CN116091200A - Scene credit granting system and method based on machine learning, electronic equipment and medium - Google Patents
Scene credit granting system and method based on machine learning, electronic equipment and medium Download PDFInfo
- Publication number
- CN116091200A CN116091200A CN202211657560.5A CN202211657560A CN116091200A CN 116091200 A CN116091200 A CN 116091200A CN 202211657560 A CN202211657560 A CN 202211657560A CN 116091200 A CN116091200 A CN 116091200A
- Authority
- CN
- China
- Prior art keywords
- credit
- scene
- characteristic data
- income
- giving
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The embodiment of the invention discloses a scene credit granting system and method based on machine learning, electronic equipment and medium, and the scene credit granting method based on machine learning comprises the following steps: acquiring credit investigation characteristics; removing redundant sign features through correlation detection and multiple collinearity calculation, and screening out access module sign features; constructing a scene credit-giving model based on the entry-module credit-giving characteristics; acquiring income characteristic data of a user to be trusted; correcting the income characteristic data from different dimensions, and dividing the corrected income characteristic data into intervals; and inputting the income characteristic data of each interval into the scene credit-giving model to obtain a credit-giving result. The scene credit granting method based on machine learning solves the problems that a credit granting limit model is determined by risks and user liability in the prior art, and is monotonous in dimension and lack of accuracy.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a scene credit granting system, a scene credit granting method, electronic equipment and a scene credit granting medium based on machine learning.
Background
With the increasingly vigorous competition of financial institutions in the scene consumption financial market, in order to meet the market demand of quick approval, the complicated background manual approval is converted into quick on-site pre-approval, and more credit services are provided for customers with good credit;
the existing credit line strategy mainly takes rules, expert experience and a simple model, multiple persons are needed to participate, maintenance is complex, the general credit line model is determined by risks and user liability, maintenance is monotonous, accuracy and flexibility are lacking, correction is not performed on inaccurate places in the existing characteristics, the credit risk of a client can be estimated only by using limited data, and comprehensive estimation of the risk cannot be achieved.
Disclosure of Invention
The embodiment of the invention aims to provide a scene credit granting system, a scene credit granting method, electronic equipment and a scene credit granting medium based on machine learning, which are used for solving the problems that a credit granting limit model in the prior art is determined by risks and user liability, and has monotonous dimension and lack of accuracy.
To achieve the above objective, an embodiment of the present invention provides a scene credit method based on machine learning, which specifically includes:
acquiring credit investigation characteristics;
removing redundant sign features through correlation detection and multiple collinearity calculation, and screening out access module sign features;
constructing a scene credit-giving model based on the entry-module credit-giving characteristics;
acquiring income characteristic data of a user to be trusted;
correcting the income characteristic data from different dimensions, and dividing the corrected income characteristic data into intervals;
and inputting the income characteristic data of each interval into the scene credit-giving model to obtain a credit-giving result.
Based on the technical scheme, the invention can also be improved as follows:
further, the constructing a scene credit model based on the entry module credit feature includes:
dividing the module-entering credit characteristics into a training set, a verification set and a test set;
training the scene credit model based on the training set;
performing performance verification on the scene credit-giving model based on the verification set, and storing the scene credit-giving model meeting performance conditions;
and evaluating the trust result of the scene trust model based on the test set.
Further, the correcting the revenue feature data from different dimensions and dividing the corrected revenue feature data into intervals includes:
judging whether a co-person exists in the monthly income characteristic data of which the monthly income is lower than the public accumulation fund repayment amount and the commodity credit repayment amount, if so, judging whether the total of the monthly income characteristic data of the co-person and the user to be trusted is lower than a designated multiple of monthly liabilities, and if so, deleting the income characteristic data;
and when the credit card usage amount of the user to be trusted is too high in a certain period of time, the income characteristic data of the user to be trusted is adjusted.
Further, the inputting the income characteristic data of each interval into the scene credit-giving model to obtain a credit-giving result includes:
predicting the income interval of each interval, assigning and analyzing each predicted income interval, and evaluating the income characteristic data by combining with the upper limit of months to obtain the credit giving amount.
