CN112163943A - Method, device, equipment and medium for determining default probability - Google Patents
Method, device, equipment and medium for determining default probability Download PDFInfo
- Publication number
- CN112163943A CN112163943A CN202010981131.8A CN202010981131A CN112163943A CN 112163943 A CN112163943 A CN 112163943A CN 202010981131 A CN202010981131 A CN 202010981131A CN 112163943 A CN112163943 A CN 112163943A
- Authority
- CN
- China
- Prior art keywords
- customer
- score
- predicted
- behavior
- application
- 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
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000004364 calculation method Methods 0.000 claims abstract description 37
- 238000004590 computer program Methods 0.000 claims description 3
- 230000006399 behavior Effects 0.000 description 117
- 238000010586 diagram Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction 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
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The embodiment of the invention discloses a method, a device, equipment and a medium for determining default probability. Wherein, the method comprises the following steps: acquiring target information of a client to be predicted, and determining whether the client to be predicted is a new client or not according to the target information; if yes, calculating default scores of the customers to be predicted according to the first calculation rule; if not, calculating default scores of the customers to be predicted according to a second calculation rule; and determining the default probability of the customer to be predicted according to the default score. According to the embodiment of the invention, the default score of the loan client is calculated, so that the default probability of the loan client is accurately determined.
Description
Technical Field
The embodiment of the invention relates to a data processing technology, in particular to a method, a device, equipment and a medium for determining default probability.
Background
The loan default means that after the borrower applies for a loan from the bank, the borrower has a debt relationship with the bank but cannot fulfill the loan on time. The method for predicting the default probability of the loan clients means that comprehensive scanning and linkage analysis of data such as financial data, credit contract information, account fund transaction, external judicial information, enterprise high-management personal information and the like of the clients are realized by integrating and associating the existing information data (including financial data, behavior data and external data) of the clients and analyzing the existing information data by using professional knowledge, so that the clients are predicted to have default risks in the future. The conventional prediction method is mainly to determine the default probability of the loan based on the historical default information of the loan client and based on empirical knowledge by a professional.
The defects of the scheme are as follows: when the professional is predicted according to experience, subjective judgment is often adopted, and different professionals have different judgment standards for default probability, so that the judgment result of the default probability is inaccurate.
Disclosure of Invention
The embodiment of the application provides a method, a device, equipment and a medium for determining default probability, and can realize accurate determination of the default probability of a loan customer by calculating default scores of the loan customer.
In a first aspect, an embodiment of the present invention provides a method for determining a default probability, including:
acquiring target information of a client to be predicted, and determining whether the client to be predicted is a new client or not according to the target information;
if yes, calculating default scores of the customers to be predicted according to a first calculation rule; if not, calculating the default score of the customer to be predicted according to a second calculation rule;
and determining the default probability of the customer to be predicted according to the default score.
In a second aspect, an embodiment of the present invention provides an apparatus for determining a default probability, including:
the new client prediction module is used for acquiring target information of a client to be predicted and determining whether the client to be predicted is a new client or not according to the target information;
the default score calculating module is used for calculating the default score of the customer to be predicted according to a first calculating rule if the default score is positive; if not, calculating the default score of the customer to be predicted according to a second calculation rule;
and the default probability determining module is used for determining the default probability of the customer to be predicted according to the default scores.
In a third aspect, an embodiment of the present invention further provides an electronic device, where the electronic device includes:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the method for determining a probability of breach described in any of the embodiments of the present invention.
In a fourth aspect, the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the method for determining a default probability according to any one of the embodiments of the present invention.
The method comprises the steps of obtaining target information of a client to be predicted, and determining whether the client to be predicted is a new client or not according to the target information; and calculating default scores of the new and old customers based on different calculation rules respectively, and determining default probability of the customer to be predicted according to the default scores. According to the embodiment of the invention, the default score of the loan client is calculated, so that the default probability of the loan client is accurately determined.
