CN110335141A - A kind of accrediting amount based on multi-model determines method, apparatus and electronic equipment - Google Patents
A kind of accrediting amount based on multi-model determines method, apparatus and electronic equipment Download PDFInfo
- Publication number
- CN110335141A CN110335141A CN201910582538.0A CN201910582538A CN110335141A CN 110335141 A CN110335141 A CN 110335141A CN 201910582538 A CN201910582538 A CN 201910582538A CN 110335141 A CN110335141 A CN 110335141A
- Authority
- CN
- China
- Prior art keywords
- amount
- model
- basic
- accrediting
- dynamic gene
- 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 42
- 108090000623 proteins and genes Proteins 0.000 claims abstract description 73
- 238000012549 training Methods 0.000 claims description 37
- 230000006399 behavior Effects 0.000 claims description 4
- 206010016256 fatigue Diseases 0.000 claims description 3
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 claims description 2
- 239000010931 gold Substances 0.000 claims description 2
- 229910052737 gold Inorganic materials 0.000 claims description 2
- 238000012545 processing Methods 0.000 description 11
- 238000010801 machine learning Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 6
- 238000004590 computer program Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 230000005611 electricity Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000014509 gene expression Effects 0.000 description 3
- 238000009434 installation Methods 0.000 description 3
- 239000000203 mixture Substances 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 239000000047 product Substances 0.000 description 3
- 241001269238 Data Species 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000005291 magnetic effect Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 239000013589 supplement Substances 0.000 description 2
- 241001062009 Indigofera Species 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 210000004027 cell Anatomy 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 210000000352 storage cell Anatomy 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000035922 thirst Effects 0.000 description 1
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)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of accrediting amounts based on multi-model to determine method, apparatus and electronic equipment and computer-readable medium.The method establishes a basic amount model, and the basic accrediting amount of financial user is calculated based on the basis amount model, at least one amount Dynamic gene model is established simultaneously, and the amount Dynamic gene of the financial user is calculated based on the amount Dynamic gene model.Finally, determining the accrediting amount of the financial user based on the amount Dynamic gene that the basic accrediting amount and each amount Dynamic gene model are calculated.The present invention can comprehensively consider the actual conditions of Debit User, provide more matching and the accurate accrediting amount, while reducing the cost of manual intervention, improve efficiency.
Description
Technical field
The present invention relates to computer information processing fields, determine in particular to a kind of accrediting amount in multi-model
Method, apparatus, electronic equipment and computer-readable medium.
Background technique
With economic rapid development, people can solve to ask caused by insufficient funds by loan in insufficient funds
Topic.In existing loan transaction, user generally requires when submitting loan application and fills in personal information, and loan platform is connecing
After receiving loan requests, the personal information for being also generally basede on user is verified, and finally provides corresponding loan according to personal information.
But this pattern of lending is for a user, and loan limit if desired is higher than the loan limit that lending platforms provide, and can reduce use
Family experience.For lending platforms, determine whether to provide a loan only according to personal information, reliability is low, and credit risk is big.
Traditional accrediting amount strategy mainly based on rule, expertise and naive model, needs more people to participate in, maintenance
Get up complex.Moreover, general accrediting amount model is determined by risk and user's borrowing potential, dimensional comparison is dull,
Lack accuracy and flexibility.
Summary of the invention
Present invention seek to address that the existing accrediting amount determines that the dimension that method is based on is more single, lacks flexibility,
The high problem of the cost of manual maintenance.
In order to solve the above-mentioned technical problem, first aspect present invention proposes a kind of accrediting amount determination side based on multi-model
Method, comprising:
A basic amount model is established, and calculates the basic accrediting amount of financial user based on the basis amount model；
At least one amount Dynamic gene model is established, and the financial user is calculated based on the amount Dynamic gene model
Amount Dynamic gene；
Based on the amount Dynamic gene that the basic accrediting amount and each amount Dynamic gene model are calculated, institute is determined
State the accrediting amount of financial user.
The step of a preferred embodiment of the invention, the accrediting amount of the determination financial user, wraps
It includes:
The basic accrediting amount and each amount Dynamic gene are tired out multiplied to the accrediting amount.
A preferred embodiment of the invention, the method also includes:
Training dataset is established, the basic amount model and each amount Dynamic gene model are trained.
A preferred embodiment of the invention, for training the data set input variable of the basic amount model
Related coefficient between the target variable of each data set of each amount Dynamic gene model is lower than predetermined threshold.
A preferred embodiment of the invention, the threshold value is between 0.2 to 0.4.
A preferred embodiment of the invention, for training the input of data set of the basic amount model to become
Amount includes assets or fund class index, for training the input variable of data set of each amount Dynamic gene model not include
Assets or fund class index.
A preferred embodiment of the invention, for training the data set of each amount Dynamic gene model
Target variable is chosen from following index: moving branch class index, default risk class index, except its of dynamic branch class or default risk class
Its user behavior shows class index.