A machine learning based scene trust system comprising:
the first acquisition module is used for acquiring credit investigation characteristics;
the screening module is used for removing redundant sign features through correlation detection and multiple collinearity calculation and screening out in-out module sign features;
the construction module is used for removing redundant sign features and screening out in-out module sign features through correlation detection and multiple collinearity calculation;
the second acquisition module is used for acquiring income characteristic data of the user to be trusted;
the correction module is used for correcting the income characteristic data from different dimensions and dividing the corrected income characteristic data into sections;
and receiving the income characteristic data input of each interval based on the scene credit giving model to obtain a credit giving result.
Further, the construction module is further configured to:
dividing the module-entering credit characteristics into a training set, a verification set and a test set; training the scene credit model based on the training set; performing performance verification on the scene credit-giving model based on the verification set, and storing the scene credit-giving model meeting performance conditions; and evaluating the trust result of the scene trust model based on the test set.
Further, the correction module is further configured to:
judging whether a co-person exists in the monthly income characteristic data of which the monthly income is lower than the public accumulation fund repayment amount and the commodity credit repayment amount, if so, judging whether the total of the monthly income characteristic data of the co-person and the user to be trusted is lower than a designated multiple of monthly liabilities, and if so, deleting the income characteristic data; and when the credit card usage amount of the user to be trusted is too high in a certain period of time, the income characteristic data of the user to be trusted is adjusted.
Further, the scene trust model is further used for:
predicting the income interval of each interval, assigning and analyzing each predicted income interval, and evaluating the income characteristic data by combining with the upper limit of months to obtain the credit giving amount.
An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method when the computer program is executed.
A non-transitory computer readable medium having stored thereon a computer program which, when executed by a processor, implements the steps of the method.
The embodiment of the invention has the following advantages:
according to the scene credit authorization method based on machine learning, credit investigation characteristics are obtained; removing redundant sign features through correlation detection and multiple collinearity calculation, and screening out access module sign features; constructing a scene credit-giving model based on the entry-module credit-giving characteristics; acquiring income characteristic data of a user to be trusted; correcting the income characteristic data from different dimensions, and dividing the corrected income characteristic data into intervals; inputting the income characteristic data of each interval into the scene credit-giving model to obtain a credit-giving result;
and correcting the income characteristic data from different dimensions according to the data analysis result, wherein the income characteristic data is manually filled and is highly correlated with the credit line, so that more accurate income characteristic data can achieve more accurate credit effect.
And taking the corrected income characteristic data as a final Y value in a sub-box mode, extracting effective information from the multidimensional data, and fitting the nonlinear condition more comprehensively, thereby realizing accurate prediction of the income range.
And carrying out credit assignment on the predicted income interval by adopting different modes, and finally obtaining the final credit limit by comparing and using the optimal mode. The method solves the problems that in the prior art, the credit limit model is determined by risks and liability of users, the dimension is monotonous, and accuracy is lacking.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It will be apparent to those of ordinary skill in the art that the drawings in the following description are exemplary only and that other implementations can be obtained from the extensions of the drawings provided without inventive effort.
The structures, proportions, sizes, etc. shown in the present specification are shown only for the purposes of illustration and description, and are not intended to limit the scope of the invention, which is defined by the claims, so that any structural modifications, changes in proportions, or adjustments of sizes, which do not affect the efficacy or the achievement of the present invention, should fall within the ambit of the technical disclosure.
FIG. 1 is a flow chart of a machine learning based scene trust method of the present invention;
FIG. 2 is a block diagram of a machine learning based scenario trust system of the present invention;
fig. 3 is a schematic diagram of an entity structure of an electronic device according to the present invention.
Wherein the reference numerals are as follows:
the system comprises a first acquisition module 10, a screening module 20, a construction module 30, a second acquisition module 40, a correction module 50, a scene credit model 60, an electronic device 70, a processor 701, a memory 702 and a bus 703.
Detailed Description
Other advantages and advantages of the present invention will become apparent to those skilled in the art from the following detailed description, which, by way of illustration, is to be read in connection with certain specific embodiments, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Examples
Fig. 1 is a flowchart of an embodiment of a scene credit authorization method based on machine learning according to the present invention, as shown in fig. 1, and the scene credit authorization method based on machine learning provided by the embodiment of the present invention includes the following steps:
s101, acquiring credit investigation characteristics;
specifically, the features are mainly credit features, and the modeling is performed by using 25000+ credit features derived from secondary pedestrian credit. The credit feature is mainly characterized by dimensions such as personal basic information, information summary, credit transaction information detail, non-credit transaction information detail, public information detail, other labeling and statement information, inquiry records and the like. The payment capability and the payment willingness of the user are displayed in a multi-dimensional and omnibearing manner, and a foundation is laid for building a credit application admission model to identify the risk of the user and reduce the credit risk of the client.