Drawings
FIG. 1 is a flowchart illustrating a method for determining a default probability according to a first embodiment of the present invention;
FIG. 2 is a flowchart illustrating a method for determining a default probability according to a second embodiment of the present invention;
FIG. 3 is a schematic structural diagram of a default probability determination apparatus according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device in the fourth embodiment.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a flowchart illustrating a method for determining a default probability according to a first embodiment of the present invention. The present embodiment may be applied to situations where the loan client's probability of default is predicted. The method of the present embodiment may be performed by a device for determining the probability of breach, which may be implemented in hardware and/or software and may be configured in an electronic device. The method for determining the default probability according to any embodiment of the present application can be implemented. As shown in fig. 1, the method specifically includes the following steps:
s110, acquiring target information of a client to be predicted, and determining whether the client to be predicted is a new client or not according to the target information; if yes, go to S120; if not, go to S130.
In this embodiment, the customer to be predicted is a user who has made a loan project in a certain bank, and may include a personal user and an enterprise user; the target information is information of the client to be predicted in a certain period of time before or after the loan, and may include client basic information, debt information, real control person information, deposit information, credit investigation information, settlement information and post-loan information (such as post-loan behavior data or repayment behavior); the user in this embodiment is preferably a small micro enterprise.
Specifically, determining whether the client to be predicted is a new client according to the target information includes: comparing the client name and/or the client code in the client basic information with an information table pre-stored in the system; if the corresponding customer name and/or customer code is found in the information table, determining that the customer to be predicted is not a new user; if the customer to be predicted is not found, determining that the customer to be predicted is a new user; the information table pre-stored in the system contains the data of the history clients loan in the bank, such as the client name, the client code or the name of the client real control person.
And S120, calculating the default score of the customer to be predicted according to the first calculation rule.
In this embodiment, for the new customer and the old customer, since the historical information stored in the banking system is different, the new customer and the old customer cannot judge according to the same rule, and the default scoring needs to be implemented on the basis of not passing the rule, so as to ensure the accuracy of the default scoring of the new customer and the old customer.
In this embodiment, optionally, the calculating the default score of the customer to be predicted according to the first calculation rule includes: calculating the client application score of the client to be predicted according to a first calculation rule; the default score of the new customer calculated by the first calculation rule is not related to the loan service of the bank system before the new customer, so that the customer application score of the new customer needs to be judged according to the information before the new customer loan in order to ensure the accuracy of the default score calculation of the new customer.
And S130, calculating the default score of the customer to be predicted according to the second calculation rule.
In this embodiment, the second calculation rule is directed to the calculation of the past default score; optionally, calculating a default score of the customer to be predicted according to a second calculation rule, including: calculating the customer behavior score of the customer to be predicted according to a second calculation rule; the customer behavior score can visually reflect some basic behavior information of the old customer after the loan, so that the default probability of the old customer can be calculated based on the historical behavior information.
S140, determining the default probability of the customer to be predicted according to the default score.
In this embodiment, when the default score difference is small, it indicates that the class of users has similar features, and the difference of default probabilities of the customers with large feature similarity is smaller; and using the default probability of the customer group with larger similarity to the default score of the customer to be predicted as the default probability of the customer to be predicted. The default probability is the prediction probability that after the customer to be predicted loans and before repayment, the banking system predicts whether the repayment can be completed on time on the repayment date; and the credit investigation value of the customer to be predicted in the bank can be correspondingly evaluated by utilizing the default probability.
The method comprises the steps of obtaining target information of a client to be predicted, and determining whether the client to be predicted is a new client or not according to the target information; and calculating default scores of the new and old customers based on different calculation rules respectively, and determining default probability of the customer to be predicted according to the default scores. According to the embodiment of the invention, the default score of the loan client is calculated, so that the default probability of the loan client is accurately determined.
Example two
Fig. 2 is a flowchart illustrating a method for determining a default probability according to a second embodiment of the present invention. The embodiment is further expanded and optimized on the basis of the embodiment, and can be combined with any optional alternative in the technical scheme. As shown in fig. 2, the method includes:
s210, acquiring target information of a client to be predicted, and determining whether the client to be predicted is a new client according to the target information; if yes, go to S220; if not, go to S250.
S220, determining application information of a client to be predicted from the target information; the application information comprises at least one of post-loan information, settlement information, real control person information and deposit information.
