CN108648016A - The audient's model method for digging and device of bank finance product - Google Patents
The audient's model method for digging and device of bank finance product Download PDFInfo
- Publication number
- CN108648016A CN108648016A CN201810457730.2A CN201810457730A CN108648016A CN 108648016 A CN108648016 A CN 108648016A CN 201810457730 A CN201810457730 A CN 201810457730A CN 108648016 A CN108648016 A CN 108648016A
- Authority
- CN
- China
- Prior art keywords
- user characteristics
- finance product
- bank finance
- product
- matrix
- 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
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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0269—Targeted advertisements based on user profile or attribute
- G06Q30/0271—Personalized advertisement
-
- 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
- G06Q40/02—Banking, e.g. interest calculation or account maintenance
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Technology Law (AREA)
- Data Mining & Analysis (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The application provides a kind of the audient's model method for digging and device of bank finance product, it is related to computer realm, the correlation degree of each user characteristics and bank finance product can be obtained, sale for bank finance product provides reference, the cost that banking personnel judge the audience of different financial products according to personal business experience is reduced, the marketing efficiency of financial product is improved.This method includes:It obtains and the relevant user characteristics of bank finance product, according to audience matrix corresponding with the relevant user characteristics structure bank finance product of bank finance product, according to each element of audience matrix, determination can indicate user characteristics weight corresponding with each user characteristics of correlation degree of bank finance product.
Description
Technical field
This application involves audient's model method for digging of field of computer technology more particularly to a kind of bank finance product and
Device.
Background technology
At this stage, many clients of bank do not know about the financial product of bank, and bank do not know yet it is different
Financial product can be keen to by which type of customer group, and the business personnel of bank to bank client when promoting financial product, and one
As be professional knowledge and experience according to itself.This method is higher to the professional knowledge and skill requirement of business personnel, manpower
Cost is higher, and the implementation cycle is longer, can not analyze in batches the audience information of financial product.
Invention content
The application provides a kind of the audient's model method for digging and device of bank finance product, reduces banking personnel
The cost that the audience of different financial products is judged according to personal business experience improves the marketing efficiency of financial product.
In order to achieve the above objectives, the application adopts the following technical scheme that:
In a first aspect, the application provides a kind of audient's model method for digging of bank finance product, this method may include:
It obtains and the relevant user characteristics of bank finance product;User characteristics include following at least two:Age, gender, history loan
Record, wage, kinsfolk's information;According to corresponding with the relevant user characteristics structure bank finance product of bank finance product
Audience matrix, the user characteristics of the element representation user of audience matrix;User characteristics represented by same row element belong to same
User;The same user characteristics of same row element representation;Determine that each user characteristics are corresponding according to each element of audience matrix
Weight, weight indicate the correlation degree of user characteristics and bank finance product.
Second aspect, the application provide a kind of audient's model excavating gear of bank finance product, which includes:It obtains
Module, processing module and determining module.Wherein, acquisition module, for obtaining and the relevant user characteristics of bank finance product;With
Family feature includes following at least two:Age, gender, history loan documentation, wage, kinsfolk's information;Processing module is used for
According to audience matrix corresponding with the relevant user characteristics structure bank finance product of bank finance product, the element of audience matrix
Indicate the user characteristics of user;User characteristics represented by same row element belong to same user;Same row element representation is same
User characteristics;Determining module, for determining the corresponding weight of each user characteristics, weight table according to each element of audience matrix
Show the correlation degree of user characteristics and bank finance product.
The third aspect, the application provide a kind of audient's model excavating gear of bank finance product, which includes:Processing
Device, memory.Wherein, memory is for storing one or more programs.The one or more program includes that computer execution refers to
It enables, when the apparatus is operative, processor executes the computer executed instructions of memory storage, so that the device executes first
In aspect and its various optional realization methods it is one of arbitrary described in bank finance product audient's model method for digging.
Fourth aspect, the application provide a kind of computer readable storage medium, are stored in computer readable storage medium
Instruction, when computer executes the instruction, which, which executes in above-mentioned first aspect and its various optional realization methods, appoints
Audient's model method for digging of bank finance product described in one of meaning.
