Non-performing asset package value evaluation method based on historical collection data

Abstract

The invention discloses a non-performing asset package value evaluation method based on historical collection data. The method comprises the following steps: step 1, constructing an non-performing asset collection prediction model; step 2, carrying out importance sorting on variables; step 3, solving a union set of a plurality of most important variables to obtain a most important variable set; step 4, utilizing the variables in the most important variable set to obtain newly constructed derivative variables and construction rules; step 5, sampling and creating a plurality of virtual asset packages, and obtaining the derivative variables of each virtual asset package according to the step 4; step 6, combining the derivative variables in the step 5 with the total amount of collection of the virtual asset packages to obtain a non-performing asset package value evaluation model; and step 7, creating the derivative variables for a to-be-evaluated non-performing asset package, importing the derivative variables into the non-performing asset value evaluation model in the step 6, and performing asset package value prediction. According to the invention, an asset package characteristic which is crucial to model construction is abstracted, and the accuracy of a non-performing asset multi-factor regression model is ensured.

Description

technical field [0001] The invention relates to the technical field of asset evaluation, in particular to a method for evaluating the value of non-performing asset packages based on historical collection data. Background technique [0002] In a broad sense, financial non-performing assets refer to various types of equity, creditor's rights, and physical assets held by commercial banks and other licensed financial institutions that cannot bring normal economic benefits to them. The disposal methods of financial non-performing assets mainly include litigation collection, debt restructuring, creditor's rights assignment, debt-to-equity swap, asset securitization, etc. Reasonable evaluation and pricing of non-performing assets is inseparable from the disposal of non-performing assets. This valuation will become an important reference for the transaction consideration of buyers and sellers in the non-performing asset market. [0003] The "Guidelines for Valuation of Financial No...

AI Technical Summary

Problems solved by technology

Multi-factor regression analysis adopts statistical analysis method, which is more suitable for the pricing analysis of non-performing assets, but it needs a large number of non-performing asset disposal cases, that is, non-performing asset packages as the basis of theoretical research, and the accuracy of the final valuation is largely Depending on the variables selected when establishing the regression equation, if the initially selected relevant factors affecting the recovery rate of non-performing assets are wrong, the final result may be far from the actual situation

[0009] Among the existing methods, for example, method 1 and method 2 are based on the calculation or simulation of the cash flow of the case, but the cash flow is subject to many objective (various attributes of non-performing asset cases) and subjective (the debtor’s actual repayment willingness to pay) and many other factors that are difficult to reflect in the case itself, such as the debtor's current actual financial situation, job stability, family burden, health status, etc., so this method is difficult to apply to the non-performing asset package transaction evaluation

Images