In the embodiment, the calculation of the default score of the new customer needs to be determined according to some application information before loan; the loan information is behavior data or repayment data and other information of the loan clients after loaning, such as loan balance; the settlement information can be the settlement-related enterprise number of I's bank after loan; the real controller information may be, for example, whether there has been a bad credit record; the deposit information is the deposit balance or the deposit time of the client after the loan.
And S230, determining the client application score of the client to be predicted according to the application information.
In the embodiment, the at least one item of application information is quantized into a specific numerical value based on a preset rule, the client application score of the client to be predicted is obtained according to the sum of the numerical values, the plurality of application information are converted into a specific evaluation numerical value to serve as the client application score of the client to be predicted, and the client application score can be effectively expressed visually and clearly in a numerical mode.
Specifically, in this embodiment, determining a client application score of the client to be predicted according to the application information includes:
determining the client application scores of the application information according to the application score configuration information; the application scoring configuration information comprises an incidence relation between application information and a client application score;
and taking the sum of the client application scores of the application information as the client application score of the client to be predicted.
In this embodiment, the application scoring configuration information is composed of a corresponding relationship between each application information obtained by the application scoring configuration parameters and the client application score; the application scoring configuration parameter is a proportional value, the size range of the application scoring configuration parameter can be 0-1, and the application scoring configuration parameter can be specifically formulated adaptively according to different application scoring information of banking staff.
Specifically, table 1 is a client application scoring table obtained after each application information is quantized based on application scoring configuration parameters.
TABLE 1 customer application scoring table associated with application information
Wherein the variable represents application information; the variable value represents a specific numerical value of the application information; dividing the variable into client application scores corresponding to the quantized application information; the customer application score AScore1+ AScore2+ AScore3+ AScore4+ AScore5+ AScore6+ AScore7+ AScore8+ AScore9 of the customer to be predicted is obtained from table 1.
S240, determining an application scoring pool to which the client to be predicted belongs according to the client application scoring of the client to be predicted; taking the default probability of the application scoring pool as the default probability of the customer to be predicted; and the default probability of the application scoring pool is determined by the default probability of the historical default customers in the application scoring pool.
In the embodiment, the application score pools are classified in advance according to the application scores of the historical loan clients, and the application score of the client contained in each application score pool is in a certain range; the application scores are used as the dividing basis of each client, the clients with similar application scores are classified into one application score pool, and the default probability of the client based on the application score pool can be quickly, simply and conveniently determined when the default probability of the client is predicted.
Specifically, determining default probabilities of the application scoring pool, including; counting the total number of customers and the number of default customers of all customers in the application scoring pool; taking the ratio of the number of default customers to the total number of customers as the default probability of the application scoring pool; the default probability can also represent the default probability of other non-default customers belonging to the same sub-pool in a future period of time.
In this embodiment, optionally, determining an application score pool to which the to-be-predicted client belongs according to the client application score of the to-be-predicted client includes:
if the client application score of the client to be predicted is smaller than or equal to the first application score threshold value, determining a first application score pool to which the client to be predicted belongs;
if the client application score of the client to be predicted is larger than the first application score threshold and smaller than the second application score threshold, determining a second application score pool to which the client to be predicted belongs;
and if the client application score of the client to be predicted is detected to be larger than or equal to the second application score threshold, determining a third application score pool to which the client to be predicted belongs.
In this embodiment, the application scoring pool is divided into three levels, namely, a first application scoring pool, which belongs to a low application scoring pool; the second application scoring pool belongs to the Chinese application scoring pool; the third application scoring pool belongs to the high application scoring pool; in this embodiment, the level of the application scoring pool only represents the level of the application scoring including the customer in the scoring pool, and is unrelated to the default probability of the scoring pool, that is, the default probabilities of the three application scoring pools are relatively independent.
S250, determining behavior information of the client to be predicted from the target information; wherein the behavior information comprises at least one of debt information, credit information, deposit information and information after credit.
In this embodiment, the calculation of default scores of old customers needs to be determined according to some application information after loan; wherein, the debt information can be the amount of the client loan or the loan date, etc.; credit information is credit data of the client, such as whether the client has defaulted before, the number of defaults, the default amount and the like; the deposit information is the deposit balance or deposit time of the client after loan; the loan information is information such as behavior data or repayment data of the loan client after the loan, for example, the balance of the loan.