Audient's model method for digging, the apparatus and system of bank finance product provided by the present application, first acquisition and bank
The relevant user characteristics of financial product, according to corresponding with the relevant user characteristics structure bank finance product of bank finance product
Audience matrix, according to each element of audience matrix, determination can indicate user characteristics and the correlation degree of bank finance product
The corresponding weight of each user characteristics.After the corresponding weight of each user characteristics for obtaining each bank finance product, weight
Information can provide reference for the sale of bank finance product, for example, the maximum user characteristics of weight indicate the user characteristics and silver
The correlation degree of row financial product v is maximum, and banking personnel, can preferential root when promoting bank finance product to bank client
It is promoted to it according to the maximum user characteristics of the weight of client.It reduces banking personnel and different gold is judged according to personal business experience
The cost for melting the audience of product improves the marketing efficiency of financial product.
Description of the drawings
Fig. 1 is audient's model method for digging flow chart of bank finance product provided by the embodiments of the present application;
Fig. 2 is another flow chart of audient's model method for digging of bank finance product provided by the embodiments of the present application;
Fig. 3 is the structural schematic diagram of audient's model excavating gear of bank finance product provided by the embodiments of the present application;
Fig. 4 is another structural representation of audient's model excavating gear of bank finance product provided by the embodiments of the present application
Figure;
Fig. 5 is another structural representation of audient's model excavating gear of bank finance product provided by the embodiments of the present application
Figure.
Specific implementation mode
Below in conjunction with the accompanying drawings to the audient's model method for digging and device of bank finance product provided by the embodiments of the present application
It is described in detail.
The terms "and/or", only a kind of incidence relation of description affiliated partner, indicates that there may be three kinds of passes
System, for example, A and/or B, can indicate:Individualism A exists simultaneously A and B, these three situations of individualism B.
In addition, the term " comprising " and " having " being previously mentioned in the description of the present application and their any deformation, it is intended that
It is to cover and non-exclusive includes.Such as process, method, system, product or the equipment for containing series of steps or unit do not have
It is defined in the step of having listed or unit, but further includes the steps that optionally that other are not listed or unit, or optionally
Further include for the intrinsic other steps of these processes, method, product or equipment or unit.
It should be noted that in the embodiment of the present application, " illustrative " or " such as " etc. words make example, example for indicating
Card or explanation.Be described as in the embodiment of the present application " illustrative " or " such as " any embodiment or design scheme do not answer
It is interpreted than other embodiments or design scheme more preferably or more advantage.Specifically, " illustrative " or " example are used
Such as " word is intended to that related notion is presented in specific ways.
In the description of the present application, unless otherwise indicated, the meaning of " plurality " is refer to two or more.
The embodiment of the present application provides a kind of audient's model method for digging of bank finance product, as shown in Figure 1, this method can
To include S101-S103:
S101, acquisition and the relevant user characteristics of bank finance product.
User characteristics include following at least two:Age, gender, history loan documentation, wage, kinsfolk's information.With
Kinsfolk's information in the feature of family can refer to:The age of sons and daughters, the age of parent, parent wage situation etc..
Computer can be obtained in audient's model method for digging of the bank finance product in executing the application from banking system
It takes and the relevant user characteristics of bank finance product.
Include buying or the use of the browsed bank finance product with the relevant user characteristics of bank finance product
The user characteristics at family.After selling financial product, banking system can store the sales information of financial product for bank,
In, including with the relevant user characteristics of financial product.Optionally, website of bank or bank client are browsed in terminal as user
When end, banking system can also store the user characteristics of the user and the bank finance product information that user is browsed.
S102, basis audience matrix corresponding with the relevant user characteristics structure bank finance product of bank finance product.
The user characteristics of the element representation user of audience matrix;User characteristics represented by same row element belong to same use
Family;The same user characteristics of same row element representation;It is produced according to the relevant user characteristics structure bank finance of bank finance product
The corresponding audience matrix of product.
Include step according to audience matrix corresponding with the relevant user characteristics structure bank finance product of bank finance product
Rapid S1021 and step S1022.
S1021, basis initial matrix corresponding with the relevant user characteristics structure bank finance product of bank finance product.
