CN111861693A - Mortgage asset calculation method and device, electronic equipment and storage medium - Google Patents
Mortgage asset calculation method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN111861693A CN111861693A CN201910354999.2A CN201910354999A CN111861693A CN 111861693 A CN111861693 A CN 111861693A CN 201910354999 A CN201910354999 A CN 201910354999A CN 111861693 A CN111861693 A CN 111861693A
- Authority
- CN
- China
- Prior art keywords
- loan
- data
- mortgage
- determining
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004364 calculation method Methods 0.000 title claims abstract description 16
- 239000003999 initiator Substances 0.000 claims abstract description 76
- 238000000034 method Methods 0.000 claims abstract description 44
- 230000032683 aging Effects 0.000 claims description 36
- 230000002596 correlated effect Effects 0.000 claims description 18
- 230000008569 process Effects 0.000 claims description 17
- 230000000875 corresponding effect Effects 0.000 claims description 14
- 238000012847 principal component analysis method Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 230000009467 reduction Effects 0.000 description 5
- 230000036962 time dependent Effects 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 230000001186 cumulative effect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000000513 principal component analysis Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 238000012790 confirmation Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000013139 quantization Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000000052 comparative effect Effects 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000036961 partial effect Effects 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
Abstract
The application provides a mortgage asset calculation method and device, electronic equipment and a storage medium, wherein the method comprises the following steps: determining a loan trust value of a loan initiator; determining a popularity value of a target vehicle of the loan initiator, wherein loan funds of a loan initiated by the loan initiator are used for purchasing the target vehicle; calculating a mortgage proportion based on the loan confidence value and the heat value; and determining the mortgage property of the loan initiator according to the mortgage proportion and the loan fund. According to the method and the system, the mortgage proportion is calculated based on the loan trust value (used for measuring the credit condition and the repayment capability of the loan initiator) of the loan initiator and the heat value of the target vehicle, so that the finally determined mortgage property needing to be delivered by the loan initiator is more reasonable, and the risk of the lender of the loan fund can be effectively reduced.
Description
Technical Field
The present application relates to the field of computer network technologies, and in particular, to a method and an apparatus for calculating mortgage assets, an electronic device, and a storage medium.
Background
The dealer can loan the car platform for sale as a batch of vehicles by delivering certain mortgage assets to the car platform. For example, a car dealer may pay a certain amount of money as a guarantee fee to the car platform, thereby lending the car platform with loan money for purchasing a car, and then repaying the loan by selling the money earned by the car. In the related art, it is common that a car dealer pays a deposit in a fixed proportion of loan funds, and the fixed proportion is set by an operator of a car platform according to experience. Therefore, the situation that the proportion is set unreasonably is easy to occur, so that risks are easily caused to the automobile platform, and the loss of the automobile platform is increased.
Disclosure of Invention
In view of the above, the present application provides a method and an apparatus for calculating a mortgage asset, an electronic device, and a storage medium.
In order to achieve the above purpose, the present application provides the following technical solutions:
according to a first aspect of the present application, a method for calculating a mortgage asset is provided, including:
determining a loan trust value of a loan initiator;
determining a popularity value of a target vehicle of the loan initiator, wherein loan funds of a loan initiated by the loan initiator are used for purchasing the target vehicle;
Calculating a mortgage proportion based on the loan confidence value and the heat value;
and determining the mortgage property of the loan initiator according to the mortgage proportion and the loan fund.
Optionally, the determining the loan trust value of the loan initiator includes:
determining a weight fraction of each data associated with the loan confidence value;
and calculating the loan trust value of the loan initiator based on the weight ratio of each data.
Optionally, the determining a weight ratio of each data associated with the loan trust value includes:
determining an aging weight for each data associated with the loan trust value; the aging weight of any data is in negative correlation with the corresponding time interval, and the time interval of any data is the time between the occurrence moment of any data and the current moment;
determining importance weights of the data associated with the loan trust value using analytic hierarchy process;
determining a weight ratio for each data associated with the loan trust value based on the age weight and the importance weight.
Optionally, the aging weight is calculated by the following formula:
wherein f (t) represents an aging weight of the data;
tnowRepresents the current time;
t0indicating the occurrence time of the data;
tstartrepresenting the earliest moment of occurrence of all data associated with the loan confidence value;
gamma denotes preset overfitting adjustment parameters.
Optionally, the mortgage proportion is negatively correlated with the loan trust value, and the mortgage proportion is negatively correlated with the heat value.
Alternatively to this, the first and second parts may,
further comprising: obtaining a current market environment coefficient, the market environment coefficient being associated with a sales situation for the target vehicle;
the determining the mortgage property of the loan initiator according to the mortgage proportion and the loan fund comprises the following steps: and adjusting the mortgage proportion according to the market environment coefficient, and determining the mortgage property of the loan initiator based on the adjusted mortgage proportion and the loan fund.
Optionally, the loan trust value is associated with the loan originator's basic data, property data, historical loan data, credit data.