The second aspect of the present invention proposes a kind of accrediting amount determining device based on multi-model, comprising:
Basic amount module for establishing a basic amount model, and calculates finance based on the basis amount model and uses
The basic accrediting amount at family；
Amount adjusts module, for establishing at least one amount Dynamic gene model, and is based on the amount Dynamic gene mould
Type calculates the amount Dynamic gene of the financial user；
Determining module, the amount tune for being calculated based on the basic accrediting amount and each amount Dynamic gene model
Integral divisor determines the accrediting amount of the financial user.
A preferred embodiment of the invention, the determining module are also used to:
The basic accrediting amount and each amount Dynamic gene are tired out multiplied to the accrediting amount.
A preferred embodiment of the invention further includes training module, for establishing training dataset, to described
Basic amount model and each amount Dynamic gene model are trained.
A preferred embodiment of the invention, for training the data set input variable of the basic amount model
Related coefficient between the target variable of each data set of each amount Dynamic gene model is lower than predetermined threshold.
A preferred embodiment of the invention, the threshold value is between 0.2 to 0.4.
A preferred embodiment of the invention, for training the input of data set of the basic amount model to become
Amount includes assets or fund class index, for training the input variable of data set of each amount Dynamic gene model not include
Assets or fund class index.
A preferred embodiment of the invention, for training the data set of each amount Dynamic gene model
Target variable is chosen from following index: moving branch class index, default risk class index, except its of dynamic branch class or default risk class
Its user behavior shows class index.
In order to solve the above-mentioned technical problem, third aspect present invention propose a kind of electronic equipment comprising processor and
The memory of computer executable instructions is stored, the computer executable instructions when executed execute the processor
The method stated.
In order to solve the above-mentioned technical problem, fourth aspect present invention proposes a kind of computer readable storage medium, this is described
Computer-readable recording medium storage one or more program is realized when one or more of programs are executed by processor
Above-mentioned method.
The accrediting amount is determined since present invention employs multiple models, can comprehensively consider the practical feelings of Debit User
Condition provides more matching and the accurate accrediting amount；Meanwhile the present invention is produced by the way of the automaticmanual intelligence computation of amount
Raw amount, can minimize the cost of manual intervention, and improve efficiency.
Detailed description of the invention
In order to keep technical problem solved by the invention, the technological means of use and the technical effect of acquirement clearer,
Detailed description of the present invention specific embodiment below with reference to accompanying drawings.But it need to state, drawings discussed below is only this
The attached drawing of the exemplary embodiment of invention, to those skilled in the art, without creative efforts,
The attached drawing of other embodiments can be obtained according to these attached drawings.
Fig. 1 is the flow chart that the accrediting amount of the invention based on multi-model determines method；
Fig. 2 is the flow diagram of one embodiment that the accrediting amount of the invention based on multi-model determines method；
Fig. 3 is the module composition figure of the accrediting amount determining device of the invention based on multi-model；
Fig. 4 is the structural block diagram of the exemplary embodiment of a kind of electronic equipment according to the present invention；
Fig. 5 is the schematic diagram of a computer-readable medium embodiment of the invention.
Specific embodiment
Exemplary embodiment of the present invention is more fully described with reference to the drawings, although each exemplary embodiment
Can by it is a variety of it is specific in a manner of implement, but be not understood that the invention be limited to embodiment set forth herein.On the contrary, providing this
A little exemplary embodiments are easily facilitated inventive concept being comprehensively communicated to ability to keep the contents of the present invention more complete
The technical staff in domain.
Under the premise of meeting technical concept of the invention, the properity described in some specific embodiment, effect
Fruit or other features can be integrated in any suitable manner in one or more other embodiments.
During the introduction for specific embodiment, the datail description to properity, effect or other features is
In order to enable those skilled in the art to fully understand embodiment.But, it is not excluded that those skilled in the art can be
Under specific condition, implement the present invention not contain the technical solution of above structure, performance, effect or other features.
Flow chart in attached drawing is only a kind of illustrative process demonstration, and not representing must include stream in the solution of the present invention
All contents, operation and step in journey figure, also not representing must execute according to sequence shown in figure.For example, stream
Operation/the step having in journey figure can decompose, and some operation/steps can merge or part merges, etc., not depart from this hair
In the case where bright inventive concept, the execution sequence shown in flow chart can change according to the actual situation.
What the block diagram in attached drawing typicallyed represent is functional entity, might not be necessarily opposite with physically separate entity
It answers.I.e., it is possible to realize these functional entitys using software form, or in one or more hardware modules or integrated circuit in fact
These existing functional entitys, or these functions reality is realized in heterogeneous networks and/or processor device and/or microcontroller device
Body.
