Data mining to determine the most influential factors in the occurrence of traffic accidents in Ecuador in the year 2020

Authors

  • Yulissa Torres-Quezada Carrera de Ingeniería en Sistema/Computación, Universidad Nacional de Loja, Loja, Ecuador.

DOI:

https://doi.org/10.54753/cedamaz.v11i2.1181

Keywords:

Data mining, KDD methodology, Decision trees, Neural networks, Bayesian networks.

Abstract

Currently, the occurrence of traffic accidents represents a public health problem at the national and regional level, causing human losses, in addition to the fact that every day is increasing worldwide, which is why it is essential and important to propose a study to determine what are the factors that cause the occurrence of traffic accidents. In this research work, data mining is applied to determine the most influential factors in the occurrence of traffic accidents in Ecuador in the year 2020, this was carried out using five phases of the Knowledge Discovery in Databases (KDD) methodology consisting of: information search, data collection, database cleansing, application of data mining techniques and interpretation and presentation of results, these, used for the discovery of hidden patterns in the dataset, which was collected by the National Traffic Agency (ANT) and has a total of 418 variables and 16972 records of events recorded on traffic crashes in Ecuador. Seven data mining techniques were applied, such as: CHAID, Exhaustive CHAID, CRT, Multilayer Perceptron, Radial Basis Function, Naive Bayes, and BayesNet. The Exhaustive CHAID algorithm was the one that obtained the best results with which the most important patterns in the data were identified and the possible associations between the collected variables were evaluated. Finally, the human factor was determined to be the most influential factor with a probability of occurrence of 69.64%.

Metrics

Metrics Loading ...

Published

2021-12-24

How to Cite

Torres-Quezada, Y. . (2021). Data mining to determine the most influential factors in the occurrence of traffic accidents in Ecuador in the year 2020. CEDAMAZ, 11(2), 124 – 132. https://doi.org/10.54753/cedamaz.v11i2.1181

Issue

Section

Ciencias exactas e ingenierías