CN107301577A - Training method, credit estimation method and the device of credit evaluation model - Google Patents
Training method, credit estimation method and the device of credit evaluation model Download PDFInfo
- Publication number
- CN107301577A CN107301577A CN201610236701.4A CN201610236701A CN107301577A CN 107301577 A CN107301577 A CN 107301577A CN 201610236701 A CN201610236701 A CN 201610236701A CN 107301577 A CN107301577 A CN 107301577A
- Authority
- CN
- China
- Prior art keywords
- training
- feature
- tree
- primitive character
- models
- 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 OR CALCULATING; 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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0609—Qualifying participants for shopping transactions
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
This application discloses a kind of training method of credit evaluation model, credit estimation method and device, the wherein training method includes：Obtain training primitive behavior data of the training user in operation system；Extract the training primitive character in training primitive behavior data；Combinations of features is carried out according to iteration decision tree GBDT models to training primitive character to generate corresponding training combined crosswise feature；Logistic regression Logistic Regression models are trained to build credit evaluation model according to training combined crosswise feature.This method is trained to generate corresponding training combined crosswise feature by non-linear GBDT models to training primitive character, and by training combined crosswise feature to be trained to build credit evaluation model linear LR models, so that the credit evaluation model had both possessed the high-performance of nonlinear model, but also with the interpretation of linear model.
Description
Technical field
The application is related to data assessment field, more particularly to a kind of training method of credit evaluation model, uses the credit evaluation
Model carries out the method and device of credit evaluation.
Background technology
At present, the Credit Model of user is built in conventional traditional credit investigation system using scorecard mostly, scorecard is actually
It is a kind of two disaggregated model, builds the model and mainly realized using logistic regression Logistic Regression algorithms.Comment
Snap gauge type is divided to need to pre-process variable, the need for making scoring, variable first can be segmented by scorecard model,
Then variable is encoded based on target again, the coded system commonly used in Credit Model is WOE (Weight Of
Evidence), it intuitively can be understood as becoming influence when measuring some value to target, can improve linear by this method
The performance of model.
But, the problem of presently, there are is：In traditional credit investigation system, using purely linear model although ensure that model can
It is explanatory, but performance comparatively can be weaker, also, the method for traditional linear model combinations of features is less efficient, leads
Cause the user credit model performance built relatively low, so as to cause to forbid the credit evaluation result of user by this model
Really.
The content of the invention
The purpose of the application is intended at least solve one of technical problem in correlation technique to a certain extent.
Therefore, first purpose of the application is to propose a kind of training method of credit evaluation model.This method passes through non-thread
Property GBDT models training primitive character is trained to generate corresponding training combined crosswise feature, and by training intersection group
Close feature to be trained to build credit evaluation model linear LR models so that the credit evaluation model both possesses nonlinear model
The high-performance of type, but also with the interpretation of linear model.
Second purpose of the application is to propose a kind of method of credit evaluation.
The 3rd purpose of the application is to propose a kind of trainer of credit evaluation model.
The 4th purpose of the application is to propose a kind of device of credit evaluation.
For up to above-mentioned purpose, the training method of the credit evaluation model of the application first aspect embodiment, including：Obtain training
Training primitive behavior data of the user in operation system；Extract the training primitive character in the training primitive behavior data；
Carry out combinations of features to the training primitive character to generate corresponding training combined crosswise according to iteration decision tree GBDT models
Feature；Logistic regression Logistic Regression models are trained according to the training combined crosswise feature to build
Credit evaluation model.
The training method of the credit evaluation model of the embodiment of the present application, is carried out by non-linear GBDT models to training primitive character
Training with generate it is corresponding training combined crosswise feature, and by train combined crosswise feature to be trained linear LR models with
Build credit evaluation model so that the credit evaluation model had both possessed the high-performance of nonlinear model, but also with linear model
Interpretation.
For up to above-mentioned purpose, the credit evaluation described in use the application first aspect embodiment of the application second aspect embodiment
The method that model carries out credit evaluation, including：Obtain primitive behavior data of the targeted customer in operation system；Extract described
Primitive character in primitive behavior data；Carry out combinations of features to the primitive character to generate corresponding friendship according to GBDT models
Pitch assemblage characteristic；The combined crosswise feature is predicted according to the credit evaluation model to obtain the targeted customer's
Credit information.
The method of the credit evaluation of the embodiment of the present application, when carrying out credit evaluation prediction to targeted customer, can first obtain the mesh
Primitive behavior data of the user in operation system are marked, and extract the primitive character in primitive behavior data, afterwards, will be original
Feature is trained by GBDT tree-model to obtain corresponding combined crosswise feature, finally, and the combined crosswise feature is put
It is predicted into credit evaluation model, draws the user profile of the targeted customer, i.e., by using both possesses higher solve
The property released carries out credit evaluation but also with high performance credit evaluation model to targeted customer so that assessment result is relatively reliable, effect
Fruit more preferably, improves the accuracy of assessment result.