According to a second aspect of the present application, a computing device for mortgage of assets is proposed, comprising:
a trust value determination unit for determining a loan trust value of a loan initiator;
the system comprises a popularity value confirmation unit, a loan fund collection unit and a loan fund collection unit, wherein the popularity value confirmation unit is used for determining the popularity value of a target vehicle of the loan initiator, and the loan fund of the loan initiated by the loan initiator is used for purchasing the target vehicle;
A proportion calculation unit which calculates a mortgage proportion based on the loan trust value and the heat value;
and the mortgage determining unit determines the mortgage assets of the loan initiator according to the mortgage proportion and the loan funds.
Optionally, the trust value determining unit is specifically configured to:
determining a weight fraction of each data associated with the loan confidence value;
and calculating the loan trust value of the loan initiator based on the weight ratio of each data.
Optionally, the trust value determining unit is further configured to:
determining an aging weight for each data associated with the loan trust value; the aging weight of any data is in negative correlation with the corresponding time interval, and the time interval of any data is the time between the occurrence moment of any data and the current moment;
determining importance weights of the data associated with the loan trust value using analytic hierarchy process;
determining a weight ratio for each data associated with the loan trust value based on the age weight and the importance weight.
Optionally, the aging weight is calculated by the following formula:
wherein f (t) represents an aging weight of the data;
tnowRepresents the current time;
t0indicating the occurrence time of the data;
tstartrepresenting the earliest moment of occurrence of all data associated with the loan confidence value;
gamma denotes preset overfitting adjustment parameters.
Optionally, the mortgage proportion is negatively correlated with the loan trust value, and the mortgage proportion is negatively correlated with the heat value.
Alternatively to this, the first and second parts may,
further comprising: a coefficient acquisition unit that acquires a current market environment coefficient associated with a sales situation for the target vehicle;
the mortgage determination unit is specifically configured to: and adjusting the mortgage proportion according to the market environment coefficient, and determining the mortgage property of the loan initiator based on the adjusted mortgage proportion and the loan fund.
Optionally, the loan trust value is associated with the loan originator's basic data, property data, historical loan data, credit data.
According to a third aspect of the present application, there is provided an electronic device comprising:
a processor;
a memory for storing processor-executable instructions;
wherein, the processor implements the calculation method of the mortgage assets by executing the executable instructions.
According to a fourth aspect of the embodiments of the present disclosure, there is provided a computer readable storage medium having stored thereon computer instructions which, when executed by a processor, implement the steps of the method for calculating mortgage assets as described in any one of the above embodiments.
According to the technical scheme, the mortgage proportion is calculated based on the loan trust value (used for measuring the credit condition and the repayment capability of the loan initiator) of the loan initiator and the heat value of the target vehicle, so that the finally determined mortgage assets needing to be delivered by the loan initiator are more reasonable, and the risk of the lender of the loan funds can be effectively reduced. Furthermore, the loan trust value is determined by integrating the aging weight and the importance weight of each data associated with the loan trust value, so that the determined loan trust value is more comprehensive and reasonable. Meanwhile, the effectiveness and accuracy of the data reflecting the credit condition and the repayment capacity of the loan initiator are reduced along with the increase of time, and the finally calculated loan trust value can more accurately reflect the credit condition and the repayment capacity of the loan initiator by setting the aging weight of any data to be negatively correlated with the time interval between the occurrence moment corresponding to any data and the current moment.
Drawings
Fig. 1 is a flow chart illustrating a method of mortgage asset computation according to an exemplary embodiment of the present application.
Fig. 2 is a flow chart illustrating another method of computing mortgage assets according to an exemplary embodiment of the present application.
Fig. 3 is a schematic structural diagram of an electronic device according to an exemplary embodiment of the present application.
FIG. 4 is a block diagram of a computing device for mortgage of assets in accordance with an exemplary embodiment of the present application.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It is to be understood that although the terms first, second, third, etc. may be used herein to describe various information, such information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present application. The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination", depending on the context.
Referring to fig. 1, fig. 1 is a flow chart illustrating a method for calculating mortgage assets according to an exemplary embodiment of the present application. As shown in fig. 1, the method may be applied to a background server of an automobile platform, and may include the following steps:
In this embodiment, the loan trust value of the loan originator is used to measure the credit and repayment abilities of the loan originator. As an exemplary embodiment, the basic data of the loan originator, the property data, the historical loan data, the credit data may be used as the basis for determining the loan trust value. Taking the loan initiator as a car dealer as an example, the basic data of the loan initiator may include admission information of the car dealer in the system and operation information of the car dealer; for example, the access information includes the age, sex, education background, working age, etc. of the car and business person, and the operation information may include the operation age, shop area, main brand, number of salesmen, sales performance, etc. The asset data may include running funds, real estate, deposits, etc. over a preset period of time. The historical loan data may include cumulative loan times, cumulative loan amounts, cumulative loan vehicles, and the like. The credit data may include repayment time, number of defaults, length of default, amount of default, etc. Of course, the specific content of each data can be flexibly set according to the actual situation, and the application does not limit this.