S102, removing redundant credit sign features through correlation detection and multiple collinearity calculation, and screening access module credit sign features;
specifically, due to the prediction of income, the screening features are mainly selected from age, month income, month liabilities and credit investigation features of repayment capability and repayment willingness.
The missing values, unique values, and class type features are processed. Deleting credit sign features with the deletion proportion being more than 90%, and then filling the mode and the mean value of other indexes according to index meanings. And deleting a list of credit features with only one value, and finally converting the category credit features into numerical values to participate in the final modeling process.
And selecting credit sign features with higher and more stable bid value information, removing redundant credit sign features through correlation detection and multiple collinearity calculation, and finally screening the entrance module credit sign features of the entrance module.
S103, constructing a scene credit module 60 based on the entry module credit characteristics;
specifically, the modeling sign feature is divided into a training set, a verification set and a test set;
training the scene trust model 60 based on the training set;
performing performance verification on the scene credit giving model 60 based on the verification set, and storing the scene credit giving model 60 meeting performance conditions;
and evaluating the trust result of the scene trust model 60 based on the test set.
And modeling the sample by using a machine learning model by using the screened sign-on characteristics to obtain predicted income. The rationality of the model predictions is then verified by screening the samples. And evaluating the effect and stability of the model through ROC, KS and the PSI of the model, respectively verifying the effect of the model on a training set sample, a verification set sample and a test set sample, and adjusting the model effect.
S104, acquiring income characteristic data of the user to be trusted.
S105, correcting the income characteristic data from different dimensions, and dividing the corrected income characteristic data into sections.
Specifically, judging whether a co-person exists for the month income characteristic data with the month income lower than the public accumulation payment amount and the business credit payment amount, if so, judging whether the total of the month income characteristic data of the co-person and the user to be trusted is lower than a designated multiple of month liabilities, and if so, deleting the income characteristic data;
and when the credit card usage amount of the user to be trusted is too high in a certain period of time, the income characteristic data of the user to be trusted is adjusted.
The income characteristic data is manually input data, and partial data is found to have a larger influence on the final result by analyzing the income characteristic data in boxes, so that correction and partial data deletion are required for the income characteristic data to be more accurate. Firstly, correcting, wherein the month income is lower than that calculated by the public accumulation fund and the house credit; whether people are shared or not is combined, and the month income is lower than the designated multiple of the month liability; credit card usage credit for the last 6 months is adjusted for excessive revenue.
Then deleting part of income characteristic data, marking 1.5w of income, and fishing back after removing the income during modeling; deleting overdue high income characteristic data; and deleting the income characteristic data with high vehicle price, high pay-per-view and low income.
Dividing the corrected income into five sections, wherein each section is used as a category, and the final model is also a five-category model. The specific interval division is obtained after adjustment according to the actual distribution condition of the data and the specific effect of the model.
S106, inputting the income characteristic data of each interval into the scene credit giving model 60 to obtain a credit giving result.
Specifically, a income interval of each interval is predicted, each predicted income interval is assigned and analyzed, and the income characteristic data is evaluated by combining with a month upper limit to obtain a credit amount.
The five predicted intervals are assigned and analyzed, and simultaneously evaluated in combination with the upper month limit.
Interval assignment thought: the method comprises the following steps: the lowest month income meeting the rigid deduction condition is reversely pushed according to the paying amount, the stage period number and the month liability, and 98% of the score is obtained according to the target; the second method is as follows: multiplying a maximum value of a section threshold by 0.9 coefficient; and a third method: if the maximum value of the credit line of the RMB credit card is less than 50% of the fractional number of the interval, the middle number of the interval of income is assigned, and if the maximum value of the credit line of the RMB credit card is greater than 50% of the fractional number of the interval, the maximum value of the interval of income is assigned; the method four: interval threshold maximum (primary auxiliary assessment) is taken. And calculating the payoff amount according to the predicted assignment result, and then comparing the payoff amount with the actual payoff amount, and selecting a more suitable method for final assignment.
