Research on Intelligent Classification Algorithm for Telecom Network Fraud Related Individuals

This study analyzes telecom network fraud cases using the K-means clustering algorithm and the Chi-squared Automatic Interaction detection (CHAID) decision tree algorithm to identify the characteristics of victims and suspects and the factors influencing the amount of fraud. Through clustering analysis of victim and suspect attributes, it was found that there are five main types of victims, while suspects involved in network fraud are generally young and have a low level of education. In the decision tree analysis, it was found that the monthly income of victims has the greatest impact on the amount of fraud, followed by the education level and criminal history of the suspects. Based on these results, it can be predicted that victims with lower education levels and higher monthly incomes are more likely to experience higher amounts of fraud, while suspects who have been exposed to the internet for a longer time and have lower education levels are more likely to engage in criminal activities.