Explaining and predicting workplace accidents using data-mining techniques

T. Rivas

doi:10.1016/j.ress.2011.03.006

Explaining and predicting workplace accidents using data-mining techniques

2011-07-01

97

PRE

AI

DOI：10.1016/j.ress.2011.03.006

Original

Original request for help

Save

Abstract

En 中文

Current research into workplace risk is mainly conducted using conventional descriptive statistics, which, however, fail to properly identify cause-effect relationships and are unable to construct models that could predict accidents. The authors of the present study modelled incidents and accidents in two companies in the mining and construction sectors in order to identify the most important causes of accidents and develop predictive models. Data-mining techniques (decision rules, Bayesian networks, support vector machines and classification trees) were used to model accident and incident data compiled from the mining and construction sectors and obtained in interviews conducted soon after an incident/accident occurred. The results were compared with those for a classical statistical techniques (logistic regression), revealing the superiority of decision rules, classification trees and Bayesian networks in predicting and identifying the factors underlying accidents/incidents. (C) 2011 Elsevier Ltd. All rights reserved.

Keywords:

Workplace accidents

Classification trees

Data mining

Bayesian networks

Support vector machines

Mine and construction safety

Explaining and predicting workplace accidents using data-mining techniques

Abstract

AI Summary

Journal

Organization