S1022, initial matrix is normalized according to preset algorithm, obtains the corresponding audient's square of financial product
Battle array.
Wherein, the structure initial matrix in S1021, including:Obtain the use with the relevant multiple users of bank finance product
Family feature;According to the value of each user characteristics to each element assignment of initial matrix, it is corresponding to obtain bank finance product
Initial matrix.Such as:According to following at least two in user characteristics:Age, gender, history loan documentation, wage, family at
Member's information, determines the value of each element of initial matrix.For example, following formula (1) are the initial matrixs of financial product v:
In above-mentioned formula (1), the user characteristics represented by same row element belong to same user, such as x11, x12 ...
The user characteristics that x1m is indicated belong to user A, x21, x22 ... the user characteristics that x2m is indicated belong to user B.It is above-mentioned same
The same user characteristics of column element expression, such as x11, x21 ... these elements of xn1 all indicate the age of user.x12、x22、…
These elements of xn2 all indicate the amount of the loan of user.Wherein, if the user characteristics of a certain user do not store in banking system,
It is then assigned a value of 0, for example, the age as user B does not store in banking system, then the age of user B is assigned a value of 0, other are then
According to stored user characteristics in banking system to the initial matrix assignment.
After initial matrix structure is completed, the initial matrix need to be normalized according to preset algorithm, obtained
The corresponding audience matrix of the financial product.
Optionally, the preset algorithm refers to carries out normalizing to the initial matrix using Z-score standardized methods by row
Change is handled, and the specific implementation of the algorithm can refer to the prior art, and details are not described herein again.
I.e. to above-mentioned matrix XvIt is normalized by row.The expression formula of the audience matrix obtained after normalization is:Ev=
[eij]n×m, whereinWherein, xijIt is the user spy of respective column in initial matrix
The assignment of sign,Per the corresponding preset value of column element, i.e., the average value of the user characteristics of respective column in the initial matrix for referring to, σ are
Standard deviation, N are the line number of initial matrix.
Then, the corresponding weight of each user characteristics is determined according to each element of above-mentioned audience matrix.
If the corresponding weight matrix of the user characteristics of the audience matrix is Wv=[w1,w2,...,wm], WvRefer to following symmetrical square
Battle array:
In above-mentioned formula (2), 0≤wj≤ 1, and
S103, the corresponding weight of each user characteristics is determined according to each element of audience matrix.
This kind of decision problem of the selection of multiple attribute decision making (MADM), that is, system schema depending on the satisfaction degree of multiple targets, or
The problem of being optimized for more attributes, can be applied to solve optimal case, and the quality of scheme is ranked up.According to more attributes
The characteristics of decision, above-mentioned audience matrix can regard a multiple attribute decision making (MADM) matrix, W asv=[w1,w2,...,wm] it is exactly attribute
Weight vectors.TOPSIS(Technique for Order Preference by Similarity to an Ideal
Solution approaches the ordering techniques of ideal solution) it is a kind of Multiple Attribute Decision Making Theory method, it can be according to limited a alternative
Scheme is ranked up with the degree of closeness of idealization target.
There are three main bodys in Multiple Attribute Decision Problems:Alternative set X={ x1,x2,…,xN, to weigh scheme good and bad
Attribute set A={ a1,a2,…aM, and indicate the attribute weight vector of Importance of attribute degreeThis
PlaceAlso refer to symmetrical matrix.Scheme collection X={ x1,x2,…,xNIn each scheme xi(i=1,2 ... N) it can be expressed as
For a M dimensional vectorThe vector of all schemes can be formed by multiple attribute decision making (MADM) matrix altogether.
