of research. We perform an initial validation of the proposed approach on real-world data.

Paper Citation

in Harvard Style

Abrahamsson P., Fronza I. and Vlasenko J. (2011). FAILURE PREDICTION USING THE COX PROPORTIONAL HAZARD MODEL . In Proceedings of the 6th International Conference on Software and Database Technologies - Volume 2: ICSOFT, ISBN 978-989-8425-77-5, pages 201-206. DOI: 10.5220/0003557802010206

in Bibtex Style

@conference{icsoft11,
author={Pekka Abrahamsson and Ilenia Fronza and Jelena Vlasenko},
title={FAILURE PREDICTION USING THE COX PROPORTIONAL HAZARD MODEL},
booktitle={Proceedings of the 6th International Conference on Software and Database Technologies - Volume 2: ICSOFT,},
year={2011},
pages={201-206},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003557802010206},
isbn={978-989-8425-77-5},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 6th International Conference on Software and Database Technologies - Volume 2: ICSOFT,
TI - FAILURE PREDICTION USING THE COX PROPORTIONAL HAZARD MODEL
SN - 978-989-8425-77-5
AU - Abrahamsson P.
AU - Fronza I.
AU - Vlasenko J.
PY - 2011
SP - 201
EP - 206
DO - 10.5220/0003557802010206