Pricing method and device based on neural network, electronic equipment and storage medium

Abstract

The invention relates to the technical field of artificial intelligence, and particularly discloses a pricing method and device based on a neural network, electronic equipment and a storage medium, and the pricing method comprises the steps: carrying out the preprocessing of an initial sample set, and obtaining a training sample set, wherein the initial sample set is a data set which comprises the identification of the resource returning capability and resource returning willingness of a user; determining model training parameters according to the training sample set; inputting the training sample set and the model training parameters into a long and short memory neural network for training to obtain a recycled resource prediction model; acquiring historical resource return data and basic information of assets to be priced; determining a prediction duration according to the basic information; inputting historical resource return data, basic information and the prediction duration into the recycled resource prediction model to obtain a first value of the resource returned by the holder of the to-be-priced asset in a time period determined by the prediction duration; and taking the first numerical value as the reference price of the to-be-priced asset.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to a neural network-based pricing method, device, electronic equipment and storage medium. Background technique [0002] In recent years, with the rapid development of retail banking business, the scale of consumer loans and personal credit card overdrafts has grown rapidly, leading to a rise in the scale of personal non-performing loans. Especially under the impact of the new crown pneumonia epidemic, the number of overdue credit cards and non-performing loans for personal consumption has surged. Based on this, it is imminent to accelerate the disposal of personal non-performing loans. [0003] At present, banks have relatively simple channels for disposing of personal non-performing assets, and can only carry out collection or write-off, or securitize personal non-performing loan assets. However, the threshold for asset securitization of personal non-performing l...

AI Technical Summary

Problems solved by technology

[0003] At present, banks have relatively simple channels for disposing of personal non-performing assets, and can only carry out collection or write-off, or securitize personal non-performing loan assets

However, the threshold for asset securitization of personal non-performing loans is relatively high, and the overall cost is also relatively high. In practical applications, not many successful issuances

Images