So if by X in the applicationvSet of the row vector as an alternative, user characteristics regard one as
The attribute set of a measurement scheme quality, then according to Multiple Attribute Decision Making Theory, the product audience matrix E after normalizationv=
[eij]n×mIt is exactly a multiple attribute decision making (MADM) matrix, Wv=[w1,w2,…,wm] it is exactly attribute weight vector.If Wv=[w1,
w2,…,wm] it is known, then alternative can be ranked up using Multiple Attribute Decision Making Theory, it is optimal to provide
Scheme.But the application is in order to determine Wv=[w1,w2,…,wm].Therefore Multiple Attribute Decision Making Theory will be utilized, to solve Attribute Weight
Weight vector Wv=[w1,w2,…,wm]。
Since the significance level of different attribute is different, the influence for considering attribute weight is needed when determining ideal solution, so,
It needs to Standard Process Ev=[eij]n×mBeing weighted, i.e. formula (3):
At this point, in TOPSIS plus-minus ideal solutions by formula (4) determine, i.e.,:
Particularly, audient's feature of product is neither profit evaluation model attribute, nor cost type attribute, so, in TOPSIS
Determination plus-minus ideal solutions method and not applicable such case.
Herein, ideal solution is set as the average value of each user characteristics.Ideal solution is represented by:
In above-mentioned formula (5):If y*It is ideal solution;It is 1 of the average value composition of each row user characteristics in audience matrix
The vector of row m row,For W in symmetrical matrixvJth row element, for the unknown attribute weight vector of setting.According to
TOPSIS methods keep the quadratic sum of the distance between optimal solution and ideal solution minimum, can establish following equation group:
In above-mentioned formula (6),It is to instigate the quadratic sum of the distance between optimal solution and ideal solution minimum,For calculatingIt enablesLagrange's equation is built, it is as follows:
In above-mentioned formula (7), respectively to wjIt is 0 to seek local derviation with λ and enable the value of corresponding local derviation, i.e., following formula (8):
Equation group (8) is solved, is obtained:
Above-mentioned formula (9) is the solution of equation group (8).To Lagrange equationsIn wjSecond order local derviation is asked to build
Hesse matrixes are as follows:
Due toSoFor positive definite matrix.Therefore, in formula (9)It is
The optimal solution of Optimized model.
It gets above-mentionedLater, Wv=[w1,w2,...,wm] it is known.The corresponding each use of product v
The user characteristics at family weights shared in all user characteristics are known, wherein the maximum user characteristics of weight indicate the use
Family feature and the correlation degree of bank finance product v are maximum.For example, the weight shared by the user characteristics age is 0.7, user's loan
Weight shared by the amount of money is 0.1, then banking personnel can be according to client's when promoting bank finance product v to bank client
Age promotes to it.If for product u, the weight shared by the product u corresponding user characteristics ages is 0.15, user's loan
Weight shared by the amount of money is 0.55, then banking personnel can be according to client when promoting bank finance product u to bank client
The amount of the loan to its promote.
Audient's model method for digging of bank finance product provided by the present application obtains related to bank finance product first
User characteristics obtain bank's gold according to the value of each user characteristics to each element assignment of the initial matrix
Melt the corresponding initial matrix of product, and initial matrix is normalized according to preset algorithm, obtains financial product correspondence
Audience matrix.According to each element of audience matrix, determination can indicate being associated with for user characteristics and the bank finance product
The corresponding weight of each user characteristics of degree.It obtains in each financial product after the corresponding weight of each user characteristics, weighs
Weight can provide reference for the sale of bank finance product, for example, the maximum user characteristics of weight indicate the user characteristics and bank
The correlation degree of financial product v is maximum, and banking personnel, can preferential basis when promoting bank finance product to bank client
The age of client promotes to it.Reduce the audient group that banking personnel judge different financial products according to personal business experience
The cost of body improves the marketing efficiency of financial product.
The embodiment of the present application can carry out audient's model excavating gear of bank finance product according to above method example
The division of function module either functional unit divides each function module or functional unit for example, each function can be corresponded to,
Two or more functions can also be integrated in a processing module.Hardware both may be used in above-mentioned integrated module
Form realize, can also be realized in the form of software function module or functional unit.Wherein, right in the embodiment of the present application
The division of module or unit is schematical, only a kind of division of logic function, can there is other draw in actual implementation
The mode of dividing.
Fig. 3 shows a kind of possibility of audient's model excavating gear of bank finance product involved in above-described embodiment
Structural schematic diagram.The device includes acquisition module 201, processing module 202, determining module 203.
Wherein, the acquisition module 201, for obtaining and the relevant user characteristics of bank finance product.