And S260, determining the customer behavior score of the customer to be predicted according to the behavior information.
In the embodiment, the at least one item of behavior information is quantized into a specific numerical value based on a preset rule, the customer behavior score of the customer to be predicted is obtained according to the sum of the numerical values, the plurality of pieces of behavior information are converted into a specific evaluation numerical value to serve as the customer behavior score of the customer to be predicted, and the customer behavior score can be effectively expressed visually and clearly in a numerical mode.
In this embodiment, determining a customer behavior score of the customer to be predicted according to the behavior information includes:
determining the customer behavior scores of all the behavior information according to the behavior score configuration information; the behavior scoring configuration information comprises the association relationship between the behavior information and the customer behavior scoring;
and taking the sum of the customer behavior scores of the various behavior information as the customer behavior score of the customer to be predicted.
In this embodiment, the behavior scoring configuration information is composed of a corresponding relationship between each behavior information obtained by the behavior scoring configuration parameters and the behavior score of the customer; the behavior scoring configuration parameter is a proportional value, the size range of the behavior scoring configuration parameter can be 0-1, and the behavior scoring configuration parameter can be specifically formulated adaptively according to different behavior scoring information of banking staff.
Specifically, table 2 is a customer behavior score table obtained after quantifying each behavior information based on the behavior score configuration parameter.
TABLE 2 behavior information associated client behavior scoring sheet
Wherein the variables represent behavior information; the variable value represents a specific numerical value of the behavior information; dividing the variable into client behavior scores corresponding to the quantified behavior information; the customer behavior score BScore1+ BScore2+ BScore3+ BScore4+ BScore5+ BScore6+ BScore7+ BScore8 of the customer to be predicted is derived from table 2.
S270, determining a behavior score pool to which the customer to be predicted belongs according to the customer behavior score of the customer to be predicted; taking the default probability of the behavior scoring pool as the default probability of the customer to be predicted; wherein, the default probability of the behavior scoring pool is determined by the default probability of the historical default customers in the behavior scoring pool.
In the embodiment, the behavior score pools are classified in advance according to the behavior scores of the historical loan clients, and the behavior score of the client contained in each behavior score pool is in a certain range; the behavior scores are used as the dividing basis of each customer, the customers with similar behavior scores are classified into one behavior score pool, and the default probability of the customer can be quickly, simply and conveniently determined based on the default probability of the behavior score pool to which the customer belongs when the default probability of the customer is predicted.
Specifically, determining the default probability of the behavior scoring pool, including; counting the total number of customers and the number of default customers of all customers in the behavior scoring pool; taking the ratio of the number of default customers to the total number of customers as the default probability of the behavior scoring pool; the default probability can also represent the default probability of other non-default customers belonging to the same sub-pool in a future period of time.
In this embodiment, optionally, determining a behavior score pool to which the customer to be predicted belongs according to the customer behavior score of the customer to be predicted, includes:
if the fact that the customer behavior score of the customer to be predicted is smaller than or equal to the first behavior score threshold value is detected, determining a first behavior score pool to which the customer to be predicted belongs;
if the fact that the customer behavior score of the customer to be predicted is larger than the first behavior score threshold and smaller than the second behavior score threshold is detected, determining a second behavior score pool to which the customer to be predicted belongs;
and if the customer behavior score of the customer to be predicted is detected to be larger than or equal to the second behavior score threshold value, determining a third behavior score pool to which the customer to be predicted belongs.
In the embodiment, the behavior scoring pool is divided into scoring pools of three levels by different scoring thresholds, so that the behavior scoring of the customer to be detected can accurately belong to the behavior scoring pool of one level, and the default probability of the customer to be detected can be rapidly and accurately determined.
On the basis of the foregoing embodiment, optionally, the method of this embodiment further includes:
and displaying a scoring pool to which the customer to be predicted belongs, default probability, and customer application score or customer behavior score.
In this embodiment, the determined scoring pool of a certain customer, default probability, customer application score or customer behavior score can be displayed on the display interface of the banking system at regular time, so that the staff can remind the loan officer of appropriate repayment before the loan expires based on the information; for example, the loan may be appropriately reminded before it expires, such as by mail or text message.
