Scholarlink

While performing tasks that target particular income groups, we initially classify them by doing income classification. Most companies use statistical methods, which are time-consuming or complex to perform actions. In this research, we try to increase the accuracy of an existing system by changing the implementation using the XGBoost algorithm and the way we pre-process the data. We have utilized the adult income dataset from the UCI machine learning repository for testing, training, and evaluating our model. Notably, an accuracy of 88% was obtained from the evaluation, while the previous one was just 75.31%. To check how the model works with individual data, we have tested our machine learning model with a user persona. The implemented system has various applications in banking, government schemes, and businesses.

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

Income Classification: Using XGBoost and Evaluation of Its Performance with Accuracy and Confusion Matrix

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • A. Vijayaraj,
  • P. Kumar,
  • N. V. Gaurav,
  • R. Karthiga,
  • R. Megavannan,
  • J. Sathiamoorthy

摘要

While performing tasks that target particular income groups, we initially classify them by doing income classification. Most companies use statistical methods, which are time-consuming or complex to perform actions. In this research, we try to increase the accuracy of an existing system by changing the implementation using the XGBoost algorithm and the way we pre-process the data. We have utilized the adult income dataset from the UCI machine learning repository for testing, training, and evaluating our model. Notably, an accuracy of 88% was obtained from the evaluation, while the previous one was just 75.31%. To check how the model works with individual data, we have tested our machine learning model with a user persona. The implemented system has various applications in banking, government schemes, and businesses.