Method and device for predicting user loss and computer storage medium

The invention provides a method and device for predicting user loss and a computer storage medium. The method comprises the steps of obtaining historical data generated by a shared automobile leasing APP of a to-be-predicted user, extracting target features of the to-be-predicted user from the historical data, inputting the target features into a preset model, and then calculating the loss probability of the to-be-predicted user. As the target features accurately and comprehensively reflect the shared car rental scene, the target feature prediction probability based on the model has high accuracy. And moreover, the data processing speed of the model is higher, so the user loss prediction efficiency is improved while the accuracy of the prediction result is ensured, and the method has important practical significance for a shared automobile rental scene. 本申请提供了用户流失的预测方法、装置和计算机存储介质。通过获取待预测用户的共享汽车租赁APP生成的历史数据，从历史数据中提取待预测用户的目标特征，并将目标特征输入预设模型，然后计算待预测用户的流失概率。由于目标特征准确全面反映共享汽车租赁场景，基于此模型的目标特征预测概率具有较高的准确性。并且，模型处理数据的速度较