Respectively the same reference numbers in the drawings refer to same or similar element, component or parts, thus hereinafter may
It is omitted to same or similar element, component or partial repeated description.Although should also be understood that may use the herein
One, the attribute of the expressions such as second, third number describes various devices, element, component or part, but these devices, element,
Component or part should not be limited by these attributes.That is, these attributes are intended merely to distinguish one and another one.Example
Such as, the first device is also referred to as the second device, but without departing from the technical solution of essence of the invention.In addition, term "and/or",
" and/or " refer to all combinations including any one or more in listed project.
In view of the existing defect for determining the credit accrediting amount using single model, the present invention proposes a kind of based on more
The accrediting amount of model determines method.The main thought of this method is, it is contemplated that the accrediting amount is codetermined by Multiple factors, is
Reflect effect of the different factors for the accrediting amount more accurately, propose to establish the basic accrediting amount and amount adjustment because
Son, and model is individually established to each Dynamic gene, so as to quantify different factors more accurately in the accrediting amount
Effect.
Fig. 1 is the flow chart that the accrediting amount of the invention based on multi-model determines method.As shown in Figure 1, of the invention
Method includes:
S1, a basic amount model is established, and calculates the basic credit volume of financial user based on the basis amount model
Degree.
In this step, we establish a basic amount model using existing mode.Basic amount model can be adopted
With machine learning model, such as xgboost model or neural network model etc..When using machine learning model, it usually needs
It establishes a training dataset and model is trained.Basic amount model can be according to the basic attribute data of user, money
Index of golden assets class etc. generates a basic amount value.
Training dataset is typically derived from history Debit User data.In training, it usually needs in specified data set
Input variable (input parameter) and target variable (target variable).In the present invention, due to the basic main task of amount model
The basic demand for loan that user is measured according to the essential attribute of user, moreover, in order to avoid with amount Dynamic gene model
Correlation it is too strong, the present invention is preferably in the training process of basic amount model, using compared with based on or simple input
Variable is trained.It is furthermore preferred that can be using the index including basic attribute data and investment assetses class as input variable
Carry out training pattern, and in the other amount Dynamic gene models of training, input variable does not include assets or fund class index.
The basic attribute data is submitted when being, for example, the registration credit product such as age, gender, educational background, occupation of user
Essential information；Capital fund data may include income, debt, fixed assets, monthly average consumption volume, credit card amount etc..
S2, at least one amount Dynamic gene model is established, and the finance is calculated based on the amount Dynamic gene model
The amount Dynamic gene of user.
Unlike the prior art, the invention also includes establish at least one amount Dynamic gene model.Theoretically come
It says, the number of amount Dynamic gene model is more, higher to the accuracy of the adjustment of the accrediting amount.But the increase of model
Data operation quantity similarly is increased, increases cost.In addition, excessive amount Dynamic gene model is also it is difficult to ensure that each mould
Correlation control between type is within the acceptable range.If the correlation between model is excessive, the weight of the factor may cause
It takes a second test and considers and influence the accuracy of the accrediting amount.The present invention is preferably 2 to 4 amount Dynamic gene models.
For each amount Dynamic gene model, machine learning model can also be used.For machine learning model, usually also
It needs to establish training dataset to be trained.For being trained to the basic amount model and each amount Dynamic gene model
Training dataset can be the same data set, different data sets can also be selected.But in order to guarantee basic amount mould
Correlation between type and each amount Dynamic gene model is unlikely to excessive, on the one hand, for train each amount adjustment because
The input variable of the data set of submodel can not include assets or fund class index, on the other hand, for training the basis
Phase relation between the target variable of each data set of the data set input variable of amount model and each amount Dynamic gene model
Number may be controlled to lower than predetermined threshold.It can be by measuring and calculating, by threshold value control between 0.2 to 0.4.
For example, referring to for training the target variable of the data set of each amount Dynamic gene model to can be dynamic branch class
Mark, default risk class index, and except other user behaviors of dynamic branch class or default risk class show class index, such as party
Behavioral indicator etc..Correspondingly, these achievement datas can be rejected in the input variable of basic amount model.
When the target variable of the data set of amount Dynamic gene model is branch class index, then dynamic Zhi Yinzi is produced,
When the target variable of the data set of amount Dynamic gene model is default risk class index, then produces the overdue factor or other are disobeyed
About factor etc..
S3, the amount Dynamic gene being calculated based on the basic accrediting amount and each amount Dynamic gene model, really
The accrediting amount of the fixed financial user.
When obtaining the basic accrediting amount and amount Dynamic gene by step S1 and step S2, gold can be calculated accordingly
Melt the accrediting amount of user.A kind of simple and effective way is, by the basic accrediting amount and each amount adjustment because
Son tires out multiplied to the accrediting amount.