Further, after the specific information of the basic data, the property data, the historical loan data and the credit data of the loan initiator is obtained, the specific information of the data can be subjected to dimensionality reduction processing by adopting a principal component analysis method (also called principal component analysis), so that the dimensionality reduction effect is achieved. Specifically, the plurality of associated information can be combined into a small number of pieces of mutually independent integrated information (i.e., principal components), wherein each principal component can reflect most of the information of the original information and contains information that is not repeated. For example, after the specific information of the data is obtained, the variables with higher correlation in the specific information can be converted into the independent or uncorrelated variables by the principal component analysis method, and usually, a few new variables (i.e., principal components) which are less than the original variables and can explain the variables contained in most information are selected. The correlation between each variable can be calculated by using a principal component analysis method, and the variable with higher correlation is replaced by other variables through linear weighting, so that the variable in the correlation information is reduced from high dimension to low dimension, and the subsequent calculation amount is reduced.
In this embodiment, before performing the dimension reduction processing on the associated specific information, operations such as converting, completing, deleting, and cleaning may be performed on the specific information. Specifically, the service data is converted into a specific numerical value for quantization, and based on the quantized specific information, when the data loss rate of any information in the specific information is within a first preset range, the medium number of the any information is adopted to complement the lost data; when the data loss rate of any one of the specific information exceeds the upper limit value of the first preset range, deleting the any one of the specific information; when the data missing rate of any information in the specific information is lower than the lower limit value of the first preset range, predicting missing data by using a machine learning algorithm; and screening abnormal values in the specific information, and deleting the screened abnormal values.
In this embodiment, since there are multiple bases for determining the loan trust value, the weight ratio of each data associated with the loan trust value may be determined first, and then the loan trust value of the loan initiator may be calculated based on the weight ratio of each data. When the weight proportion of each data is determined, the weight proportion of the data can be measured from the timeliness and the importance of the data respectively. In consideration of the fact that the validity and accuracy of the data representing the credit condition and the repayment ability of the loan initiator are reduced along with the increase of time, for example, the closer the property data and the credit data of the vehicle company to the current moment, the more truly the repayment ability and the credit condition of the vehicle company can be reflected. Therefore, the aging weight of any data can be set to be in negative correlation with the corresponding time interval (the time interval of any data is the time interval from the occurrence time of any data to the current time), namely when the weight proportion of each data related to the loan trust value is determined, the calculation accuracy of the loan trust value can be improved by adding the measurement based on the time attenuation.
For example, the age weight may be calculated by the following formula:
wherein f (t) represents an aging weight of the data;
tnowRepresents the current time;
t0indicating the occurrence time of the data;
tstartrepresenting the earliest moment of occurrence of all data associated with the loan confidence value;
gamma denotes preset overfitting adjustment parameters.
In this embodiment, an Analytic Hierarchy Process (AHP) may be utilized to determine the importance weight of each data associated with a loan confidence value (the specific Process of calculating importance weights by Analytic Hierarchy Process is described in detail below). Further, after determining the aging weight and the importance weight of each data associated with the loan trust value, a weight ratio of each data associated with the loan trust value may be determined based on the aging weight and the importance weight. For example, the time-dependent weight and the importance weight are multiplied to obtain the weight ratio, or the time-dependent weight and the importance weight are further multiplied to obtain the weight ratio after being weighted. Of course, this application is not so limited.
And 104, determining the popularity value of the target vehicle of the loan initiator, wherein the loan fund of the loan initiated by the loan initiator is used for purchasing the target vehicle.
In the present embodiment, the heat value of the target vehicle may be determined from the following data: sales number, consultation number, distribution number, sharing number, etc. for the target vehicle. Wherein the heat value is positively correlated with the above amount.
In this embodiment, the mortgage proportion is negatively correlated with the loan trust value of the loan originator and negatively correlated with the heat value of the target vehicle.
And step 108, determining the mortgage property of the loan initiator according to the mortgage proportion and the loan fund.
In one case, the mortgage property of the loan originator may be determined directly from the mortgage proportion and the loan funds. For example, the loan initiator should multiply the loan fund by the mortgage proportion to obtain the result as the mortgage property.
In another case, further reference may be made to the current economic environment in determining the mortgage asset of the loan originator. For example, a current market environment coefficient may be obtained, the market environment coefficient being associated with a sales situation for the target vehicle. For example, the market environment coefficient is positively correlated with the sales condition of the target vehicle, i.e., the better the sales condition of the target vehicle, the larger the market environment coefficient is. Of course, the current market environment coefficient may also be determined according to parameters in other dimensions, which is not limited in this application. Based on the acquisition of the current market environment coefficient, the mortgage proportion can be adjusted according to the market environment coefficient, and then the mortgage property of the loan initiator is determined based on the adjusted mortgage proportion and the loan fund. For example, the market environment coefficient may be set to be inversely related to the mortgage ratio. By associating the mortgage proportion with the current market environment coefficient, the repayment capability of the loan initiator for the loan fund can be further accurately measured, so that the accuracy and the reasonableness of calculating the mortgage property are improved.
According to the technical scheme, the mortgage proportion is calculated based on the loan trust value (used for measuring the credit condition and the repayment capability of the loan initiator) of the loan initiator and the heat value of the target vehicle, so that the finally determined mortgage assets needing to be delivered by the loan initiator are more reasonable, and the risk of the lender of the loan funds can be effectively reduced. Furthermore, the loan trust value is determined by integrating the aging weight and the importance weight of each data associated with the loan trust value, so that the determined loan trust value is more comprehensive and reasonable. Meanwhile, the effectiveness and accuracy of the data reflecting the credit condition and the repayment capacity of the loan initiator are reduced along with the increase of time, and the finally calculated loan trust value can more accurately reflect the credit condition and the repayment capacity of the loan initiator by setting the aging weight of any data to be negatively correlated with the time interval between the occurrence moment corresponding to any data and the current moment.