The scene credit authorization method based on machine learning acquires credit investigation characteristics; removing redundant sign features through correlation detection and multiple collinearity calculation, and screening out access module sign features; constructing a scene credit model 60 based on the entry modeling credit features; acquiring income characteristic data of a user to be trusted; correcting the income characteristic data from different dimensions, and dividing the corrected income characteristic data into intervals; inputting the income characteristic data of each interval into the scene trust model 60 to obtain trust results;
and correcting the income characteristic data from different dimensions according to the data analysis result, wherein the income characteristic data is manually filled and is highly correlated with the credit line, so that more accurate income characteristic data can achieve more accurate credit effect.
And taking the corrected income characteristic data as a final Y value in a sub-box mode, extracting effective information from the multidimensional data, and fitting the nonlinear condition more comprehensively, thereby realizing accurate prediction of the income range.
And carrying out credit assignment on the predicted income interval by adopting different modes, and finally obtaining the final credit limit by comparing and using the optimal mode. The method solves the problems that in the prior art, the credit limit model is determined by risks and liability of users, the dimension is monotonous, and accuracy is lacking.
FIG. 2 is a flow chart of an embodiment of a machine learning based scene credit system of the present invention; as shown in fig. 2, the scene credit granting system based on machine learning provided by the embodiment of the invention includes the following steps:
a first acquisition module 10, configured to acquire credit standing features;
the screening module 20 is used for removing redundant sign features and screening out access module sign features through correlation detection and multiple collinearity calculation;
the construction module 30 is used for removing redundant sign features and screening out access module sign features through correlation detection and multiple collinearity calculation;
a second obtaining module 40, configured to obtain revenue feature data of a user to be trusted;
the correction module 50 is configured to correct the revenue feature data from different dimensions, and divide the corrected revenue feature data into intervals;
and receiving revenue feature data input of each interval based on the scene trust model 60 to obtain trust results.
The building block 30 is also configured to:
dividing the module-entering credit characteristics into a training set, a verification set and a test set; training the scene trust model 60 based on the training set; performing performance verification on the scene credit giving model 60 based on the verification set, and storing the scene credit giving model 60 meeting performance conditions; and evaluating the trust result of the scene trust model 60 based on the test set.
The correction module 50 is further configured to:
judging whether a co-person exists in the monthly income characteristic data of which the monthly income is lower than the public accumulation fund repayment amount and the commodity credit repayment amount, if so, judging whether the total of the monthly income characteristic data of the co-person and the user to be trusted is lower than a designated multiple of monthly liabilities, and if so, deleting the income characteristic data; and when the credit card usage amount of the user to be trusted is too high in a certain period of time, the income characteristic data of the user to be trusted is adjusted.
The scenario trust model 60 is further configured to:
predicting the income interval of each interval, assigning and analyzing each predicted income interval, and evaluating the income characteristic data by combining with the upper limit of months to obtain the credit giving amount.
According to the scene credit system based on machine learning, credit features are acquired through the first acquisition module 10, redundant credit features are removed through correlation detection and multiple collinearity calculation through the screening module 20, access module credit features are screened, redundant credit features are removed through correlation detection and multiple collinearity calculation through the construction module 30, access module credit features are screened, income feature data of users to be trusted are acquired through the second acquisition module 40, the income feature data are corrected through the correction module 50 from different dimensions, the corrected income feature data are divided into intervals, a credit result is obtained through receiving income feature data of each interval based on the scene credit model 60, and the problems that a credit limit model in the prior art is determined by risks and user liability, and the dimensions are monotonous and lack of accuracy are solved.
Fig. 3 is a schematic diagram of an entity structure of an electronic device according to an embodiment of the present invention, as shown in fig. 3, an electronic device 70 includes: a processor 701, a memory 702, and a bus 703;
wherein, the processor 701 and the memory 702 complete communication with each other through the bus 703;
the processor 701 is configured to invoke program instructions in the memory 702 to perform the methods provided by the above-described method embodiments, for example, including: acquiring credit investigation characteristics; removing redundant sign features through correlation detection and multiple collinearity calculation, and screening out access module sign features; constructing a scene credit model 60 based on the entry modeling credit features; acquiring income characteristic data of a user to be trusted; correcting the income characteristic data from different dimensions, and dividing the corrected income characteristic data into intervals; and inputting the income characteristic data of each interval into the scene trust model 60 to obtain trust results.