But the present invention is not excluded for other calculation methods, for example, it is also possible to add volume on the basis of the basic accrediting amount
It spends Dynamic gene and one and adjusts the product of basic amount, at this point, amount Dynamic gene can be negative value.
Fig. 2 is the flow diagram of one embodiment that the accrediting amount of the invention based on multi-model determines method.Under
Face describes one embodiment of the present of invention referring to Fig. 2.
As shown in Fig. 2, the embodiment calculates the accrediting amount of financial user using multiple machine learning models.In order to right
Multiphase machine learning model is trained, which constructs a training dataset.In the embodiment, model is respectively base
Plinth amount model, dynamic branch factor model and overdue factor model, these three models all use xgboost model to construct.
As shown, above three model is all trained using the data that same training data is concentrated.But at other
In embodiment, it can also be trained using the data that different training datas are concentrated, or using the different numbers in same data set
It is trained according to entry.
In this embodiment, training dataset includes a large amount of financial user data, including basic data, accrediting amount number
According to, capital fund class achievement data, dynamic branch class achievement data and overdue class achievement data.Certainly, in actual user data also
It may include other all kinds of data, can be interpreted to cover in basic data, can also be interpreted not above-mentioned each
Within class data, but the substantive process of the method for the present invention is not influenced.
In this embodiment, as shown in Fig. 2, the basis amount model is in training, select credit it is preferable, without overdue
Financial user data, and using basic data and capital fund class index as input variable, accrediting amount data are as target
Variable.And in dynamic branch factor model, it is instructed as input variable, dynamic branch class index as target variable using basic data
Practice；In overdue factor model, it is trained as input variable, overdue class index as target variable using basic data.
Referring back to Fig. 2, completed after training when to each model, so that it may the calculating of credit volume is carried out using above-mentioned model.
For basic amount model, when it receives the data of a new user, a basic credit can be directly generated
Amount.Certainly, which can be some discontinuous specific amounts, for example, 5000,5500 ..., 10000,11000 ... etc.,
And it has a lower and upper limit, and lower limit is, for example, 2000, and the upper limit is, for example, 300,000.These data can be in modelling
When set.
For moving branch factor model, when it receives the data of a new user, what is firstly generated is a dynamic branch
Scoring.What dynamic branch scoring indicated is the dynamic branch probability for the user that model provides, and the fund for measuring user is hungered and thirst degree, such as
Generate the probability that branch is moved in user 7 days.The scoring can be between zero and one, and bigger expression user was more possible in 7 days
Dynamic branch.
In order to which the dynamic branch scoring to be converted to the dynamic Zhi Yinzi of amount, which establishes a corresponding table.
The table is for example as follows:
| Dynamic branch scoring | Dynamic Zhi Yinzi |
| 0.10-0.15 | 0.2 |
| 0.15-0.20 | 0.3 |
| 0.20-0.25 | 0.4 |
| … | … |
| 0.55-0.60 | 1.1 |
| … | … |
| 0.95-1.00 | 1.9 |
According to the correspondence table, it may be convenient to which the scoring of dynamic branch is converted to dynamic Zhi Yinzi.One kind is shown in the correspondence table
Simple linear corresponding relation, certainly, the present invention can also be using other nonlinear correspondence relations.
Similar, for exceeding its factor model, when it receives the data of a new user, what is firstly generated is one
A overdue scoring.What this exceeded that its scoring indicates is the user that provides of model probability overdue after dynamic branch, measures the letter of user
Use risk.Such as generate user it is overdue be more than 30 probability.The scoring is also possible between zero and one, but it is noted that should
In embodiment, the bigger expression user of the scoring is more possible to overdue in 7 days.
In order to which the overdue scoring is also converted into the overdue factor, which also establishes a corresponding table.
It is as follows:
| Overdue scoring | The overdue factor |
| 0.95-0.90 | 0.2 |
| 0.90-0.85 | 0.3 |
| 0.85-0.80 | 0.4 |
| … | … |
| 0.50-0.45 | 1.1 |
| … | … |
| 0.10-0.05 | 1.9 |
Likewise, according to the correspondence table, it may be convenient to which overdue scoring is converted to the overdue factor.Although the correspondence table
A kind of simple linear corresponding relation is shown, but the present invention can also be using other nonlinear correspondence relations.
For the new user A, if the basic amount that basic amount model provides is 10000 yuan, move branch factor model and
Overdue factor model exports dynamic Zhi Yinzi 1.2 and the overdue factor 1.5 respectively, in this way, the embodiment with 10000 × 1.2 × 1.5 come
It calculates, obtains 18000 accrediting amount.For another example for user B, the basic amount that basic amount model provides is 6000 yuan,
Overdue factor model exports not so good, and output factor is 0.8, and overdue factor model output is also not so good, and coefficient is 0.9, this
Its accrediting amount of sample is 6000 × 0.8 × 0.9, obtains 4320 accrediting amount.