The processing module 202, for building bank finance with the relevant user characteristics of bank finance product according to described
The corresponding audience matrix of product.
The determining module 203, for determining that each user characteristics are corresponding according to each element of the audience matrix
Weight.
Optionally, processing module 202 are additionally operable to build bank with the relevant user characteristics of bank finance product according to described
The corresponding initial matrix of financial product;The initial matrix is normalized according to preset algorithm, obtains the finance
The corresponding audience matrix of product.
Optionally, processing module 202 are additionally operable to:Every column element of the initial matrix is pressed respectively according to preset algorithm
It is normalized according to preset value, obtains the corresponding audience matrix of the financial product;It is corresponding with respectively accordingly per column element
Preset value.
Optionally, acquisition module 201 is additionally operable to obtain:It had bought or the user of the browsed bank finance product
User characteristics.
Audient's model excavating gear of bank finance product provided by the present application obtains related to bank finance product first
User characteristics obtain bank's gold according to the value of each user characteristics to each element assignment of the initial matrix
Melt the corresponding initial matrix of product, and initial matrix is normalized according to preset algorithm, obtains the financial product
Corresponding audience matrix.According to each element of audience matrix, determination can indicate user characteristics and the bank finance product
The corresponding weight of each user characteristics of correlation degree.Obtain in each financial product the corresponding weight of each user characteristics it
Afterwards, weight can provide reference for the sale of bank finance product, for example, the maximum user characteristics of weight indicate the user characteristics with
The correlation degree of bank finance product v is maximum, and banking personnel, can be preferential when promoting bank finance product to bank client
It is promoted to it according to the maximum user characteristics of the weight of client.Banking personnel are reduced according to personal business experience to be judged not
With the cost of the audience of financial product, the marketing efficiency of financial product is improved.
Fig. 4 shows in above-described embodiment that another of audient's model excavating gear of involved bank finance product can
The structural schematic diagram of energy.The device includes:Processing unit 302 and communication unit 303.Processing unit 302 is used for the device
Action carries out control management, for example, the step of above-mentioned acquisition module 201, processing module 202, determining module 203 execute is executed,
And/or other processes for executing techniques described herein.Communication unit 303 is for supporting that the device is real with other networks
The communication of body, for example, executing the step of above-mentioned acquisition module 201 executes.The device can also include storage unit 301, storage
Unit 301 is used to store the program code and data of the device.
Wherein, as shown in figure 5, above-mentioned processing unit 302 can be bank finance product audient's model excavating gear in
Processor 401 or controller, the processor 401 or controller be may be implemented or executed in conjunction with described by present disclosure
Various illustrative logic blocks, module and circuit.The processor 401 or controller can be central processing unit, general place
Manage device, digital signal processor, application-specific integrated circuit, field programmable gate array or other programmable logic device, crystal
Pipe logical device, hardware component or its arbitrary combination.It is may be implemented or executed in conjunction with described in present disclosure
Various illustrative logic blocks, module and circuit.The processor 401 can also be the combination of realization computing function, such as
Including one or more microprocessors combine, the combination etc. of DSP and microprocessor.
Communication unit 303 can be transceiver in audient's model excavating gear of bank finance product, transmission circuit or
Communication interface 402 etc..
Storage unit 301 can be the memory 403 etc. in audient's model excavating gear of bank finance product, the storage
Device 403 may include volatile memory, such as random access memory;The memory can also include non-volatile memories
Device, such as read-only memory, flash memory, hard disk or solid state disk;The memory can also include the storage of mentioned kind
The combination of device.
Bus 404 can be expanding the industrial standard structure (Extended Industry Standard
Architecture, EISA) bus etc..Bus 404 can be divided into address bus, data/address bus, controlling bus etc..For ease of table
Show, only indicated with a thick line in Fig. 5, it is not intended that an only bus or a type of bus.
Through the above description of the embodiments, it is apparent to those skilled in the art that, for description
It is convenienct and succinct, only the example of the division of the above functional modules, in practical application, can as needed and will be upper
It states function distribution to be completed by different function modules, i.e., the internal structure of device is divided into different function modules, to complete
All or part of function described above.The specific work process of the system, apparatus, and unit of foregoing description, before can referring to
The corresponding process in embodiment of the method is stated, details are not described herein.
