Individual loan type unfavorable asset risk rating method based on LightGBM decision tree algorithm

Abstract

The invention discloses an individual loan type unfavorable asset risk rating method based on a LightGBM decision tree algorithm. The method comprises the following steps: collecting and processing data used for risk rating; inputting the collected and processed data into a decision-making system constructed based on a LightGBM decision-making tree, wherein the decision-making system performs analysis according to the input data and a model constructed in the decision-making system; and outputting a rating result according to the analysis of the decision-making system. The Individual loan type unfavorable asset risk rating method based on the LightGBM decision tree algorithm has the beneficial effect that rating is carried out from the perspective of asset refunding possibility instead of the value of assets.

Description

technical field [0001] This application relates to a risk rating method, in particular, to a risk rating method for personal loan non-performing assets based on the LightGBM decision tree algorithm. Background technique [0002] Personal loan non-performing assets are financial non-performing assets, which refer to substandard, doubtful and loss loans held by banks, financial non-performing claims acquired or taken over by financial asset management companies, and non-performing claims held by other non-bank financial institutions. The existing non-performing asset ratings of personal loans mainly focus on the value evaluation of assets, and the follow-up action is often to dispose of assets through ABS asset subcontracting. However, there is almost no risk rating in terms of the possibility of repayment of non-performing assets, and most evaluation methods are Based on personal experience, highly subjective and incomplete. Contents of the invention [0003] In order to s...

AI Technical Summary

Problems solved by technology

The existing non-performing asset ratings of personal loans mainly focus on the value evaluation of assets, and the follow-up action is often to dispose of assets through ABS asset subcontracting. However, there is almost no risk rating in terms of the possibility of repayment of non-performing assets, and most evaluation methods are Based on personal experience, highly subjective, and incomplete

Images