It certainly, in other embodiments, can also be using other corresponding tables and corresponding algorithm.For example, can set
Corresponding table is to allow dynamic Zhi Yinzi and the overdue factor is 0 or negative.If for new user C, basic amount is 10000 yuan,
Dynamic Zhi Yinzi is 1.2, and the overdue factor is -1.5.At this moment the basic amount of adjusting can be set to be adjusted.Such as dynamic branch is adjusted
Basic amount is 1000 yuan, and the basic amount of overdue adjusting is 2000 yuan, then:
The dynamic basic amount of Zhi Yinzi+overdue adjusting of the accrediting amount=basis amount+dynamic branch adjusts basis amount × × overdue
The factor=10000+1000*1.2-1.5*2000=7200 (member).
It will be understood by those skilled in the art that realizing that all or part of the steps of above-described embodiment is implemented as by data
Manage the program that equipment (including computer) executes, i.e. computer program.It is performed in the computer program, this hair may be implemented
The above method of bright offer.Moreover, the computer program can store in computer readable storage medium, which is situated between
Matter can be the readable storage medium storing program for executing such as disk, CD, ROM, RAM, be also possible to the storage array of multiple storage medium compositions, example
Such as disk or tape storage array.The storage medium is not limited to centralised storage, is also possible to distributed storage, such as
Cloud storage based on cloud computing.
The device of the invention embodiment is described below, which can be used for executing embodiment of the method for the invention.For
Details described in apparatus of the present invention embodiment should be regarded as the supplement for above method embodiment；For in apparatus of the present invention
Undisclosed details in embodiment is referred to above method embodiment to realize.
Fig. 3 is the module composition figure of the accrediting amount determining device of the invention based on multi-model.As shown in figure 3, the reality
The accrediting amount determining device based on multi-model for applying example includes basic amount module, amount adjustment module and determining module.
Basic amount module calculates financial user for establishing a basic amount model, and based on the basis amount model
The basic accrediting amount.
Basic amount module establishes a basic amount model.Basic amount model can use machine learning model, example
Such as xgboost model or neural network model.When using machine learning model, it usually needs establish a training dataset
And model is trained.Basic amount model can give birth to according to basic attribute data, the index of investment assetses class etc. of user
At a basic amount value.
Amount adjustment module is based on the amount Dynamic gene model for establishing at least one amount Dynamic gene model
Calculate the amount Dynamic gene of the financial user.
The number that amount adjusts the amount Dynamic gene model that module is established is more, to the accurate of the adjustment of the accrediting amount
Property is higher.But the increase of model similarly increases data operation quantity, increases cost.In addition, excessive amount adjustment because
Submodel is also it is difficult to ensure that the correlation between each model controls within the acceptable range.If the correlation between model
Excessive, the repetition that may cause the factor considers and influences the accuracy of the accrediting amount.The present invention is preferably 2 to 4 amount adjustment
Factor model.
For each amount Dynamic gene model, machine learning model can also be used.For machine learning model, usually also
Training module is needed to be trained to establish training dataset.For to the basic amount model and each amount Dynamic gene mould
The training dataset that type is trained can be the same data set, can also select different data sets.But in order to guarantee
Correlation between basic amount model and each amount Dynamic gene model is unlikely to excessive, on the one hand, described each for training
The input variable of the data set of amount Dynamic gene model can not include assets or fund class index, on the other hand, for instructing
Practice the data set input variable of the basic amount model and each data set of each amount Dynamic gene model target variable it
Between related coefficient may be controlled to lower than predetermined threshold.It can be by measuring and calculating, by threshold value control between 0.2 to 0.4.
Determining module is used for the amount tune being calculated based on the basic accrediting amount and each amount Dynamic gene model
Integral divisor determines the accrediting amount of the financial user.
When basic amount module, amount adjustment module obtain the basic accrediting amount and amount Dynamic gene, determining module
The accrediting amount of financial user can be calculated accordingly.A kind of simple and effective way is, by the basic accrediting amount with
Each amount Dynamic gene tires out multiplied to the accrediting amount.But the present invention is not excluded for other calculation methods, for example, can also
The product of basic amount is adjusted to add amount Dynamic gene and one on the basis of the basic accrediting amount, at this point, amount adjusts
The factor can be negative value.
It will be understood by those skilled in the art that each module in above-mentioned apparatus embodiment can be distributed in device according to description
In, corresponding change can also be carried out, is distributed in one or more devices different from above-described embodiment.The mould of above-described embodiment
Block can be merged into a module, can also be further split into multiple submodule.
Electronic equipment embodiment of the invention is described below, which can be considered as the method for aforementioned present invention
With the embodiment of the entity form of Installation practice.For details described in electronic equipment embodiment of the present invention, should be regarded as
For the supplement of the above method or Installation practice；It, can be with for the undisclosed details in electronic equipment embodiment of the present invention
It is realized referring to the above method or Installation practice.
