Agoi, Joseph (2023) Predicting Chicago Crash Severity Using Machine Learning Algorithms and Identifying Influential Factors. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (1MB) | Preview |
Preview |
PDF (Configuration Manual)
Download (1MB) | Preview |
Abstract
This study investigates the performance comparison of diverse machine learning algorithms in predicting accident severity in Chicago, drawing from crash records spanning 2021 - 2022. To achieve the research goal, Random Forest, Support Vector Machine, and Binary Logistic Regression machine learning algorithms were used to develop predictive models for accident severity. The Random Forest Classifier was used to assess the significance of each factor and sub-factor, evaluating their weights and contributions to crash severity. The evaluation of the models built incorporated accuracy, precision, recall, and F-1 score metrics. The findings of the research show Random Forest is the best-suited model for severe crash prediction with an accuracy score of 71.78%. Support Vector Machine had an accuracy score of 69.65% while the Binary Logistics Regression Model had an accuracy score of 69.52%. Spatial and temporal factors were more prevalent in severe crash incidents.
Item Type: | Thesis (Masters) |
---|---|
Supervisors: | Name Email Sahni, Anu UNSPECIFIED |
Uncontrolled Keywords: | Machine Algorithms; Random Forest; Support Vector Machine; Binary Logistic Regression; Data Preprocessing |
Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science T Technology > TL Motor vehicles. Aeronautics. Astronautics Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning H Social Sciences > HD Industries. Land use. Labor > Specific Industries > Motor Industry |
Divisions: | School of Computing > Master of Science in Data Analytics |
Depositing User: | Ciara O'Brien |
Date Deposited: | 29 Apr 2025 16:49 |
Last Modified: | 06 May 2025 13:41 |
URI: | https://norma.ncirl.ie/id/eprint/7484 |
Actions (login required)
![]() |
View Item |