Scholarlink

Due to the importance of predicting the effectiveness of banks’ telemarketing campaigns, this work presents a comparison between boosting and standard classification algorithms in this context. Accordingly, we compared the performance of two boosting Machine Learning algorithms (i.e., XGBoost and AdaBoost) with three standard Machine Learning algorithms (i.e., SVM, KNN, and Decision Trees) in predicting the effectiveness of banks’ telemarketing campaigns. The dataset used is imbalanced; therefore, four advanced data balancing techniques were utilized to address this issue. In addition, the performance of the classifiers has been evaluated using four metrics: accuracy, recall, specificity, and precision. Accordingly, the combination of XGBoost with SMOTE-ENN outperformed the other combinations, achieving the best evaluation metrics values.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Evaluating Boosting Versus Standard Classifiers in Predicting the Success of Bank Telemarketing Campaigns

  • 章节

  • 发表日期：

    2025年

查看全文
  • Huthaifa Aljawazneh,
  • Saad G. Yaseen

摘要

Due to the importance of predicting the effectiveness of banks’ telemarketing campaigns, this work presents a comparison between boosting and standard classification algorithms in this context. Accordingly, we compared the performance of two boosting Machine Learning algorithms (i.e., XGBoost and AdaBoost) with three standard Machine Learning algorithms (i.e., SVM, KNN, and Decision Trees) in predicting the effectiveness of banks’ telemarketing campaigns. The dataset used is imbalanced; therefore, four advanced data balancing techniques were utilized to address this issue. In addition, the performance of the classifiers has been evaluated using four metrics: accuracy, recall, specificity, and precision. Accordingly, the combination of XGBoost with SMOTE-ENN outperformed the other combinations, achieving the best evaluation metrics values.