Fig. 4 is the structural block diagram of the exemplary embodiment of a kind of electronic equipment according to the present invention.The electronics that Fig. 4 is shown is set
A standby only example, should not function to the embodiment of the present invention and use scope bring any restrictions.
As shown in figure 4, the electronic equipment 410 of the exemplary embodiment is showed in the form of communications data processing unit.Electricity
The component of sub- equipment 410 can include but is not limited to: at least one processing unit 411, at least one storage unit 412, connection
The buses 416 of different system components (including storage unit 412 and processing unit 411), display unit 413 etc..
Wherein, the storage unit 412 is stored with computer-readable program, can be source program or all reader
Code.Described program can be executed with unit 411 processed, so that the processing unit 210 executes the various embodiments of the present invention
The step of.For example, the processing unit 411 can execute step as shown in Figure 1.
The storage unit 412 may include the readable medium of volatile memory cell form, such as random access memory
Unit (RAM) 4121 and/or cache memory unit 4122 can further include read-only memory unit (ROM) 4123.
The storage unit 412 can also include program/utility 4124 with one group of (at least one) program module 4125, this
The program module 4125 of sample includes but is not limited to: operating system, one or more application program, other program modules and journey
It may include the realization of network environment in ordinal number evidence, each of these examples or certain combination.
Bus 416 can be to indicate one of a few class bus structures or a variety of, including storage unit bus or storage
Cell controller, peripheral bus, graphics acceleration port, processing unit use any bus structures in a variety of bus structures
Local bus.
Electronic equipment 410 can also be with one or more external equipments 420 (such as keyboard, display, the network equipment, indigo plant
Tooth equipment etc.) communication, it enables a user to interact via these external equipments 420 with the electronic equipment 420, and/or make the electricity
Sub- equipment 410 can be communicated with one or more of the other data processing equipment (such as router, modem etc.).This
Kind communication can be carried out by input/output (I/O) interface 414, can also pass through network adapter 415 and one or more
Network (such as local area network (LAN), wide area network (WAN) and/or public network, such as internet) carry out.Network adapter 415 can
To be communicated by bus 416 with other modules of electronic equipment 420.It should be understood that although not shown in the drawings, electronic equipment 410
In other hardware and/or software module can be used, including but not limited to: microcode, device driver, redundant processing unit, outer
Portion's disk drive array, RAID system, tape drive and data backup storage system etc..
Fig. 5 is the schematic diagram of a computer-readable medium embodiment of the invention.As shown in figure 4, the computer journey
Sequence can store on one or more computer-readable mediums.Computer-readable medium can be readable signal medium or can
Read storage medium.Readable storage medium storing program for executing for example can be but be not limited to the system of electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor,
Device or device, or any above combination.The more specific example (non exhaustive list) of readable storage medium storing program for executing includes: tool
Have the electrical connections of one or more conducting wires, portable disc, hard disk, random access memory (RAM), read-only memory (ROM), can
Erasing programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read only memory (CD-ROM), optical storage
Device, magnetic memory device or above-mentioned any appropriate combination.When the computer program is by one or more data processings
When equipment executes, so that the computer-readable medium can be realized the above method of the invention.
Through the above description of the embodiments, those skilled in the art it can be readily appreciated that the present invention describe it is exemplary
Embodiment can also be realized by software realization in such a way that software is in conjunction with necessary hardware.Therefore, according to this hair
The technical solution of bright embodiment can be embodied in the form of software products, which can store calculates at one
In the readable storage medium of machine (can be CD-ROM, USB flash disk, mobile hard disk etc.) or on network, including some instructions are so that one
Platform data processing equipment (can be personal computer, server or network equipment etc.) executes above-mentioned side according to the present invention
Method.
The computer readable storage medium may include in a base band or the data as the propagation of carrier wave a part are believed
Number, wherein carrying readable program code.The data-signal of this propagation can take various forms, including but not limited to electromagnetism
Signal, optical signal or above-mentioned any appropriate combination.Readable storage medium storing program for executing can also be any other than readable storage medium storing program for executing
Readable medium, the readable medium can send, propagate or transmit for by instruction execution system, device or device use or
Person's program in connection.The program code for including on readable storage medium storing program for executing can transmit with any suitable medium, packet
Include but be not limited to wireless, wired, optical cable, RF etc. or above-mentioned any appropriate combination.
The program for executing operation of the present invention can be write with any combination of one or more programming languages
Code, described program design language include object oriented program language-Java, C++ etc., further include conventional
Procedural programming language-such as " C " language or similar programming language.Program code can be fully in user
It calculates and executes in equipment, partly executes on a user device, being executed as an independent software package, partially in user's calculating
Upper side point is executed on a remote computing or is executed in remote computing device or server completely.It is being related to far
Journey calculates in the situation of equipment, and remote computing device can pass through the network of any kind, including local area network (LAN) or wide area network
(WAN), it is connected to user calculating equipment, or, it may be connected to external computing device (such as utilize ISP
To be connected by internet).