Specifically, if the customer to be predicted is an old customer, the current scoring pool, the current default probability and the current customer behavior score of the customer to be predicted can be used for being compared with the historical scoring pool, the historical default probability and the historical customer behavior score, respectively, and the customer to be predicted is rechecked to effectively verify whether the prediction result is accurate.
On the basis of the foregoing embodiment, optionally, the method of this embodiment further includes:
and responding to the scoring pool updating request, and updating the application scoring pool and/or the behavior scoring pool.
In this embodiment, after the loan service of the customer to be detected is finished, the corresponding scoring pool is updated according to whether the customer to be detected violates or not, so as to update the default condition of the customer in the application scoring pool and/or the behavior scoring pool in real time, thereby improving the real-time accuracy of the default probability of the application scoring pool and the behavior scoring pool.
Illustratively, after the loan service of a certain customer to be detected is finished, if the customer is a new customer loan and the customer repays the loan on time, adding the customer into the corresponding application scoring pool, and marking that the loan state is not default; and if the client is a loan of the old client and the client does not pay on time, marking the marking state of the client in the behavior scoring pool to which the client belongs as default and marking the default times.
EXAMPLE III
Fig. 3 is a schematic structural diagram of a default probability determination device in the third embodiment of the present invention, which is applicable to the case of predicting the default probability of a loan client. The device is configured in the electronic equipment, and can realize the method for determining the default probability described in any embodiment of the application. The device specifically comprises the following steps:
the new client prediction module 310 is configured to obtain target information of a client to be predicted, and determine whether the client to be predicted is a new client according to the target information;
a default score calculation module 320, configured to calculate, if yes, a default score of the customer to be predicted according to a first calculation rule; if not, calculating the default score of the customer to be predicted according to a second calculation rule;
and the default probability determination module 330 is configured to determine a default probability of the customer to be predicted according to the default score.
On the basis of the foregoing embodiment, optionally, the default score calculating module 320 is specifically configured to:
calculating the client application score of the client to be predicted according to a first calculation rule;
correspondingly, the default score calculating module 320 is further specifically configured to:
and calculating the customer behavior score of the customer to be predicted according to a second calculation rule.
On the basis of the foregoing embodiment, optionally, the default score calculation module 320 is further specifically configured to:
determining application information of the client to be predicted from the target information; the application information comprises at least one item of post-loan information, settlement information, real control person information and deposit information;
and determining the client application score of the client to be predicted according to the application information.
On the basis of the foregoing embodiment, optionally, the default score calculation module 320 is further specifically configured to:
determining the client application scores of the application information according to the application score configuration information; the application scoring configuration information comprises an incidence relation between application information and a client application score;
and taking the sum of the client application scores of the application information as the client application score of the client to be predicted.
On the basis of the foregoing embodiment, optionally, the default score calculation module 320 is further specifically configured to:
determining behavior information of the customer to be predicted from the target information; the behavior information comprises at least one of debt information, credit information, deposit information and information after credit;
and determining the customer behavior score of the customer to be predicted according to the behavior information.
On the basis of the foregoing embodiment, optionally, the default score calculation module 320 is further specifically configured to:
determining the customer behavior scores of all the behavior information according to the behavior score configuration information; the behavior scoring configuration information comprises the association relationship between behavior information and customer behavior scoring;
and taking the sum of the customer behavior scores of the various behavior information as the customer behavior score of the customer to be predicted.
On the basis of the foregoing embodiment, optionally, the default probability determination module 330 is specifically configured to:
determining an application score pool to which the customer to be predicted belongs according to the customer application score of the customer to be predicted;
taking the default probability of the application scoring pool as the default probability of the customer to be predicted; wherein the default probability of the application scoring pool is determined by the default probability of the historical default customers in the application scoring pool.
On the basis of the foregoing embodiment, optionally, the default probability determination module 330 is further specifically configured to:
if the client application score of the client to be predicted is detected to be smaller than or equal to a first application score threshold value, determining a first application score pool to which the client to be predicted belongs;
if the client application score of the client to be predicted is detected to be larger than a first application score threshold and smaller than a second application score threshold, determining a second application score pool to which the client to be predicted belongs;
and if the client application score of the client to be predicted is detected to be larger than or equal to a second application score threshold value, determining a third application score pool to which the client to be predicted belongs.
