A Hybrid AdaBoost-Random Forest Framework for Telecom Fraud Detection using CDRs

Today, telecommunications fraud has emerged as a major challenge for operators, resulting in billions of dollars in financial losses annually. the presence of substantial noise and severe class imbalance between legitimate and fraudulent data complicates the identification of fraud patterns within massive volumes of Call Detail Records (CDRs). This paper proposes a hybrid ensemble model, termed Hybrid AdaBoost-RF, for telecommunication fraud detection. In this model, Random Forest is employed as the base learner within the AdaBoost framework to enhance the model's robustness against noise. Furthermore, the SMOTE technique is utilized to address the class imbalance problem. Additionally, we applied a decision threshold tuned on the training predictions to improve the model's sensitivity in detecting fraudulent behavior. Experimental results demonstrate that the proposed model outperforms existing methods in recent research, achieving a Recall of ۰.۸۷ and an F۱-Score of ۰.۸۶ on the test partition of the evaluated CDR dataset using the adopted experimental protocol achieving a Recall of ۰.۸۷ and an F۱-Score of ۰.۸۶. Moreover, the Area Under the Curve (AUC) for ROC and PR metrics reach ۰.۹۷۷۷ and ۰.۸۷۳۳, respectively, validating the high efficiency of the proposed model.

کلیدواژه ها:

Telecommunications Fraud Detection ، Ensemble learning ، Call Detail Record (CDR) ، Imbalanced Data ، SMOTE