For ease of understanding, the following description will be made in detail with reference to the calculation scheme of mortgage property of the present application, taking the example of credit from a car dealer to a car platform.
Referring to fig. 2, fig. 2 is a flow chart illustrating another mortgage asset calculation method according to an exemplary embodiment of the present application. As shown in fig. 2, the method may be applied to a background server of an automobile platform, and may include the following steps:
In the embodiment, the relevant data of the vehicle trader comprises vehicle trader data (admission information and operation information of the vehicle trader in the local system), property data, historical loan data and credit data.
For example, the obtained data related to the car dealer are shown in tables 1 to 5:
TABLE 1
TABLE 2
TABLE 3
TABLE 4
TABLE 5
Based on the acquisition of the data, operations such as conversion, completion, deletion, and cleaning need to be further performed on the data. Specifically, the service data is converted into specific numerical values for quantization. For example, sex conversion: male-1, female-1; major equals to 1, this family equals to 2, major equals to 4. The data with relatively large values is scaled down to reduce errors. For example, for data related to an amount of money, the amount of money is reduced by 800 times, or an amount of money of 8000 ten thousand or more is fixedly converted to 10, and so on. The missing data is either filled or deleted. For example, data with a data loss rate of more than 80% is deleted; filling data with the data missing rate of 40-80% by using a median; predicting missing data in data with a data missing rate of less than 40% by using a random forest algorithm; and screening and deleting the abnormal point data by adopting a box separation method.
Furthermore, a principal component analysis (also called principal component analysis) method can be used to perform dimensionality reduction processing on the specific information of the data, so as to play a role in reducing dimensionality. Specifically, the plurality of associated information can be combined into a small number of pieces of mutually independent integrated information (i.e., principal components), wherein each principal component can reflect most of the information of the original information and contains information that is not repeated. For example, after the specific information of the data is obtained, the variables with higher correlation in the specific information can be converted into the independent or uncorrelated variables by the principal component analysis method, and usually, a few new variables (i.e., principal components) which are less than the original variables and can explain the variables contained in most information are selected. The correlation between each variable can be calculated by using a principal component analysis method, and the variable with higher correlation is replaced by other variables through linear weighting, so that the variable in the correlation information is reduced from high dimension to low dimension, and the subsequent calculation amount is reduced.
For example, assuming that the relationship between the default amount and the default singular number is high, the default amount may be weighted by the default singular number, for example, the default amount is a coefficient a × the default singular number; wherein the coefficient a is a correlation coefficient between the default amount and the default singular number.
And step 204, determining the aging weight of each data.
In this embodiment, since there are multiple bases for determining the loan trust value, the weight ratio of each data associated with the loan trust value may be determined first, and then the loan trust value of the loan initiator may be calculated based on the weight ratio of each data. When the weight proportion of each data is determined, the weight proportion of the data can be measured from the timeliness and the importance of the data respectively. In consideration of the fact that the validity and accuracy of the data representing the credit condition and the repayment ability of the loan initiator are reduced along with the increase of time, for example, the closer the property data and the credit data of the vehicle company to the current moment, the more truly the repayment ability and the credit condition of the vehicle company can be reflected. Therefore, the aging weight of any data can be set to be in negative correlation with the time interval from the current time corresponding to the occurrence time of any data, namely, when the weight proportion of each data associated with the loan trust value is determined, the calculation accuracy of the loan trust value can be improved by adding the measurement based on the time attenuation.
For example, the age weight may be calculated by the following formula:
Wherein f (t) represents an aging weight of the data;
tnowindicating the current timeEngraving;
t0indicating the occurrence time of the data;
tstartrepresenting the earliest moment of occurrence of all data associated with the loan confidence value;
gamma denotes preset overfitting adjustment parameters.
By way of example, the earliest moment of occurrence can be understood as: each data has a corresponding occurrence time, for example, if the default information of the default event of the car dealer is obtained, the time when the car dealer occurs the default event is the occurrence time of the default information; then the earliest moment of occurrence is the smallest moment of all moments of occurrence.
In step 206, the importance weight of each data is determined.
In this embodiment, Analytic Hierarchy Process (AHP) may be utilized to determine the importance weight of each data associated with a loan confidence value.
For example, it is assumed that relevant data of the vehicle dealer after the dimension reduction processing includes vehicle dealer admission information, amount, order, vehicle, default and the like.
