Road Traffic Accident
Waqas Ali
Road_Traffic_Accident
Road Traffic Severity Classification Prediction
Description:
This dataset is collected from Addis Ababa Sub-city police departments for master's research work. The data set has been prepared from manual records of road trafic accidents of the year 2017-20. All the sensitive information has been excluded during data encoding and finally it has 32 features and 12316 instances of the accident. Then it is preprocessed and for identification of major causes of the accident by analyzing it using different machine learning classification algorithms.
Problem Statement:
The target feature is Accident_severitywhich is a multi-class variable. The task is to classify this variable based on the other 31 features step-by-step by going through each day's task. Your metric for evaluation will be f1-score
What is F1 score?
F1 score is a machine learning evaluation metric that measures a model’s accuracy. It combines the precision and recall scores of a model.
Training with different Model
1- XGBClassifier
2- KNeighborsClassifier
3- DecisionTreeClassifie
4- ExtraTreeClassifier
5- RandomForestClassifier
According to my observation, I got the best results with ExtraTreesClassifier and xgboost model showing the best result**
Model
XGB => PrecisionScore = 0.9294 AccScore = 0.9283 f1_Score = 0.9281
ExtraDT => PrecisionScore = 0.9379 AccScore = 0.9373 f1_Score = 0.9373
Like this project
Posted Mar 18, 2025
The target feature is Accident_severitywhich is a multi-class variable. Your metric for evaluation will be f1-score
