Prediction of Crash Injury Severity in Florida's Interstate-95

TL;DR

This study analyzes traffic crash data on Florida's I-95 from 2016 to 2021, using classification models to predict injury severity and identify contributing factors, with AdaBoost showing superior performance.

Contribution

It introduces a comparative analysis of classification methods for injury severity prediction and employs SHAP values for model interpretability.

Findings

AdaBoost achieved highest recall and AUC scores.

Logistic regression used for feature selection.

Model insights can inform safety improvements.

Abstract

Drivers can sustain serious injuries in traffic accidents. In this study, traffic crashes on Florida's Interstate-95 from 2016 to 2021 were gathered, and several classification methods were used to estimate the severity of driver injuries. In the feature selection method, logistic regression was applied. To compare model performances, various model assessment matrices such as accuracy, recall, and area under curve (AUC) were developed. The Adaboost algorithm outperformed the others in terms of recall and AUC. SHAP values were also generated to explain the classification model's results. This analytical study can be used to examine factors that contribute to the severity of driver injuries in crashes.