1) Based on the above-mentioned related data, the comparison importance between each data is obtained (for example, a developer may set a preliminary value according to an empirical value first, and then adjust the value), as shown in table 6:
| Vehicle and business access information | Vehicle with a steering wheel | Order form | Default | Amount of money | |
| Vehicle and business access information | 1.00 | 0.50 | 0.33 | 0.50 | 0.33 |
| Vehicle with a steering wheel | 2.00 | 1.00 | 0.67 | 1.00 | 0.67 |
| Order form | 3.00 | 1.50 | 1.00 | 1.50 | 1.00 |
| Default | 2.00 | 1.00 | 0.67 | 1.00 | 0.67 |
| Amount of money | 3.00 | 1.50 | 1.00 | 1.50 | 1.00 |
TABLE 6
2) Calculating importance weight WI (weight) of each data
The importance weight WI is the power of kelvin/sum (power of kelvin); the term "n-th power" is understood to mean that the importance of each row of any adjusted data is multiplied, and the value obtained by the multiplication is subjected to n-th power operation.
TABLE 7
Taking the car dealer admission information in table 7 as an example, the operation process of "multiplication by rows" is: 1.00 × 0.50 × 0.33 × 0.50 × 0.33 ═ 0.027225; the operation process of "opening the power n" (taking n as 10 as an example, the value of n can be flexibly adjusted according to actual conditions) is as follows:
similarly, the calculation of other data is similar to that described above. Then, the importance weight WI of the dealer admission information is 0.69742384/(0.69742384+0.989277109+1.210404075+0.989277109+1.210404075) is 0.136836. Similarly, the calculation process of the importance weight WI of other data is similar to that described above, and will not be described herein again.
3) Performing a consistency check
A check coefficient CR (Consistency Ratio) is introduced to determine whether the calculated importance weight WI passes the Consistency check. If CR is <0.1, the calculated importance weight WI can be considered to pass the consistency check; otherwise, the CR may be calculated again after further adjusting the relevant parameters (e.g., the comparison importance between the data, the value of n, etc.). Where CI (Consistency Index) is (AVERGE (AWI/WI) -k) × (k-1), AVERGE represents the number of averages, and k represents the order (i.e., the number of data, in this embodiment, k is 5); the RI (RandomIndex, random consistency index) adopts the standard values shown in table 8 (different standards for consistency check are different, and the value of RI is slightly different); AWI (all weight, total rank weight) sum (importance weight of data × comparative importance).
| Order of the scale | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 |
| RI | 0 | 0 | 0.58 | 0.90 | 1.12 | 1.24 | 1.32 | 1.41 | 1.45 | 1.49 |
TABLE 8
Taking the admission information of the car dealer as an example: AWI ═ 1.0 × 0.136836+0.50 × 0.194098216+0.33 × 0.237483784+0.50 × 0.194098216+0.33 × 0.237483784 ═ 0.487673514; AVERGE (AWI/WI) ═ (3.563926978+5.049488473+6.180507114+5.049488473+6.180507114)/5 ═ 5.204783631; CI (5.204783631-5) × (5-1) ═ 0.819134522; then CR CI/RI 0.819134522/1.12 0.731370109< 0.1; therefore, it can be determined that the importance weight WI calculated as described above passes the consistency check.
Similarly, the importance weights of the data such as money amount, order, vehicle, default and the like can be obtained respectively according to the calculation process. It should be noted that the data may further include secondary information as the primary information; for example, the vehicle dealer admission information may further include, as the primary information, the age of the secondary information, the credit investigation of the legal person, the current rating, the time since the registration was made, and the like. Wherein, the importance weight of each secondary information can be calculated according to the processes 1) to 3) to obtain the corresponding secondary weight, which is not described herein again.
For example, the importance weights (including the primary weight, the secondary weight, and the integrated weight; integrated weight is the primary weight × the secondary weight) of the respective data calculated by the above-described analytic hierarchy process are shown in table 9:
TABLE 9
In step 208, the weight fraction of each data is determined.
In this embodiment, after the aging weight and the importance weight of each data are determined, the weight ratio of each data may be determined based on the aging weight and the importance weight. For example, the time-dependent weight and the importance weight are multiplied to obtain the weight ratio, or the time-dependent weight and the importance weight are further multiplied to obtain the weight ratio after being weighted. Of course, this application is not so limited.
For example, the weight proportion of data 1 is aging weight 1 × importance weight 1.
At step 210, a loan trust value is calculated.
In this embodiment, assuming that n data are included, the loan trust value is equal to age weight 1 × data 1 value × importance weight 1+ age weight 2 × data 2 value × importance weight 2+ … … age weight n × data n value × importance weight n.
Further, after the loan trust value of each vehicle merchant is calculated, each vehicle merchant can be layered according to the loan trust value. For example, the hierarchy may be made according to the correspondence shown in table 10:
| grade | Loan trust value |
| S+ | >＝300 |
| S | 240～300 |
| A+ | 200～240 |
| A | 160～200 |
| A- | 130～160 |
| B+ | 110～130 |
| B | 95～110 |
| C+ | 80～95 |
| C | 70～80 |
| D | 60～70 |
| E | <60 |
Watch 10
In step 212, a heat value of the target vehicle is determined.
In this embodiment, the heat value may be calculated according to the click rate of the user for the target vehicle in the automobile platform within a preset time period, that is, the higher the click rate is, the higher the heat value is. Of course, the basis for calculating the heat value may also be the number of telephone inquiries, payment of fixed amount of money, amount of bargain, number of sharing of the vehicle source detail page and other indexes of the user for the target vehicle in the preset time period. Of course, this application is not so limited.
