REIMBURSEMENT FORM RISK PREDICTION METHOD, APPARATUS, TERMINAL DEVICE, AND STORAGE MEDIUM

摘要

Disclosed in the present application are a reimbursement form risk prediction method, an apparatus, a device, and a medium. The method comprises: acquiring historical reimbursement form information as sample data, and dividing same into training samples and test samples according to a preset ratio; determining the risk level of each training sample according to preset reimbursement form risk levels; with regard to training samples of each risk level, using an association rule algorithm to perform model training, to obtain an initial prediction model; using the initial prediction model to perform prediction with respect to the test samples, and in each combination manner obtained by combining a set of model parameters selected from each risk level, calculating a prediction success rate at each risk level, and a total prediction success rate and test time in each combination manner; and performing a regression analysis on the model parameters, prediction success rate, test time and total prediction success rate, to obtain a target prediction model, so as to assist an operator in efficiently identifying the risk level of a reimbursement form, improving the accuracy of predicting the risk level of a reimbursement form.