Credit risk assessment method and system, terminal equipment and storage medium

The invention discloses a credit risk assessment method and system, terminal equipment and a storage medium. The method comprises the following steps: acquiring a to-be-predicted sample; the to-be-predicted sample is input into a pre-created credit risk model, the default probability of the to-be-predicted sample at each time point is obtained, early warning information is output according to the default probability, and the credit risk model is obtained through training based on an integrated learning algorithm and a semi-parameter regression model. The problem that an existing risk detection method cannot well predict the possibility of customer default at a specific time point is solved, and the prediction accuracy is improved. 本发明公开了一种信贷风险评估方法、系统、终端设备及存储介质。该方法包括：获取待预测样本；将所述待预测样本输入预先创建的信贷风险模型，得到所述待预测样本各时点的违约概率，并根据所述违约概率输出预警信息，其中，所述信贷风险模型基于集成学习算法、半参数回归模型训练得到。本发明解决了现有风险检测方法不能很好地预测具体时间点客户发生违约的可能性的问题，提高预测的准确性。