In step 214, the mortgage ratio is calculated.
In this embodiment, a preliminary mortgage proportion may be generated according to the determined heat value of the target vehicle and a preset corresponding relationship between the heat value and the mortgage proportion.
For example, the correspondence is shown in table 11:
| vehicle type inlet mode | Heat value of vehicle | Mortgage proportion |
| Middle gauge | >＝85 | 20％ |
| Middle gauge | 75-85 | 25％ |
| Middle gauge | <75 | 35％ |
| Made in China | >＝80 | 20％ |
| Made in China | 70-80 | 25％ |
| Made in China | <70 | 35％ |
| Parallel inlet | >＝90 | 20％ |
| Parallel inlet | 80-90 | 25％ |
| Parallel inlet | <80 | 35％ |
TABLE 11
Furthermore, the preliminary mortgage proportion is adjusted according to the loan trust value, and of course, the specific adjustment mode can be flexibly set according to the actual situation, which is not limited in the present application. For example, as shown in table 12:
TABLE 12
At step 216, the mortgage asset is determined.
In one case, the mortgage property of the loan originator may be determined directly from the mortgage proportion and the loan funds. For example, the loan initiator should multiply the loan fund by the mortgage proportion to obtain the result as the mortgage property.
In another case, further reference may be made to the current economic environment in determining the mortgage asset of the loan originator. For example, a current market environment coefficient may be obtained, the market environment coefficient being associated with a sales situation for the target vehicle. For example, the market environment coefficient is positively correlated with the sales condition of the target vehicle, i.e., the better the sales condition of the target vehicle, the larger the market environment coefficient is. Of course, the current market environment coefficient may also be determined according to parameters in other dimensions, which is not limited in this application. Based on the acquisition of the current market environment coefficient, the mortgage proportion can be adjusted according to the market environment coefficient, and the mortgage property of the loan initiator is determined based on the adjusted mortgage proportion and the loan fund. For example, the market environment coefficient may be set to be inversely related to the mortgage ratio. By associating the mortgage proportion with the current market environment coefficient, the repayment capability of the loan initiator for the loan fund can be further accurately measured, so that the accuracy and the reasonableness of calculating the mortgage property are improved.
For example, the adjusted mortgage ratio is (1-r × current market environment coefficient), r is 0.1;
the mortgage property is the loan amount multiplied by the mortgage proportion after adjustment.
According to the technical scheme, the mortgage proportion is calculated based on the loan trust value (used for measuring the credit condition and the repayment capability of the loan initiator) of the loan initiator and the heat value of the target vehicle, so that the finally determined mortgage assets needing to be delivered by the loan initiator are more reasonable, and the risk of the lender of the loan funds can be effectively reduced. Furthermore, the loan trust value is determined by integrating the aging weight and the importance weight of each data associated with the loan trust value, so that the determined loan trust value is more comprehensive and reasonable. Meanwhile, the effectiveness and accuracy of the data reflecting the credit condition and the repayment capacity of the loan initiator are reduced along with the increase of time, and the finally calculated loan trust value can more accurately reflect the credit condition and the repayment capacity of the loan initiator by setting the aging weight of any data to be negatively correlated with the time interval between the occurrence moment corresponding to any data and the current moment.
Fig. 3 shows a schematic block diagram of a master-based-side electronic device according to an exemplary embodiment of the present application. Referring to fig. 3, at the hardware level, the electronic device includes a processor 302, an internal bus 304, a network interface 306, a memory 308, and a non-volatile storage 310, but may also include hardware required for other services. The processor 302 reads the corresponding computer program from the non-volatile memory 310 into the memory 308 and then runs, forming a computing device of mortgage assets at a logical level. Of course, besides the software implementation, the present application does not exclude other implementations, such as logic devices or a combination of software and hardware, and the like, that is, the execution subject of the following processing flow is not limited to each logic unit, and may also be hardware or logic devices.
Referring to fig. 4, in a software implementation, the computing device of the mortgage asset may include:
a trust value determination unit 41 that determines a loan trust value of the loan initiator;
a hot value determination unit 42 that determines a hot value of a target vehicle of the loan initiator, the loan fund of the loan initiated by the loan initiator being used to purchase the target vehicle;
a proportion calculation unit 43 that calculates a mortgage proportion based on the loan trust value and the calorific value;
the mortgage determination unit 44 determines mortgage assets of the loan initiator according to the mortgage proportion and the loan funds.
Optionally, the trust value determining unit 41 is specifically configured to:
determining a weight fraction of each data associated with the loan confidence value;
and calculating the loan trust value of the loan initiator based on the weight ratio of each data.
Optionally, the trust value determining unit 41 is further configured to:
determining an aging weight for each data associated with the loan trust value; the aging weight of any data is in negative correlation with the time interval between the occurrence time of the data and the current time;
determining importance weights of the data associated with the loan trust value using analytic hierarchy process;
Determining a weight ratio for each data associated with the loan trust value based on the age weight and the importance weight.
Optionally, the aging weight is calculated by the following formula:
wherein f (t) represents an aging weight of the data;
tnowrepresents the current time;
t0indicating the occurrence time of the data;
tstartrepresenting the earliest moment of occurrence of all data associated with the loan confidence value;
gamma denotes preset overfitting adjustment parameters.