On the basis of the foregoing embodiment, optionally, the default probability determination module 330 is further specifically configured to:
determining a behavior score pool to which the customer to be predicted belongs according to the customer behavior score of the customer to be predicted;
taking the default probability of the behavior score pool as the default probability of the customer to be predicted; wherein the default probability of the behavior score pool is determined by the default probability of the historical default customers in the behavior score pool.
On the basis of the foregoing embodiment, optionally, the default probability determination module 330 is further specifically configured to:
if the customer behavior score of the customer to be predicted is smaller than or equal to a first behavior score threshold value, determining a first behavior score pool to which the customer to be predicted belongs;
if the fact that the customer behavior score of the customer to be predicted is larger than a first behavior score threshold and smaller than a second behavior score threshold is detected, determining a second behavior score pool to which the customer to be predicted belongs;
and if the customer behavior score of the customer to be predicted is detected to be larger than or equal to a second behavior score threshold value, determining a third behavior score pool to which the customer to be predicted belongs.
On the basis of the foregoing embodiment, optionally, the apparatus of this embodiment further includes:
and the display module is used for displaying the scoring pool to which the customer to be predicted belongs, default probability, customer application score or customer behavior score.
On the basis of the foregoing embodiment, optionally, the apparatus of this embodiment further includes:
and the scoring pool updating module is used for responding to a scoring pool updating request and updating the application scoring pool and/or the behavior scoring pool.
By the device for determining the default probability of the third embodiment of the invention, the default score of the loan client is calculated, so that the loan client default probability can be accurately determined.
The device for determining the default probability provided by the embodiment of the invention can execute the method for determining the default probability provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method.
Example four
Fig. 4 is a schematic structural diagram of an electronic device according to a fourth embodiment of the present invention, as shown in fig. 4, the electronic device includes a processor 410, a memory 420, an input device 430, and an output device 440; the number of the processors 410 in the electronic device may be one or more, and one processor 410 is taken as an example in fig. 4; the processor 410, the memory 420, the input device 430 and the output device 440 in the electronic apparatus may be connected by a bus or other means, and the bus connection is exemplified in fig. 4.
The memory 420 serves as a computer-readable storage medium for storing software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the method for determining a probability of breach in an embodiment of the present invention. The processor 410 executes various functional applications and data processing of the electronic device by executing the software programs, instructions and modules stored in the memory 420, namely, the method for determining the default probability provided by the embodiment of the present invention is realized.
The memory 420 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the memory 420 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, memory 420 may further include memory located remotely from processor 410, which may be connected to an electronic device over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 430 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function control of the electronic apparatus, and may include a keyboard, a mouse, and the like. The output device 440 may include a display device such as a display screen.
EXAMPLE five
The present embodiments provide a storage medium containing computer-executable instructions for implementing the method for determining a probability of breach provided by an embodiment of the present invention when executed by a computer processor.
Of course, the storage medium provided by the embodiment of the present invention contains computer-executable instructions, and the computer-executable instructions are not limited to the method operations described above, and may also perform related operations in the method for determining a default probability provided by any embodiment of the present invention.
From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly, can also be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute the methods according to the embodiments of the present invention.
It should be noted that, in the embodiment of the above search apparatus, each included unit and module are merely divided according to functional logic, but are not limited to the above division as long as the corresponding functions can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (15)
1. A method for determining a probability of breach, the method comprising:
acquiring target information of a client to be predicted, and determining whether the client to be predicted is a new client or not according to the target information;
if yes, calculating default scores of the customers to be predicted according to a first calculation rule; if not, calculating the default score of the customer to be predicted according to a second calculation rule;
and determining the default probability of the customer to be predicted according to the default score.
2. The method of claim 1, wherein calculating the default score for the customer to be forecasted according to a first calculation rule comprises:
calculating the client application score of the client to be predicted according to a first calculation rule;
correspondingly, the default score of the customer to be predicted is calculated according to a second calculation rule, and the method comprises the following steps:
and calculating the customer behavior score of the customer to be predicted according to a second calculation rule.
