Vehicle financial loan waiting time estimation method, device, and calculation medium

Abstract

The invention provides a vehicle financial loan waiting time estimation method, a device and a calculation medium. The estimation method comprises a data collection and processing stage, a model training stage and a prediction stage, firstly, an vehicle financial loan application form is collected, feature information is extracted and encoded, and the feature information comprises a time feature, a risk level feature and a quantity related feature; then, a neural network model is constructed, the neural network model is trained and verified through a sample set, and the sample set comprises the coded value of the feature information corresponding to each vehicle financial loan application form obtained in the data collecting and processing stage and the actual waiting time; and finally, obtaining a to-be-predicted vehicle financial loan application form, extracting a corresponding feature information code, inputting the feature information code into the trained neural network model, and outputting a predicted waiting time result by the trained neural network model. Compared with a traditional isochronous pre-estimation scheme, the method has the advantages that more complex data can be processed, more accurate pre-estimation time can be obtained, and more automatic model deployment can be realized.

Description

technical field [0001] The invention belongs to the technical field of queuing prediction, and relates to a method, equipment and computing medium for predicting the waiting time of an auto finance loan based on a neural network. Background technique [0002] When customers are waiting for the approval of auto finance loans, the waiting time of uncertain time is longer than the limited waiting time of known time. The waiting time estimation model can provide accurate estimated time, let customers know the loan progress and time, and facilitate customers to determine the car purchase Arrangement, ease the dissatisfaction caused by time waiting, and improve the customer experience as much as possible. [0003] At present, related technologies have been proposed in the fields of restaurant call time estimation and takeaway waiting time prediction, but there are still the following shortcomings: [0004] (1) Due to the different types of data processed in different fields and d...

AI Technical Summary

Problems solved by technology

This solution is suitable for scenarios where the number of queues fluctuates less over time, and auto loans are affected by factors such as new car releases, holidays, auto shows, etc., and cannot take advantage of changes in real-time application data on the day, resulting in poor prediction accuracy

[0006] (3) Conventional queuing follows the first-come-first-served basis. However, in the auto finance business scenario, due to special circumstances (such as supplementary documents, customer reasons, etc.), there will be frequent urgent (jumping in the queue) situations, and the relevant waiting time estimation plan Less support for urgent cases

In addition, the processing time required for individual loan review varies greatly, and the waiting time will be affected by other applications of different levels, which makes it difficult to accurately predict the time

Images