Optionally, the mortgage proportion is negatively correlated with the loan trust value, and the mortgage proportion is negatively correlated with the heat value.
Alternatively to this, the first and second parts may,
further comprising: a coefficient acquisition unit 45 that acquires a current market environment coefficient associated with a sales situation for the target vehicle;
the mortgage determination unit 44 is specifically configured to: and adjusting the mortgage proportion according to the market environment coefficient, and determining the mortgage property of the loan initiator based on the adjusted mortgage proportion and the loan fund.
Optionally, the loan trust value is associated with the loan originator's basic data, property data, historical loan data, credit data.
The implementation process of the functions and actions of each unit in the above device is specifically described in the implementation process of the corresponding step in the above method, and is not described herein again.
For the device embodiments, since they substantially correspond to the method embodiments, reference may be made to the partial description of the method embodiments for relevant points. The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of the application. One of ordinary skill in the art can understand and implement it without inventive effort.
In an exemplary embodiment, there is also provided a non-transitory computer readable storage medium, for example a memory, comprising instructions executable by a processor of a computing device of a mortgage asset as described above to implement a method as described in any of the above embodiments, such as the method may comprise: determining a loan trust value of a loan initiator; determining a popularity value of a target vehicle of the loan initiator, wherein loan funds of a loan initiated by the loan initiator are used for purchasing the target vehicle; calculating a mortgage proportion based on the loan confidence value and the heat value; and determining the mortgage property of the loan initiator according to the mortgage proportion and the loan fund.
The non-transitory computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc., which is not limited in this application.
The above description is only exemplary of the present application and should not be taken as limiting the present application, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the scope of protection of the present application.
Claims (16)
1. A method of computing a mortgage asset, comprising:
determining a loan trust value of a loan initiator;
determining a popularity value of a target vehicle of the loan initiator, wherein loan funds of a loan initiated by the loan initiator are used for purchasing the target vehicle;
calculating a mortgage proportion based on the loan confidence value and the heat value;
and determining the mortgage property of the loan initiator according to the mortgage proportion and the loan fund.
2. The method of claim 1, wherein determining a loan trust value for a loan originator comprises:
determining a weight fraction of each data associated with the loan confidence value;
and calculating the loan trust value of the loan initiator based on the weight ratio of each data.
3. The method of claim 2, wherein determining a weight ratio for each data associated with the loan confidence value comprises:
determining an aging weight for each data associated with the loan trust value; the aging weight of any data is in negative correlation with the corresponding time interval, and the time interval of any data is the time between the occurrence moment of any data and the current moment;
determining importance weights of the data associated with the loan trust value using analytic hierarchy process;
determining a weight ratio for each data associated with the loan trust value based on the age weight and the importance weight.
4. The method of claim 3, wherein the aging weight is calculated by the formula:
wherein f (t) represents an aging weight of the data;
tnowrepresents the current time;
t0indicating the occurrence time of the data;
tstartrepresenting the earliest moment of occurrence of all data associated with the loan confidence value;
gamma denotes preset overfitting adjustment parameters.
5. The method of claim 1, wherein the mortgage proportion is negatively correlated with the loan confidence value and the mortgage proportion is negatively correlated with the heat value.
6. The method of claim 1,
further comprising: obtaining a current market environment coefficient, the market environment coefficient being associated with a sales situation for the target vehicle;
determining mortgage assets of the loan initiator according to the mortgage proportion and the loan funds, wherein the mortgage assets comprise: and adjusting the mortgage proportion according to the market environment coefficient, and determining the mortgage property of the loan initiator based on the adjusted mortgage proportion and the loan fund.
7. A method according to claim 1, wherein the loan trust value is associated with the loan originator's underlying data, property data, historical loan data, credit data.
8. A computing device for mortgage of assets, comprising:
a trust value determination unit for determining a loan trust value of a loan initiator;
a popularity value determination unit for determining a popularity value of a target vehicle of the loan initiator, the loan fund of the loan initiated by the loan initiator being used for purchasing the target vehicle;
a proportion calculation unit which calculates a mortgage proportion based on the loan trust value and the heat value;
and the mortgage determining unit determines the mortgage assets of the loan initiator according to the mortgage proportion and the loan funds.
9. The apparatus according to claim 8, wherein the trust value determining unit is specifically configured to:
determining a weight fraction of each data associated with the loan confidence value;
and calculating the loan trust value of the loan initiator based on the weight ratio of each data.
10. The apparatus of claim 9, wherein the trust value determination unit is further configured to:
determining an aging weight for each data associated with the loan trust value; the aging weight of any data is in negative correlation with the corresponding time interval, and the time interval of any data is the time between the occurrence moment of any data and the current moment;
determining importance weights of the data associated with the loan trust value using analytic hierarchy process;
determining a weight ratio for each data associated with the loan trust value based on the age weight and the importance weight.
11. The apparatus of claim 10, wherein the aging weight is calculated by the formula:
wherein f (t) represents an aging weight of the data;
tnowrepresents the current time;
t0indicating the occurrence time of the data;
tstartRepresenting the earliest moment of occurrence of all data associated with the loan confidence value;
gamma denotes preset overfitting adjustment parameters.