For up to above-mentioned purpose, the trainer of the credit evaluation model of the application third aspect embodiment, including：Acquisition module,
For obtaining training primitive behavior data of the training user in operation system；Extraction module, it is original for extracting the training
Training primitive character in behavioral data；Generation module, for training original spy to described according to iteration decision tree GBDT models
Progress combinations of features is levied to generate corresponding training combined crosswise feature；Training module, for according to the training combined crosswise
Feature is trained to build credit evaluation model to logistic regression Logistic Regression models.
The trainer of the credit evaluation model of the embodiment of the present application, is entered by non-linear GBDT models to training primitive character
Row is trained to build corresponding training combined crosswise feature, and by training combined crosswise feature to be trained linear LR models
To build credit evaluation model so that the credit evaluation model had both possessed the high-performance of nonlinear model, but also with linear model
Interpretation.
For up to above-mentioned purpose, the credit evaluation described in use the application third aspect embodiment of the application fourth aspect embodiment
Model carries out the device of credit evaluation, including：Acquisition module, for obtaining primitive behavior of the targeted customer in operation system
Data；Extraction module, for extracting the primitive character in the primitive behavior data；Generation module, for according to GBDT moulds
Type carries out combinations of features to generate corresponding combined crosswise feature to the primitive character；Prediction module, for according to the letter
The combined crosswise feature is predicted with assessment models to obtain the credit information of the targeted customer.
The device of the credit evaluation of the embodiment of the present application, can be by obtaining mould when carrying out credit evaluation prediction to targeted customer
Block obtains primitive behavior data of the targeted customer in operation system, and extraction module extracts the original spy in primitive behavior data
Levy, primitive character is trained to obtain corresponding combined crosswise feature by generation module by GBDT tree-model, predicts mould
The combined crosswise feature is put into credit evaluation model and is predicted by block, draws the user profile of the targeted customer, that is, passes through
Using both possess higher interpretation but also with high performance credit evaluation model to targeted customer carry out credit evaluation so that
Assessment result is relatively reliable, better, improves the accuracy of assessment result.
The aspect and advantage that the application is added will be set forth in part in the description, and partly will become bright from the following description
It is aobvious, or recognized by the practice of the application.
Brief description of the drawings
The above-mentioned and/or additional aspect and advantage of the application will be apparent from description of the accompanying drawings below to embodiment is combined
Be readily appreciated that, wherein：
Fig. 1 is the flow chart of the training method of the credit evaluation model according to the application one embodiment；
Fig. 2 is the flow chart of the implementation process of the generation training combined crosswise feature according to the embodiment of the present application；
Fig. 3 is the schematic diagram that training combined crosswise feature is generated according to the utilization GBDT models of the embodiment of the present application；
Fig. 4 is the structured flowchart of the trainer of the credit evaluation model according to the application one embodiment；
Fig. 5 is the structured flowchart of the trainer of the credit evaluation model according to the application another embodiment；
Fig. 6 is the flow chart of the method for the credit evaluation according to the application one embodiment；
Fig. 7 is the structured flowchart of the device of the credit evaluation according to the application one embodiment；
Fig. 8 is the structured flowchart of the device of the credit evaluation according to the application another embodiment.
Embodiment
Embodiments herein is described below in detail, the example of the embodiment is shown in the drawings, wherein identical from beginning to end
Or similar label represents same or similar element or the element with same or like function.Retouched below with reference to accompanying drawing
The embodiment stated is exemplary, it is intended to for explaining the application, and it is not intended that limitation to the application.
, it is necessary to build the credit of the user by the big data of long term accumulation user in the application scenarios of credit product
Model, wherein, the sample of use is performance data of the user in credit product, as with purchase function by stages
Behavioral data in product and product with refund function after first use, the variable of use is the phase of each dimension of user
Close variable, it is overdue that the target of models fitting is whether user occurs in the preset time period after drawing, and passes through fitting
The data build Credit Model.
Because credit product is the product that region be directly facing user, the interpretation to model requires higher, in practical application
Model is often built using linear algorithm such as Logistic Regression (abbreviation LR), but linear model is complicated
Degree is relatively low compared to nonlinear model, and the performance of model can be less than nonlinear model, and the complexity of nonlinear model is higher,
Model performance is preferable, but explanatory generally poor.
Therefore, present applicant proposes a kind of training method of credit evaluation model, by using nonlinear tree-model structure group
Feature is closed, linear Algorithm for Training final mask is reused, finally show that a performance is higher than purely linear model, while have again
The model of standby interpretation.Specifically, below with reference to the accompanying drawings the training side of the credit evaluation model of the embodiment of the present application is described
Method, method and device using credit evaluation model progress credit evaluation.
Fig. 1 is the flow chart of the training method of the credit evaluation model according to the application one embodiment.As shown in figure 1, should
The training method of credit evaluation model can include：
S110, obtains training primitive behavior data of the training user in operation system.
Specifically, the user profile of a large amount of training users can be first obtained, afterwards, can be according to the user profile for largely training users
Obtain training primitive behavior data of the training user in operation system.It should be noted that in embodiments herein,
The operation system can be the system with credit product, and can also be has the system of purchase function or with energy
Enough embody the system of user credit function.
Wherein, in embodiments herein, the training primitive behavior data may include but be not limited to website or webpage click row
For (such as click on the time, number of times, frequency), training customer transaction data and behavior (as pay product information, payment,
Means of payment etc.), fund incremental data and behavior (flow direction of such as fund, the funds flow amount of money) etc..
In addition, user profile may include but be not limited to user name or ID, account name etc..That is, for example working as business
When system carrys out the uniqueness of recognition training user by using user name, can now obtain training user user name, and according to
The user name obtains all training primitive behavior data of the training user in the operation system；When operation system is by using account
When name in an account book carrys out the uniqueness of recognition training user, the account name of training user can be now obtained, and instruction is obtained according to account name
Practice training primitive behavior data of the user in current business system.
S120, extracts the training primitive character in training primitive behavior data.
Specifically, it can will be extracted from training primitive behavior data with the data that feature is showed, and this is had into feature
The data of performance as the training primitive behavior data training primitive character.For example, the training primitive character may include purchase
The amount of money, web page/site number of clicks, web page/site click frequency, funds flow etc..
S130, carries out combinations of features to training primitive character according to iteration decision tree GBDT models and is handed over generating corresponding training
Pitch assemblage characteristic.
Specifically, in embodiments herein, GBDT models can be trained according to training primitive character to build
GBDT models with N tree, wherein, N is positive integer, and the N tree in GBDT models is excavated and train original
Incidence relation between feature, finally, carries out combinations of features to training primitive character according to incidence relation and is intersected with generating training
Assemblage characteristic.
It is appreciated that GBDT is a kind of decision Tree algorithms of iteration, the algorithm is made up of many decision trees, the conclusion of all trees
Add up and do final result, for example, each tree can be gone to the residual error of K tree before being fitted, it is possible to understand that into every one tree
The result of one tree before being dependent on, therefore, between tree needs to ensure certain order.So, by many in GBDT models
Decision tree carries out Decision Classfication to training primitive character, so as to find out the incidence relation between training primitive character, and
Feature with incidence relation is combined, obtains training combined crosswise feature.
In one embodiment of the application, as shown in Fig. 2 the N tree in GBDT models excavates the original spy of training
Incidence relation between levying, and carry out combinations of features to training primitive character to generate training combined crosswise spy according to incidence relation
The process that implements levied may include following steps：
S131, will train the corresponding sample data of primitive character to pass sequentially through N tree in GBDT models, until each sample
Data divide equally the leaf node for being assigned to each tree.
S132, for each tree in GBDT models, by from the root node of each tree to leaf node paths traversed
Corresponding training primitive character is combined, to generate training combined crosswise feature.
Specifically, as shown in figure 3, node of each tree in addition to leaf node in GBDT models all corresponds to a division spy
Disruptive features of seeking peace value, if the value of the disruptive features of sample is more than the disruptive features value of node, will be trained in primitive character
Sample be assigned to the right child node of the node, otherwise assign to left child node, lower level node similarly, until the sample falls on certain
Leaf node.For example, by taking one tree as shown in Figure 3 as an example, it is assumed that sample is assigned to No. 2 leaf nodes, then is formed
Assemblage characteristic is [G<=g_v＆＆I>I_v]=1, equivalent to punishing into two sections from g_v this value to this feature of G, I this
From i_v, this value punishes into two sections to feature, and two Feature Segmentations of G and I are multiplied, and draw 4 features, wherein G first paragraphs
The characteristic value being multiplied with I second segments is 1, and remaining characteristic value is 0.It is appreciated that in as shown in Figure 3, depth is 3
The multiplication cross of as two features drawn is set, similarly, what the tree that depth is 4 drew is the multiplication cross of three features.
It is further appreciated that each node of tree corresponds to a disruptive features, the node one split values of correspondence divide this feature
Into two parts, for example, it is assumed that this feature assigns to the left side of the node less than or equal to the sample of split values, more than split values
Sample assign to the right side of the node, then the node can be translated into a pair of 0,1 binary features, e.g., work as G<=G_split is (i.e.