The embodiment of the present application also provides a kind of computer readable storage medium, and finger is stored in computer readable storage medium
It enables, when computer executes the instruction, which executes method flow Computer shown in above method embodiment and execute
Each step.
Wherein, computer readable storage medium, such as electricity, magnetic, optical, electromagnetic, infrared ray can be but not limited to or partly led
System, device or the device of body, or the arbitrary above combination.The more specific example of computer readable storage medium is (non-poor
The list of act) include:Electrical connection, portable computer diskette with one or more conducting wires, hard disk, random access memory
(Random Access Memory, RAM), read-only memory (Read-Only Memory, ROM), erasable type may be programmed read-only
It is memory (Erasable Programmable Read Only Memory, EPROM), register, hard disk, optical fiber, portable
Compact disc read-only memory (Compact Disc Read-Only Memory, CD-ROM), light storage device, magnetic memory
Part or the computer readable storage medium of above-mentioned any appropriate combination or any other form well known in the art.
A kind of illustrative storage medium is coupled to processor, to enable a processor to from the read information, and can be to
Information is written in the storage medium.Certainly, storage medium can also be the component part of processor.Pocessor and storage media can be with
In application-specific IC (Application Specific Integrated Circuit, ASIC).In the application
In embodiment, computer readable storage medium, which can be any, includes or the tangible medium of storage program, which can be referred to
Enable the either device use or in connection of execution system, device.
The above, the only specific implementation mode of the application, but the protection domain of the application is not limited thereto, it is any
Change or replacement in the technical scope that the application discloses, should all cover within the protection domain of the application.Therefore, this Shen
Protection domain please should be subject to the protection scope in claims.
Claims (10)
1. a kind of audient's model method for digging of bank finance product, which is characterized in that including:
It obtains and the relevant user characteristics of bank finance product;The user characteristics include following at least two:Age, gender,
History loan documentation, wage, kinsfolk's information;
According to the corresponding audience matrix of relevant with the bank finance product user characteristics structure bank finance product, it is described by
The user characteristics of the element representation user of many matrixes;User characteristics represented by same row element belong to same user;Same row
The same user characteristics of element representation;
Determine that the corresponding weight of each user characteristics, the weight indicate user characteristics according to each element of the audience matrix
With the correlation degree of the bank finance product.
2. according to the method described in claim 1, it is characterized in that, described in the basis with the relevant user of bank finance product
The corresponding audience matrix of feature construction bank finance product, including:
According to the initial matrix corresponding with the relevant user characteristics structure bank finance product of bank finance product;
The initial matrix is normalized according to preset algorithm, obtains the corresponding audient's square of the financial product
Battle array.
3. according to the method described in claim 2, it is characterized in that, described in the basis with the relevant user of bank finance product
The corresponding initial matrix of feature construction bank finance product, including:
Obtain the user characteristics with the relevant multiple users of bank finance product;
According to the value of each user characteristics to each element assignment of the initial matrix, the bank finance product pair is obtained
The initial matrix answered.
4. according to the method described in claim 2, it is characterized in that, described return the initial matrix according to preset algorithm
One change is handled, and obtains the corresponding audience matrix of the financial product, including:
Every column element of the initial matrix is normalized respectively according to preset value according to preset algorithm, is obtained described
The corresponding audience matrix of financial product;It is corresponding with corresponding preset value respectively per column element.
5. according to claim 1-4 any one of them methods, which is characterized in that the described and relevant user of bank finance product
Feature further includes:
It had bought or the user characteristics of the user of the browsed bank finance product.
6. a kind of audient's model excavating gear of bank finance product, which is characterized in that including:
Acquisition module, for obtaining and the relevant user characteristics of bank finance product;The user characteristics include following at least two
:Age, gender, history loan documentation, wage, kinsfolk's information;
Processing module, for according to it is described build with the relevant user characteristics of bank finance product bank finance product it is corresponding by
Many matrixes, the user characteristics of the element representation user of the audience matrix;User characteristics represented by same row element belong to same
One user;The same user characteristics of same row element representation;
Determining module, for determining the corresponding weight of each user characteristics, the power according to each element of the audience matrix
The correlation degree of user characteristics and the bank finance product is indicated again.