12. The apparatus of claim 8, wherein the mortgage proportion is negatively correlated with the loan confidence value and the mortgage proportion is negatively correlated with the heat value.
13. The apparatus of claim 8,
further comprising: a coefficient acquisition unit that acquires a current market environment coefficient associated with a sales situation for the target vehicle;
the mortgage determination unit is specifically configured to: and adjusting the mortgage proportion according to the market environment coefficient, and determining the mortgage property of the loan initiator based on the adjusted mortgage proportion and the loan fund.
14. The apparatus of claim 8, wherein the loan trust value is associated with base data, property data, historical loan data, credit data of the loan originator.
15. An electronic device, comprising:
a processor;
a memory for storing processor-executable instructions;
wherein the processor implements the method of any one of claims 1-7 by executing the executable instructions.
16. A computer-readable storage medium having stored thereon computer instructions, which when executed by a processor, perform the steps of the method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910354999.2A CN111861693A (en) | 2019-04-29 | 2019-04-29 | Mortgage asset calculation method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910354999.2A CN111861693A (en) | 2019-04-29 | 2019-04-29 | Mortgage asset calculation method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111861693A true CN111861693A (en) | 2020-10-30 |
Family
ID=72966250
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910354999.2A Pending CN111861693A (en) | 2019-04-29 | 2019-04-29 | Mortgage asset calculation method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111861693A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002230288A (en) * | 2001-02-01 | 2002-08-16 | Ryoichi Ino | Preliminary examination system for automobile loan |
| CN107909467A (en) * | 2017-11-15 | 2018-04-13 | 重庆小雨点小额贷款有限公司 | A kind of loan limit appraisal procedure and relevant device |
| CN107944772A (en) * | 2017-12-27 | 2018-04-20 | 深圳市轱辘车联数据技术有限公司 | Car based on block chain borrows risk information processing method and processing device |
| CN108460678A (en) * | 2017-02-22 | 2018-08-28 | 北京数信互融科技发展有限公司 | Assets screening, quality-monitoring, prediction whole process internet financial asset manage cloud platform |
-
2019
- 2019-04-29 CN CN201910354999.2A patent/CN111861693A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002230288A (en) * | 2001-02-01 | 2002-08-16 | Ryoichi Ino | Preliminary examination system for automobile loan |
| CN108460678A (en) * | 2017-02-22 | 2018-08-28 | 北京数信互融科技发展有限公司 | Assets screening, quality-monitoring, prediction whole process internet financial asset manage cloud platform |
| CN107909467A (en) * | 2017-11-15 | 2018-04-13 | 重庆小雨点小额贷款有限公司 | A kind of loan limit appraisal procedure and relevant device |
| CN107944772A (en) * | 2017-12-27 | 2018-04-20 | 深圳市轱辘车联数据技术有限公司 | Car based on block chain borrows risk information processing method and processing device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP5122285B2 (en) | Method and system for estimating insurance reserves and confidence intervals using insurance policy and claims level detailed predictive modeling | |
| US20040030629A1 (en) | System and method for portfolio valuation using an age adjusted delinquency rate | |
| US20170053278A1 (en) | Systems and Methods for Processing Charges for Disputed Transactions | |
| WO2009065134A1 (en) | Method for deal-based pricing and estimation of deal winning probability using multiple prospective models | |
| CN109213936B (en) | Commodity searching method and device | |
| WO2016084642A1 (en) | Credit examination server, credit examination system, and credit examination program | |
| JP5955436B1 (en) | Loan risk evaluation parameter calculation apparatus, program, and method | |
| US20150348186A1 (en) | System and method for dynamic customer acquisition probability and risk-adjusted return-on-equity analysis | |
| Kau et al. | An analysis of mortgage termination risks: a shared frailty approach with MSA-level random effects | |
| CN111784487A (en) | Ultra-short term credit evaluation method for small and medium-sized enterprises based on dynamic financial and resource flows | |
| US20110213731A1 (en) | Techniques for identifying high-risk portfolio with automated commercial real estate stress testing | |
| CN110827137A (en) | Credit evaluation method and device | |
| US20150178827A1 (en) | Computer modeling of propery tax delinquency risk | |
| CN111861693A (en) | Mortgage asset calculation method and device, electronic equipment and storage medium | |
| CN114119107A (en) | Steel trade enterprise transaction evaluation method, device, equipment and storage medium | |
| CN117252677A (en) | Credit line determination method and device, electronic equipment and storage medium | |
| CN114240599A (en) | Loan calculation method and device, computer equipment and storage medium | |
| CN114240605A (en) | Loan calculation method and device, computer equipment and storage medium | |
| CN112102094A (en) | Method and apparatus for securitization and stratification of assets | |
| JP4610732B2 (en) | Loan management system and method | |
| US20200065897A1 (en) | Financial instrument pricing | |
| Li et al. | Semiparametric estimation of default probability: Evidence from the Prosper online credit market | |
| Baker et al. | The challenge of measuring intangibles: Insights from brand valuation | |
| KR102253857B1 (en) | A method and system for generating an indicator of change in securities balance rate | |
| US20160283956A1 (en) | Country specific revenue estimation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |