本文在互联网金融蓬勃发展的背景下,针对客户认购定期存款的行为预测进行了深入研究。鉴于互联网金融环境下客户行为数据的复杂性和不确定性,本文创新性地提出了一种基于密度权重与直觉模糊孪生支持向量机的鲁棒分类器模型。该模型通过...本文在互联网金融蓬勃发展的背景下,针对客户认购定期存款的行为预测进行了深入研究。鉴于互联网金融环境下客户行为数据的复杂性和不确定性,本文创新性地提出了一种基于密度权重与直觉模糊孪生支持向量机的鲁棒分类器模型。该模型通过引入密度权重来优化样本空间的分布,增强了对不均衡数据集的处理能力;同时,结合直觉模糊集理论,有效处理了数据中的噪声和异常值,提升了模型的预测精度。在互联网金融竞争加剧的当下,准确预测客户认购定期存款的行为,有助于银行及金融机构优化产品设计、制定精准的营销策略,进而提升客户满意度和市场份额。实验结果表明,该分类器显著提高了客户认购定期存款预测的准确性和鲁棒性,为银行精准识别和服务客户群体提供了有力工具。In this paper, an in-depth study is conducted on the prediction of customers’ behaviour in subscribing time deposits in the context of the booming development of Internet finance. In view of the complexity and uncertainty of customer behavioural data in the Internet financial environment, this paper innovatively proposes a robust classifier model based on density weights and intuitionistic fuzzy twin support vector machine. The model optimises the distribution of the sample space by introducing density weights, which enhances the ability to handle unbalanced datasets;at the same time, combining with the intuitionistic fuzzy set theory, it effectively handles the noise and outliers in the data, and improves the prediction accuracy of the model. At a time of intensified competition in Internet finance, accurately predicting the behaviour of customers subscribing to time deposits helps banks and financial institutions to optimize product design and formulate precise marketing strategies, which in turn enhances customer satisfaction and market share. The experimental results show that the classifier significantly improves the accuracy and robustness of the prediction of customer subscription to time deposits, and provides a powerful tool for banks to accurately identify and serve their customer groups.展开更多
文摘本文在互联网金融蓬勃发展的背景下,针对客户认购定期存款的行为预测进行了深入研究。鉴于互联网金融环境下客户行为数据的复杂性和不确定性,本文创新性地提出了一种基于密度权重与直觉模糊孪生支持向量机的鲁棒分类器模型。该模型通过引入密度权重来优化样本空间的分布,增强了对不均衡数据集的处理能力;同时,结合直觉模糊集理论,有效处理了数据中的噪声和异常值,提升了模型的预测精度。在互联网金融竞争加剧的当下,准确预测客户认购定期存款的行为,有助于银行及金融机构优化产品设计、制定精准的营销策略,进而提升客户满意度和市场份额。实验结果表明,该分类器显著提高了客户认购定期存款预测的准确性和鲁棒性,为银行精准识别和服务客户群体提供了有力工具。In this paper, an in-depth study is conducted on the prediction of customers’ behaviour in subscribing time deposits in the context of the booming development of Internet finance. In view of the complexity and uncertainty of customer behavioural data in the Internet financial environment, this paper innovatively proposes a robust classifier model based on density weights and intuitionistic fuzzy twin support vector machine. The model optimises the distribution of the sample space by introducing density weights, which enhances the ability to handle unbalanced datasets;at the same time, combining with the intuitionistic fuzzy set theory, it effectively handles the noise and outliers in the data, and improves the prediction accuracy of the model. At a time of intensified competition in Internet finance, accurately predicting the behaviour of customers subscribing to time deposits helps banks and financial institutions to optimize product design and formulate precise marketing strategies, which in turn enhances customer satisfaction and market share. The experimental results show that the classifier significantly improves the accuracy and robustness of the prediction of customer subscription to time deposits, and provides a powerful tool for banks to accurately identify and serve their customer groups.