The present embodiment provides a non-transitory computer readable medium storing computer instructions that cause a computer to perform the methods provided by the above-described method embodiments, for example, including: acquiring credit investigation characteristics; removing redundant sign features through correlation detection and multiple collinearity calculation, and screening out access module sign features; constructing a scene credit model 60 based on the entry modeling credit features; acquiring income characteristic data of a user to be trusted; correcting the income characteristic data from different dimensions, and dividing the corrected income characteristic data into intervals; and inputting the income characteristic data of each interval into the scene trust model 60 to obtain trust results.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware associated with program instructions, where the foregoing program may be stored in a computer readable medium, and when executed, the program performs steps including the above method embodiments; and the aforementioned medium includes: various media that can store program code, such as ROM, RAM, magnetic or optical disks.
The apparatus embodiments described above are merely illustrative, wherein elements illustrated as separate elements may or may not be physically separate, and elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable medium such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method of the respective embodiments or parts of the embodiments.
While the invention has been described in detail in the foregoing general description and specific examples, it will be apparent to those skilled in the art that modifications and improvements can be made thereto. Accordingly, such modifications or improvements may be made without departing from the spirit of the invention and are intended to be within the scope of the invention as claimed.
Claims (10)
1. A machine learning-based scene credit method, which is characterized by comprising the following steps:
acquiring credit investigation characteristics;
removing redundant sign features through correlation detection and multiple collinearity calculation, and screening out access module sign features;
constructing a scene credit-giving model based on the entry-module credit-giving characteristics;
acquiring income characteristic data of a user to be trusted;
correcting the income characteristic data from different dimensions, and dividing the corrected income characteristic data into intervals;
and inputting the income characteristic data of each interval into the scene credit-giving model to obtain a credit-giving result.
2. The machine learning based scene credit method of claim 1, wherein said constructing a scene credit model based on said in-mold credit features comprises:
dividing the module-entering credit characteristics into a training set, a verification set and a test set;
training the scene credit model based on the training set;
performing performance verification on the scene credit-giving model based on the verification set, and storing the scene credit-giving model meeting performance conditions;
and evaluating the trust result of the scene trust model based on the test set.
3. The machine learning based scene credit method according to claim 2, wherein the correcting the revenue feature data from different dimensions and dividing the corrected revenue feature data into intervals includes:
judging whether a co-person exists in the monthly income characteristic data of which the monthly income is lower than the public accumulation fund repayment amount and the commodity credit repayment amount, if so, judging whether the total of the monthly income characteristic data of the co-person and the user to be trusted is lower than a designated multiple of monthly liabilities, and if so, deleting the income characteristic data;
and when the credit card usage amount of the user to be trusted is too high in a certain period of time, the income characteristic data of the user to be trusted is adjusted.
4. The machine learning based scene credit method according to claim 3, wherein said inputting the income characteristic data of each section into the scene credit model to obtain credit result includes:
predicting the income interval of each interval, assigning and analyzing each predicted income interval, and evaluating the income characteristic data by combining with the upper limit of months to obtain the credit giving amount.
5. A machine learning based scene trust system, comprising:
the first acquisition module is used for acquiring credit investigation characteristics;
the screening module is used for removing redundant sign features through correlation detection and multiple collinearity calculation and screening out in-out module sign features;
the construction module is used for removing redundant sign features and screening out in-out module sign features through correlation detection and multiple collinearity calculation;
the second acquisition module is used for acquiring income characteristic data of the user to be trusted;
the correction module is used for correcting the income characteristic data from different dimensions and dividing the corrected income characteristic data into sections;
and receiving the income characteristic data input of each interval based on the scene credit giving model to obtain a credit giving result.
6. The machine learning based scenario credit system of claim 5, wherein the building module is further configured to:
dividing the module-entering credit characteristics into a training set, a verification set and a test set; training the scene credit model based on the training set; performing performance verification on the scene credit-giving model based on the verification set, and storing the scene credit-giving model meeting performance conditions; and evaluating the trust result of the scene trust model based on the test set.