In conclusion the present invention can execute method, apparatus, electronic equipment or the computer-readable medium of computer program
To realize.The communications data processing units such as microprocessor or digital signal processor (DSP) can be used in practice to come in fact
Existing some or all functions of the invention.
Particular embodiments described above has carried out further in detail the purpose of the present invention, technical scheme and beneficial effects
It describes in detail bright, it should be understood that the present invention is not inherently related to any certain computer, virtual bench or electronic equipment, various
The present invention also may be implemented in fexible unit.The above is only a specific embodiment of the present invention, is not limited to this hair
Bright, all within the spirits and principles of the present invention, any modification, equivalent substitution, improvement and etc. done should be included in the present invention
Protection scope within.
Claims (10)
1. a kind of accrediting amount based on multi-model determines method characterized by comprising
A basic amount model is established, and calculates the basic accrediting amount of financial user based on the basis amount model；
At least one amount Dynamic gene model is established, and calculates the volume of the financial user based on the amount Dynamic gene model
Spend Dynamic gene；
Based on the amount Dynamic gene that the basic accrediting amount and each amount Dynamic gene model are calculated, the gold is determined
Melt the accrediting amount of user.
2. the accrediting amount according to claim 1 based on multi-model determines method, it is characterised in that: described in the determination
The step of accrediting amount of financial user includes:
The basic accrediting amount and each amount Dynamic gene are tired out multiplied to the accrediting amount.
3. the accrediting amount according to claim 1 or 2 based on multi-model determines method, which is characterized in that the method
Further include:
Training dataset is established, the basic amount model and each amount Dynamic gene model are trained.
4. the accrediting amount according to claim 3 based on multi-model determines method, it is characterised in that: for described in training
Phase between the target variable of each data set of the data set input variable of basic amount model and each amount Dynamic gene model
Relationship number is lower than predetermined threshold.
5. the accrediting amount according to claim 4 based on multi-model determines method, it is characterised in that: the threshold value exists
Between 0.2 to 0.4.
6. the accrediting amount according to claim 4 based on multi-model determines method, which is characterized in that for described in training
The input variable of the data set of basic amount model includes assets or fund class index, for training each amount Dynamic gene
The input variable of the data set of model does not include assets or fund class index.
7. the accrediting amount according to claim 6 based on multi-model determines method, which is characterized in that for described in training
The target variable of the data set of each amount Dynamic gene model is chosen from following index: dynamic branch class index, default risk class
Index, except other user behaviors of dynamic branch class or default risk class show class index.
8. a kind of accrediting amount determining device based on multi-model characterized by comprising
Basic amount module calculates financial user's for establishing a basic amount model, and based on the basis amount model
The basic accrediting amount；
Amount adjusts module, for establishing at least one amount Dynamic gene model, and based on the amount Dynamic gene model
Calculate the amount Dynamic gene of the financial user；
Determining module, amount adjustment for being calculated based on the basic accrediting amount and each amount Dynamic gene model because
Son determines the accrediting amount of the financial user.
9. a kind of electronic equipment, comprising:
Processor；And
The memory of computer executable instructions is stored, the computer executable instructions when executed hold the processor
Row method according to any one of claims 1-7.