7. device according to claim 6, which is characterized in that the processing module is additionally operable to:
According to the initial matrix corresponding with the relevant user characteristics structure bank finance product of bank finance product;
The initial matrix is normalized according to preset algorithm, obtains the corresponding audient's square of the financial product
Battle array.
8. device according to claim 7, which is characterized in that the processing module is additionally operable to:
Obtain the user characteristics with the relevant multiple users of bank finance product;
According to the value of each user characteristics to each element assignment of the initial matrix, the bank finance product pair is obtained
The initial matrix answered.
9. device according to claim 7, which is characterized in that the processing module is additionally operable to:
Every column element of the initial matrix is normalized respectively according to preset value according to preset algorithm, is obtained described
The corresponding audience matrix of financial product;It is corresponding with corresponding preset value respectively per column element.
10. according to claim 6-9 any one of them devices, which is characterized in that the acquisition module is additionally operable to obtain:
It had bought or the user characteristics of the user of the browsed bank finance product.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810457730.2A CN108648016A (en) | 2018-05-14 | 2018-05-14 | The audient's model method for digging and device of bank finance product |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810457730.2A CN108648016A (en) | 2018-05-14 | 2018-05-14 | The audient's model method for digging and device of bank finance product |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108648016A true CN108648016A (en) | 2018-10-12 |
Family
ID=63755237
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810457730.2A Pending CN108648016A (en) | 2018-05-14 | 2018-05-14 | The audient's model method for digging and device of bank finance product |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108648016A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111353881A (en) * | 2020-03-31 | 2020-06-30 | 中国建设银行股份有限公司 | Bank equity data generation method and device |
-
2018
- 2018-05-14 CN CN201810457730.2A patent/CN108648016A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111353881A (en) * | 2020-03-31 | 2020-06-30 | 中国建设银行股份有限公司 | Bank equity data generation method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP5484968B2 (en) | Information processing apparatus, information processing method, and program | |
Thomas | Consumer finance: Challenges for operational research | |
US20190311395A1 (en) | Estimating click-through rate | |
Sohn et al. | Behavioral credit scoring model for technology-based firms that considers uncertain financial ratios obtained from relationship banking | |
KR102509348B1 (en) | Method and device for providing stock recommendation service | |
US20210287295A1 (en) | Method and apparatus for recommending financial product, electronic device, and computer storage medium | |
CN113159972B (en) | Combination determination method, device, electronic equipment and computer readable storage medium | |
CN108694626A (en) | Customer profile method for building up and device | |
CN112348659A (en) | User risk identification strategy allocation method and device and electronic equipment | |
CN109801077A (en) | A kind of arbitrage user detection method, device and equipment | |
CN115630221A (en) | Terminal application interface display data processing method and device and computer equipment | |
KR20120032606A (en) | Stock investment system enabling participattion of stock investment clients and method thereof | |
CN110033165A (en) | The recommended method of overdue loaning bill collection mode, device, medium, electronic equipment | |
Hand et al. | Evaluating models for classifying customers in retail banking collections | |
CN106354822A (en) | Method and device for acquiring target user | |
CN108648016A (en) | The audient's model method for digging and device of bank finance product | |
CN112836742A (en) | System resource adjusting method, device and equipment | |
Christiansen et al. | Stress scenario generation for solvency and risk management | |
CN114612220A (en) | Wind control strategy adjusting method and device, electronic equipment and storage medium | |
CN114298829A (en) | Data processing method and device for credit assessment | |
CN110826771A (en) | Risk analysis method and device for logistics outsourcing and storage medium | |
CN113987353B (en) | Book recommendation method, computing device and storage medium | |
CN109543880A (en) | E-commerce development level optimization method and apparatus based on prospect theory | |
TWI811745B (en) | Server and method for predicting category tag of browsed website address | |
CN112862602B (en) | User request determining method, storage medium and electronic device |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181012 |