7. The machine learning based scenario credit system of claim 6, wherein the correction module is further configured to:
judging whether a co-person exists in the monthly income characteristic data of which the monthly income is lower than the public accumulation fund repayment amount and the commodity credit repayment amount, if so, judging whether the total of the monthly income characteristic data of the co-person and the user to be trusted is lower than a designated multiple of monthly liabilities, and if so, deleting the income characteristic data; and when the credit card usage amount of the user to be trusted is too high in a certain period of time, the income characteristic data of the user to be trusted is adjusted.
8. The machine learning based scenario trust system of claim 7, wherein the scenario trust model is further configured to:
predicting the income interval of each interval, assigning and analyzing each predicted income interval, and evaluating the income characteristic data by combining with the upper limit of months to obtain the credit giving amount.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any one of claims 1 to 4 when the computer program is executed.
10. A non-transitory computer readable medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method according to any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211657560.5A CN116091200A (en) | 2022-12-22 | 2022-12-22 | Scene credit granting system and method based on machine learning, electronic equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211657560.5A CN116091200A (en) | 2022-12-22 | 2022-12-22 | Scene credit granting system and method based on machine learning, electronic equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116091200A true CN116091200A (en) | 2023-05-09 |
Family
ID=86207424
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211657560.5A Pending CN116091200A (en) | 2022-12-22 | 2022-12-22 | Scene credit granting system and method based on machine learning, electronic equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116091200A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117808577A (en) * | 2024-03-01 | 2024-04-02 | 杭银消费金融股份有限公司 | Trusted processing method based on multi-factor dynamic adjustment |
-
2022
- 2022-12-22 CN CN202211657560.5A patent/CN116091200A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117808577A (en) * | 2024-03-01 | 2024-04-02 | 杭银消费金融股份有限公司 | Trusted processing method based on multi-factor dynamic adjustment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| De Fontnouvelle et al. | Using loss data to quantify operational risk | |
| CN108665159A (en) | A kind of methods of risk assessment, device, terminal device and storage medium | |
| CN109389494B (en) | Loan fraud detection model training method, loan fraud detection method and device | |
| CN111461857A (en) | Personal online credit method, device, system, equipment and medium for small and medium-sized banks | |
| CN111383091A (en) | Asset securitization pricing method and device | |
| CN113919886A (en) | Data characteristic combination pricing method and system based on summer pril value and electronic equipment | |
| CN117010762A (en) | Data evaluation method, device, computer equipment and storage medium | |
| CN116091200A (en) | Scene credit granting system and method based on machine learning, electronic equipment and medium | |
| CN116596659A (en) | Enterprise intelligent credit approval method, system and medium based on big data wind control | |
| CN111506876A (en) | Data prediction analysis method, system, equipment and readable storage medium | |
| JP2010225103A (en) | Investment income/expenditure risk analysis method, program and investment income/expenditure risk analysis device | |
| CN117934154A (en) | Transaction risk prediction method, model training method, device, equipment, medium and program product | |
| CN117952740A (en) | Method, device and server for determining resource amount processing strategy of client | |
| CN116957777A (en) | Method, device, electronic equipment, medium and program product for determining loan amount | |
| CN116823471A (en) | Transaction policy return method and device, electronic equipment and storage medium | |
| CN117252677A (en) | Credit line determination method and device, electronic equipment and storage medium | |
| US20150170269A1 (en) | Real estate market condition indicator | |
| Lilley et al. | Credit supply and house prices: Evidence from conforming loan limits | |
| CN114240598A (en) | Credit line model generation method, credit line determination method and device | |
| CN114693428A (en) | Data determination method and device, computer readable storage medium and electronic equipment | |
| CN114240605A (en) | Loan calculation method and device, computer equipment and storage medium | |
| CN113807943A (en) | Multi-factor valuation method, system, medium and equipment for bad assets | |
| CN116151670B (en) | Intelligent evaluation method, system and medium for marketing project quality of marketing business | |
| CN112862602B (en) | User request determining method, storage medium and electronic device | |
| WO2023038571A1 (en) | Multilevel, multivariate loan request evaluation platform and evaluation method |
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 |