10. a kind of computer readable storage medium, wherein the computer-readable recording medium storage one or more program,
When one or more of programs are executed by processor, method of any of claims 1-7 is realized.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910582538.0A CN110335141A (en) | 2019-06-29 | 2019-06-29 | A kind of accrediting amount based on multi-model determines method, apparatus and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910582538.0A CN110335141A (en) | 2019-06-29 | 2019-06-29 | A kind of accrediting amount based on multi-model determines method, apparatus and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110335141A true CN110335141A (en) | 2019-10-15 |
Family
ID=68143763
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910582538.0A Pending CN110335141A (en) | 2019-06-29 | 2019-06-29 | A kind of accrediting amount based on multi-model determines method, apparatus and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110335141A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110992171A (en) * | 2019-12-03 | 2020-04-10 | 支付宝(杭州)信息技术有限公司 | User credit granting strategy determination method and device and electronic equipment |
| CN111179055A (en) * | 2019-12-20 | 2020-05-19 | 北京淇瑀信息科技有限公司 | Credit limit adjusting method and device and electronic equipment |
| CN111353872A (en) * | 2019-12-20 | 2020-06-30 | 上海淇玥信息技术有限公司 | Credit granting processing method and device based on financial performance value and electronic equipment |
| CN112017023A (en) * | 2020-07-15 | 2020-12-01 | 北京淇瑀信息科技有限公司 | Method and device for determining resource limit of small and micro enterprise and electronic equipment |
| CN112862594A (en) * | 2021-02-01 | 2021-05-28 | 深圳无域科技技术有限公司 | Financial risk control method, system, device and computer readable medium |
| CN113379533A (en) * | 2021-06-11 | 2021-09-10 | 重庆农村商业银行股份有限公司 | Method, device, equipment and storage medium for improving circulating loan quota |
| CN113781198A (en) * | 2020-06-09 | 2021-12-10 | 台北富邦商业银行股份有限公司 | Enterprise loan application evaluation system |
| CN113837869A (en) * | 2021-09-30 | 2021-12-24 | 重庆富民银行股份有限公司 | Multi-dimension-based customer analysis and management method |
-
2019
- 2019-06-29 CN CN201910582538.0A patent/CN110335141A/en active Pending
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110992171A (en) * | 2019-12-03 | 2020-04-10 | 支付宝(杭州)信息技术有限公司 | User credit granting strategy determination method and device and electronic equipment |
| CN111179055A (en) * | 2019-12-20 | 2020-05-19 | 北京淇瑀信息科技有限公司 | Credit limit adjusting method and device and electronic equipment |
| CN111353872A (en) * | 2019-12-20 | 2020-06-30 | 上海淇玥信息技术有限公司 | Credit granting processing method and device based on financial performance value and electronic equipment |
| CN111179055B (en) * | 2019-12-20 | 2024-04-02 | 北京淇瑀信息科技有限公司 | Credit line adjusting method and device and electronic equipment |
| CN113781198A (en) * | 2020-06-09 | 2021-12-10 | 台北富邦商业银行股份有限公司 | Enterprise loan application evaluation system |
| CN112017023A (en) * | 2020-07-15 | 2020-12-01 | 北京淇瑀信息科技有限公司 | Method and device for determining resource limit of small and micro enterprise and electronic equipment |
| CN112862594A (en) * | 2021-02-01 | 2021-05-28 | 深圳无域科技技术有限公司 | Financial risk control method, system, device and computer readable medium |
| CN113379533A (en) * | 2021-06-11 | 2021-09-10 | 重庆农村商业银行股份有限公司 | Method, device, equipment and storage medium for improving circulating loan quota |
| CN113837869A (en) * | 2021-09-30 | 2021-12-24 | 重庆富民银行股份有限公司 | Multi-dimension-based customer analysis and management method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110335141A (en) | A kind of accrediting amount based on multi-model determines method, apparatus and electronic equipment | |
| CN111340616B (en) | Method, device, equipment and medium for approving online loan | |
| CN109919684A (en) | For generating method, electronic equipment and the computer readable storage medium of information prediction model | |
| CN111192131A (en) | Financial risk prediction method and device and electronic equipment | |
| CN110348727A (en) | A kind of marketing strategy formulating method, device and electronic equipment moving branch wish based on consumer's risk grade and user | |
| CN107578332A (en) | A kind of method, apparatus, equipment and storage medium for recommending cash commodity | |
| US11687352B2 (en) | Machine-learning models applied to interaction data for determining interaction goals and facilitating experience-based modifications to interface elements in online environments | |
| CN110349000A (en) | Method, apparatus and electronic equipment are determined based on the volume strategy that mentions of tenant group | |
| CN104516897B (en) | A kind of method and apparatus being ranked up for application | |
| CN108182502A (en) | The generation method of growing quality evaluation index, the statistical method of business growth value | |
| US20190244299A1 (en) | System and method for evaluating decision opportunities | |
| CN110175641A (en) | Image-recognizing method, device, equipment and storage medium | |
| CN112784986A (en) | Feature interpretation method, device, equipment and medium for deep learning calculation result | |
| CN110415103A (en) | The method, apparatus and electronic equipment that tenant group mentions volume are carried out based on variable disturbance degree index | |
| CN109213936A (en) | product search method and device | |
| CN109960650A (en) | Application assessment method, apparatus, medium and electronic equipment based on big data | |
| CN110348995A (en) | A kind of credit risk control method, apparatus and electronic equipment based on risk attribution | |
| CN114638468A (en) | Method for evaluating data value | |
| JP2023092442A (en) | Integrated circuit chip verification method, device, electronic device and storage medium | |
| CN114970357A (en) | Energy-saving effect evaluation method, system, device and storage medium | |
| CN113965313B (en) | Model training method, device, equipment and storage medium based on homomorphic encryption | |
| CN111353872A (en) | Credit granting processing method and device based on financial performance value and electronic equipment | |
| CN113158124A (en) | Data processing method and device based on artificial intelligence and storage medium | |
| US20110264602A1 (en) | Computer-Implemented Systems And Methods For Implementing Dynamic Trading Strategies In Risk Computations | |
| CN108256667A (en) | Asset data processing method, device, storage medium and computer 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 |