3. The method of claim 2, wherein calculating the customer application score of the customer to be forecasted according to a first calculation rule comprises:
determining application information of the client to be predicted from the target information; the application information comprises at least one item of post-loan information, settlement information, real control person information and deposit information;
and determining the client application score of the client to be predicted according to the application information.
4. The method of claim 3, wherein determining a customer application score for the customer to be forecasted based on the application information comprises:
determining the client application scores of the application information according to the application score configuration information; the application scoring configuration information comprises an incidence relation between application information and a client application score;
and taking the sum of the client application scores of the application information as the client application score of the client to be predicted.
5. The method of claim 2, wherein calculating the customer behavior score of the customer to be predicted according to a second calculation rule comprises:
determining behavior information of the customer to be predicted from the target information; the behavior information comprises at least one of debt information, credit information, deposit information and information after credit;
and determining the customer behavior score of the customer to be predicted according to the behavior information.
6. The method of claim 5, wherein determining a customer behavior score for the customer to be predicted based on the behavior information comprises:
determining the customer behavior scores of all the behavior information according to the behavior score configuration information; the behavior scoring configuration information comprises the association relationship between behavior information and customer behavior scoring;
and taking the sum of the customer behavior scores of the various behavior information as the customer behavior score of the customer to be predicted.
7. The method of claim 2, wherein determining a probability of breach of the customer to be forecasted based on the breach score comprises:
determining an application score pool to which the customer to be predicted belongs according to the customer application score of the customer to be predicted;
taking the default probability of the application scoring pool as the default probability of the customer to be predicted; wherein the default probability of the application scoring pool is determined by the default probability of the historical default customers in the application scoring pool.
8. The method of claim 7, wherein determining the application score pool to which the customer to be predicted belongs according to the customer application score of the customer to be predicted comprises:
if the client application score of the client to be predicted is detected to be smaller than or equal to a first application score threshold value, determining a first application score pool to which the client to be predicted belongs;
if the client application score of the client to be predicted is detected to be larger than a first application score threshold and smaller than a second application score threshold, determining a second application score pool to which the client to be predicted belongs;
and if the client application score of the client to be predicted is detected to be larger than or equal to a second application score threshold value, determining a third application score pool to which the client to be predicted belongs.
9. The method of claim 2, wherein determining a probability of breach of the customer to be forecasted based on the breach score comprises:
determining a behavior score pool to which the customer to be predicted belongs according to the customer behavior score of the customer to be predicted;
taking the default probability of the behavior score pool as the default probability of the customer to be predicted; wherein the default probability of the behavior score pool is determined by the default probability of the historical default customers in the behavior score pool.
10. The method of claim 9, wherein determining the behavior score pool to which the customer to be predicted belongs according to the customer behavior score of the customer to be predicted comprises:
if the customer behavior score of the customer to be predicted is smaller than or equal to a first behavior score threshold value, determining a first behavior score pool to which the customer to be predicted belongs;
if the fact that the customer behavior score of the customer to be predicted is larger than a first behavior score threshold and smaller than a second behavior score threshold is detected, determining a second behavior score pool to which the customer to be predicted belongs;
and if the customer behavior score of the customer to be predicted is detected to be larger than or equal to a second behavior score threshold value, determining a third behavior score pool to which the customer to be predicted belongs.
11. The method of claim 1, further comprising:
and displaying a scoring pool to which the customer to be predicted belongs, default probability, and customer application score or customer behavior score.
12. The method of claim 1, further comprising:
and responding to the scoring pool updating request, and updating the application scoring pool and/or the behavior scoring pool.
13. An apparatus for determining a probability of breach, the apparatus comprising:
the new client prediction module is used for acquiring target information of a client to be predicted and determining whether the client to be predicted is a new client or not according to the target information;
the default score calculating module is used for calculating the default score of the customer to be predicted according to a first calculating rule if the default score is positive; if not, calculating the default score of the customer to be predicted according to a second calculation rule;
and the default probability determining module is used for determining the default probability of the customer to be predicted according to the default scores.
14. An electronic device, comprising:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement a method of determining a probability of breach as claimed in any of claims 1-12.
15. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out a method of determining a probability of breach as claimed in any of claims 1 to 12.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010981131.8A CN112163943A (en) | 2020-09-17 | 2020-09-17 | Method, device, equipment and medium for determining default probability |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010981131.8A CN112163943A (en) | 2020-09-17 | 2020-09-17 | Method, device, equipment and medium for determining default probability |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112163943A true CN112163943A (en) | 2021-01-01 |
Family
ID=73858484
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010981131.8A Pending CN112163943A (en) | 2020-09-17 | 2020-09-17 | Method, device, equipment and medium for determining default probability |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112163943A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113962526A (en) * | 2021-09-24 | 2022-01-21 | 广东电力交易中心有限责任公司 | Electric power transaction service fee default risk assessment method, equipment and computer readable storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120323760A1 (en) * | 2011-06-16 | 2012-12-20 | Xerox Corporation | Dynamic loan service monitoring system and method |
| CN108416506A (en) * | 2018-02-07 | 2018-08-17 | 平安科技（深圳）有限公司 | Customer risk level management approach, server and computer readable storage medium |
| CN108648074A (en) * | 2018-05-18 | 2018-10-12 | 深圳壹账通智能科技有限公司 | Loan valuation method, apparatus based on support vector machines and equipment |
| CN111324862A (en) * | 2020-02-10 | 2020-06-23 | 深圳华策辉弘科技有限公司 | Method and system for monitoring behavior in loan |
-
2020
- 2020-09-17 CN CN202010981131.8A patent/CN112163943A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120323760A1 (en) * | 2011-06-16 | 2012-12-20 | Xerox Corporation | Dynamic loan service monitoring system and method |
| CN108416506A (en) * | 2018-02-07 | 2018-08-17 | 平安科技（深圳）有限公司 | Customer risk level management approach, server and computer readable storage medium |
| CN108648074A (en) * | 2018-05-18 | 2018-10-12 | 深圳壹账通智能科技有限公司 | Loan valuation method, apparatus based on support vector machines and equipment |
| CN111324862A (en) * | 2020-02-10 | 2020-06-23 | 深圳华策辉弘科技有限公司 | Method and system for monitoring behavior in loan |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113962526A (en) * | 2021-09-24 | 2022-01-21 | 广东电力交易中心有限责任公司 | Electric power transaction service fee default risk assessment method, equipment and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110009174B (en) | Risk recognition model training method and device and server | |
| JP6771751B2 (en) | Risk assessment method and system | |
| US11568480B2 (en) | Artificial intelligence derived anonymous marketplace | |
| CN110417721B (en) | Security risk assessment method, device, equipment and computer readable storage medium | |
| CN111008896A (en) | Financial risk early warning method and device, electronic equipment and storage medium | |
| CN111754241A (en) | User behavior perception method, device, equipment and medium | |
| CN112801670B (en) | Risk assessment method and device for payment operation | |
| CN112819611A (en) | Fraud identification method, device, electronic equipment and computer-readable storage medium | |
| CN111275338A (en) | Method, device, equipment and storage medium for judging enterprise fraud behaviors | |
| CN112785420A (en) | Credit scoring model training method and device, electronic equipment and storage medium | |
| CN111061948A (en) | User label recommendation method and device, computer equipment and storage medium | |
| CN117235608B (en) | Risk detection method, risk detection device, electronic equipment and storage medium | |
| CN113744054A (en) | Anti-fraud method, device and equipment | |
| CN112163943A (en) | Method, device, equipment and medium for determining default probability | |
| CN111325355A (en) | Method and device for determining actual control persons of enterprises, computer equipment and medium | |
| CN116975393A (en) | Enterprise portrait construction method and device and electronic equipment | |
| CN116664306A (en) | Intelligent recommendation method and device for wind control rules, electronic equipment and medium | |
| CN111401787A (en) | Site selection method, device and system | |
| CN115600818A (en) | Multi-dimensional scoring method and device, electronic equipment and storage medium | |
| CN113673870B (en) | Enterprise data analysis method and related components | |
| CN115481694A (en) | Data enhancement method, device, equipment and storage medium for training sample set | |
| CN110570301B (en) | Risk identification method, device, equipment and medium | |
| CN112686642A (en) | Video interview method and device | |
| CN111461863A (en) | Data processing method and device, computer equipment and storage medium | |
| CN112990946A (en) | Enterprise default prediction method, device, medium and electronic equipment |
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 |