本文基于UCI机器学习库中的一家银行机构营销活动的数据,以客户是否认购定期存款为响应变量,以9个描述客户信息以及社会经济状况的离散和连续指标作为解释变量建立预测模型。提出了一种改进的弹球损失模糊支持向量机(Pin-FSVM)预测模型...本文基于UCI机器学习库中的一家银行机构营销活动的数据,以客户是否认购定期存款为响应变量,以9个描述客户信息以及社会经济状况的离散和连续指标作为解释变量建立预测模型。提出了一种改进的弹球损失模糊支持向量机(Pin-FSVM)预测模型,旨在提高金融服务行业中银行识别潜在客户认购定期存款的准确性和效率。Pin-FSVM模型通过融合弹球损失函数和模糊隶属度的概念,优化了传统模糊支持向量机的性能。该模型在含噪声数据环境下维持了预测准确率,并有效处理了数据中的不确定性。在应用于银行客户认购存款的预测实践中,Pin-FSVM成功识别出更可能选择定期存款的客户,显著提升了预测效果,为银行精准识别和服务客户群体提供了有力工具。This paper is based on data from the UCI machine learning repository on the marketing activities of a banking institution, with whether a customer subscribes to a time deposit as the response variable, and nine discrete and continuous indicators describing the customer’s information as well as his socio-economic status as the explanatory variables. In this paper, an improved Pinball Loss Fuzzy Support Vector Machine (Pin-FSVM) prediction model is proposed with the aim of improving the accuracy and efficiency of banks in the financial services industry in identifying potential customers to subscribe to time deposits. The Pin-FSVM model optimises the performance of the traditional fuzzy support vector machine by incorporating the concepts of the Pinball Loss Function and the Fuzzy Affiliation Degree. The model maintains prediction accuracy in noisy data environments and effectively handles the uncertainty in the data. In the application to the practice of predicting bank customers’ subscription deposits, Pin-FSVM successfully identifies customers who are more likely to choose time deposits, which significantly improves the prediction effect and provides a powerful tool for banks to accurately identify and serve their customer groups.展开更多
文摘本文基于UCI机器学习库中的一家银行机构营销活动的数据,以客户是否认购定期存款为响应变量,以9个描述客户信息以及社会经济状况的离散和连续指标作为解释变量建立预测模型。提出了一种改进的弹球损失模糊支持向量机(Pin-FSVM)预测模型,旨在提高金融服务行业中银行识别潜在客户认购定期存款的准确性和效率。Pin-FSVM模型通过融合弹球损失函数和模糊隶属度的概念,优化了传统模糊支持向量机的性能。该模型在含噪声数据环境下维持了预测准确率,并有效处理了数据中的不确定性。在应用于银行客户认购存款的预测实践中,Pin-FSVM成功识别出更可能选择定期存款的客户,显著提升了预测效果,为银行精准识别和服务客户群体提供了有力工具。This paper is based on data from the UCI machine learning repository on the marketing activities of a banking institution, with whether a customer subscribes to a time deposit as the response variable, and nine discrete and continuous indicators describing the customer’s information as well as his socio-economic status as the explanatory variables. In this paper, an improved Pinball Loss Fuzzy Support Vector Machine (Pin-FSVM) prediction model is proposed with the aim of improving the accuracy and efficiency of banks in the financial services industry in identifying potential customers to subscribe to time deposits. The Pin-FSVM model optimises the performance of the traditional fuzzy support vector machine by incorporating the concepts of the Pinball Loss Function and the Fuzzy Affiliation Degree. The model maintains prediction accuracy in noisy data environments and effectively handles the uncertainty in the data. In the application to the practice of predicting bank customers’ subscription deposits, Pin-FSVM successfully identifies customers who are more likely to choose time deposits, which significantly improves the prediction effect and provides a powerful tool for banks to accurately identify and serve their customer groups.
