Comparison of Statistical and Machine-Learning Models on Road Traffic Accident Severity Classification
Portugal has the sixth highest road fatality rate among European Union members. This is a problem of different dimensions with serious consequences in people’s lives. This study analyses daily data from police and government authorities on road traffic accidents that occurred between 2016 and 2019 i...
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | Computers |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-431X/11/5/80 |
| _version_ | 1797500586095017984 |
|---|---|
| author | Paulo Infante Gonçalo Jacinto Anabela Afonso Leonor Rego Vitor Nogueira Paulo Quaresma José Saias Daniel Santos Pedro Nogueira Marcelo Silva Rosalina Pisco Costa Patrícia Gois Paulo Rebelo Manuel |
| author_facet | Paulo Infante Gonçalo Jacinto Anabela Afonso Leonor Rego Vitor Nogueira Paulo Quaresma José Saias Daniel Santos Pedro Nogueira Marcelo Silva Rosalina Pisco Costa Patrícia Gois Paulo Rebelo Manuel |
| author_sort | Paulo Infante |
| collection | DOAJ |
| description | Portugal has the sixth highest road fatality rate among European Union members. This is a problem of different dimensions with serious consequences in people’s lives. This study analyses daily data from police and government authorities on road traffic accidents that occurred between 2016 and 2019 in a district of Portugal. This paper looks for the determinants that contribute to the existence of victims in road traffic accidents, as well as the determinants for fatalities and/or serious injuries in accidents with victims. We use logistic regression models, and the results are compared to the machine-learning model results. For the severity model, where the response variable indicates whether only property damage or casualties resulted in the traffic accident, we used a large sample with a small imbalance. For the serious injuries model, where the response variable indicates whether or not there were victims with serious injuries and/or fatalities in the traffic accident with victims, we used a small sample with very imbalanced data. Empirical analysis supports the conclusion that, with a small sample of imbalanced data, machine-learning models generally do not perform better than statistical models; however, they perform similarly when the sample is large and has a small imbalance. |
| first_indexed | 2024-03-10T03:05:56Z |
| format | Article |
| id | doaj.art-9908e8c173f54987a3dddd11de49724d |
| institution | Directory Open Access Journal |
| issn | 2073-431X |
| language | English |
| last_indexed | 2024-03-10T03:05:56Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Computers |
| spelling | doaj.art-9908e8c173f54987a3dddd11de49724d2023-11-23T10:33:43ZengMDPI AGComputers2073-431X2022-05-011158010.3390/computers11050080Comparison of Statistical and Machine-Learning Models on Road Traffic Accident Severity ClassificationPaulo Infante0Gonçalo Jacinto1Anabela Afonso2Leonor Rego3Vitor Nogueira4Paulo Quaresma5José Saias6Daniel Santos7Pedro Nogueira8Marcelo Silva9Rosalina Pisco Costa10Patrícia Gois11Paulo Rebelo Manuel12CIMA, IIFA, University of Évora, 7000-671 Évora, PortugalCIMA, IIFA, University of Évora, 7000-671 Évora, PortugalCIMA, IIFA, University of Évora, 7000-671 Évora, PortugalDepartment of Matematics, ECT, University of Évora, 7000-671 Évora, PortugalAlgoritmi Research Centre, University of Évora, 7000-671 Évora, PortugalAlgoritmi Research Centre, University of Évora, 7000-671 Évora, PortugalAlgoritmi Research Centre, University of Évora, 7000-671 Évora, PortugalDepartment of Informatics, ECT, University of Évora, 7000-671 Évora, PortugalICT, IIFA, University of Évora, 7000-671 Évora, PortugalICT, IIFA, University of Évora, 7000-671 Évora, PortugalCICS.NOVA.UEVORA, IIFA, University of Évora, 7000-208 Évora, PortugalDepartment of Visual Arts and Design, EA, University of Évora, 7000-208 Évora, PortugalCIMA, IIFA, University of Évora, 7000-671 Évora, PortugalPortugal has the sixth highest road fatality rate among European Union