Analysis of Traffic Accidents Based on the Integration Model
Download PDF


Stacking integrated learning
Data analysis
Traffic safety



Submitted : 2023-12-19
Accepted : 2024-01-03
Published : 2024-01-18


To enhance the safety of road traffic operations, this paper proposed a model based on stacking integrated learning utilizing American road traffic accident statistics. Initially, the process involved data cleaning, transformation, and normalization. Subsequently, various classification models were constructed, including logistic regression, k-nearest neighbors, gradient boosting, decision trees, AdaBoost, and extra trees models. Evaluation metrics such as accuracy, precision, recall, F1 score, and Hamming loss were employed. Upon analysis, the passive-aggressive classifier model exhibited superior comprehensive indices compared to other models. Based on the model’s output results, an in-depth examination of the factors influencing traffic accidents was conducted. Additionally, measures and suggestions aimed at reducing the incidence of severe traffic accidents were presented. These findings served as a valuable reference for mitigating the occurrence of traffic accidents.


Wang Y, Liu Q, Cheng W, 2022, Prediction of Road Traffic Accident Severity Based on the XGBoost Algorithm. Software Guide, 21(5): 84–88.

Cao Y, Zhang B, Li S, 2022, Analysis of the Factors Influencing the Severity of Urban Road Traffic Accidents in the Ice and Snow Season. Journal of Dalian Jiao Tong University, 43(4): 8–13.

Meng Y, Zhang X, Qing G, et al., 2022, Analysis of Influencing Factors on the Consequences of Highway Traffic Accidents Based on Logistic Regression. Journal of Wuhan University of Technology (Transportation Science and Engineering Edition), 46(1): 12–16.

Chen L, Li C, Zhan L, et al., 2022, Analysis and Prediction of Urban Road Traffic Accidents. Journal of Chang’an University (Natural Science Edition), 42(4): 98–107.

Zhu H, Li H, Chi Y, et al., 2022, A Method for White Layer Prediction of Hard Car Surface Based on Gradient Lifting Decision Tree. Shanghai Municipality, CN115099266A.

Liu G, Gao Y, 2021, Review of Intrusion Detection Methods Based on Machine Learning. Information and Computer (Theoretical Edition), 33(10): 34–37.

Zhang P, Xu S, 2008, Exploring the Method of Road Traffic Safety Management and Management Planning in Heilongjiang Reclamation Area. Heilongjiang Science and Technology Information, 2008(19): 82.