Application of Decision Tree Algorithm Method to Analyze Traffic Accident Patterns

Abstract

Traffic accidents are complex problems that involve many variables such as weather conditions, vehicle type, location, and driver behavior. With the development of data processing technology, it is possible to analyze accident data in more depth to find significant hidden patterns. The Decision Tree algorithm is applied to predict the likelihood of an accident occurring and identify the factors that contribute most to the accident. The data used consists of accident records collected from various sources, including official reports and traffic statistics. The Decision Tree algorithm was chosen due to its ability to handle both categorical and numerical data, as well as the ease of interpretation of the analysis results. The results of this study show that factors such as vehicle speed, time of occurrence, and road conditions have a significant influence on the probability of an accident occurring. The results of news extraction are analyzed by creating decision rules to determine the pattern of accidents that occur. This decision rule is in the form of a decision tree with a dataset that uses data with the highest fatalities with the imputation feature mode by concept as a method of handling missing values and toll roads as attributes, resulting in an f1-score value of 60.00% and an accuracy value of 70.40%.