members. This is a problem of different dimensions with serious consequences in people’s lives. This study analyses daily data from police and government authorities on road traffic accidents that occurred between 2016 and 2019 in a district of Portugal. This paper looks for the determinants that contribute to the existence of victims in road traffic accidents, as well as the determinants for fatalities and/or serious injuries in accidents with victims. We use logistic regression models, and the results are compared to the machine-learning model results. For the severity model, where the response variable indicates whether only property damage or casualties resulted in the traffic accident, we used a large sample with a small imbalance. For the serious injuries model, where the response variable indicates whether or not there were victims with serious injuries and/or fatalities in the traffic accident with victims, we used a small sample with very imbalanced data. Empirical analysis supports the conclusion that, with a small sample of imbalanced data, machine-learning models generally do not perform better than statistical models; however, they perform similarly when the sample is large and has a small imbalance.https://www.mdpi.com/2073-431X/11/5/80injurylogistic regressionmachine learningroad traffic accidentsseverity of victims |
| spellingShingle | Paulo Infante Gonçalo Jacinto Anabela Afonso Leonor Rego Vitor Nogueira Paulo Quaresma José Saias Daniel Santos Pedro Nogueira Marcelo Silva Rosalina Pisco Costa Patrícia Gois Paulo Rebelo Manuel Comparison of Statistical and Machine-Learning Models on Road Traffic Accident Severity Classification Computers injury logistic regression machine learning road traffic accidents severity of victims |
| title | Comparison of Statistical and Machine-Learning Models on Road Traffic Accident Severity Classification |
| title_full | Comparison of Statistical and Machine-Learning Models on Road Traffic Accident Severity Classification |
| title_fullStr | Comparison of Statistical and Machine-Learning Models on Road Traffic Accident Severity Classification |
| title_full_unstemmed | Comparison of Statistical and Machine-Learning Models on Road Traffic Accident Severity Classification |
| title_short | Comparison of Statistical and Machine-Learning Models on Road Traffic Accident Severity Classification |
| title_sort | comparison of statistical and machine learning models on road traffic accident severity classification |
| topic | injury logistic regression machine learning road traffic accidents severity of victims |
| url | https://www.mdpi.com/2073-431X/11/5/80 |
| work_keys_str_mv | AT pauloinfante comparisonofstatisticalandmachinelearningmodelsonroadtrafficaccidentseverityclassification AT goncalojacinto comparisonofstatisticalandmachinelearningmodelsonroadtrafficaccidentseverityclassification AT anabelaafonso comparisonofstatisticalandmachinelearningmodelsonroadtrafficaccidentseverityclassification AT leonorrego comparisonofstatisticalandmachinelearningmodelsonroadtrafficaccidentseverityclassification AT vitornogueira comparisonofstatisticalandmachinelearningmodelsonroadtrafficaccidentseverityclassification AT pauloquaresma comparisonofstatisticalandmachinelearningmodelsonroadtrafficaccidentseverityclassification AT josesaias comparisonofstatisticalandmachinelearningmodelsonroadtrafficaccidentseverityclassification AT danielsantos comparisonofstatisticalandmachinelearningmodelsonroadtrafficaccidentseverityclassification AT pedronogueira comparisonofstatisticalandmachinelearningmodelsonroadtrafficaccidentseverityclassification AT marcelosilva comparisonofstatisticalandmachinelearningmodelsonroadtrafficaccidentseverityclassification AT rosalinapiscocosta comparisonofstatisticalandmachinelearningmodelsonroadtrafficaccidentseverityclassification AT patriciagois comparisonofstatisticalandmachinelearningmodelsonroadtrafficaccidentseverityclassification AT paulorebelomanuel comparisonofstatisticalandmachinelearningmodelsonroadtrafficaccidentseverityclassification |