Node G split values) when, F_G_L=1, F_G_R=0 work as G>During G_split, F_G_L=0, F_G_R=1, it is corresponding under
Feature F_I_L and F_I_R as a pair, and F_H_L and F_H_R can be also formed after node layer division, if
G<=G_split, then sample fall into left then node I, upper layer node is multiplied with the feature of lower level node, obtains two pairs of new features,
F_G_L*F_I_L, F_G_L*F_I_R, if sample eventually falls into F_I_R, F_G_L*F_I_R=1, remaining assemblage characteristic is equal
For 0.So, it is combined by finding feature to be multiplied the feature for being 1, so as to obtain the combination with incidence relation
Feature.It is appreciated that above-mentioned implementation is intended only as a kind of example, with for the one kind run and provided suitable for computer
Representation, is restriction as the application without being understood that.
Thus, the association between feature is excavated by using GBDT tree-models, to build training combined crosswise feature, is carried
The high performance in combinations of features stage, improves combinations of features efficiency.
S140, is trained to build according to training combined crosswise feature to logistic regression Logistic Regression models
Credit evaluation model.
Specifically, after generation training combined crosswise feature, training combined crosswise feature can be used linear model
Logistic Regression (referred to as LR) model is trained to obtain credit evaluation model.
In order to improve the performance of credit evaluation model, and the accuracy of assessment result when using the model is improved, further,
, can be according to training primitive character and training combined crosswise feature to Logistic in one embodiment of the application
Regression models are trained to build credit evaluation model.Specifically, after training combined crosswise feature is obtained,
Training combined crosswise feature can be put into LR models together with training primitive character and be trained, finally give credit evaluation mould
Type, the model is explainable linear model.It is appreciated that the model is on the premise of interpretation is ensured, effect is more
Better than GBDT and LR models.
The training method of the credit evaluation model of the embodiment of the present application, is carried out by non-linear GBDT models to training primitive character
Training with build it is corresponding training combined crosswise feature, and by train combined crosswise feature to be trained linear LR models with
Build credit evaluation model so that the credit evaluation model had both possessed the high-performance of nonlinear model, but also with linear model
Interpretation.
Training method with the credit evaluation model that above-mentioned several embodiments are provided is corresponding, and a kind of embodiment of the application is also carried
For a kind of trainer of credit evaluation model, the trainer of the credit evaluation model provided due to the embodiment of the present application with it is upper
The training method for stating the credit evaluation model that several embodiments are provided is corresponding, therefore in the training side of foregoing credit evaluation model
The embodiment of method is also applied for the trainer of the credit evaluation model of the present embodiment offer, no longer detailed in the present embodiment
Description.Fig. 4 is the structured flowchart of the trainer of the credit evaluation model according to the application one embodiment.As shown in figure 4,
The trainer of the credit evaluation model can include：Acquisition module 110, extraction module 120, generation module 130 and training
Module 140.
Wherein, acquisition module 110 can be used for obtaining training primitive behavior data of the training user in operation system.
Extraction module 120 can be used for extracting the training primitive character in training primitive behavior data.
Generation module 130 can be used for carrying out combinations of features to training primitive character to generate according to iteration decision tree GBDT models
Corresponding training combined crosswise feature.
Specifically, in one embodiment of the application, as shown in figure 5, on the basis of as shown in Figure 4, the generation
Module 130 may include：Training unit 131 and generation unit 132.
Wherein, training unit 131 can be used for being trained iteration decision tree GBDT models according to training primitive character building
GBDT models with N tree, wherein, N is positive integer.
The N tree that generation unit 132 can be used in GBDT models excavates the incidence relation between training primitive character, and
Carry out combinations of features to training primitive character to generate training combined crosswise feature according to incidence relation.
Specifically, in embodiments herein, generation unit 132 will can train the corresponding sample data of primitive character according to
N tree in the secondary model by GBDT, until each sample data divides equally the leaf node for being assigned to each tree, and for GBDT
Each tree in model, by the training primitive character corresponding from the root node of each tree to leaf node paths traversed
It is combined, to generate training combined crosswise feature.
Training module 140 can be used for entering logistic regression Logistic Regression models according to training combined crosswise feature
Row trains to build credit evaluation model.
In order to improve the performance of credit evaluation model, and the accuracy of assessment result when using the model is improved, further,
In one embodiment of the application, training module 140 can be additionally used according to training primitive character and training combined crosswise feature
Logistic Regression models are trained to build credit evaluation model.
The trainer of the credit evaluation model of the embodiment of the present application, is carried out by non-linear GBDT models to training primitive character
Training with build it is corresponding training combined crosswise feature, and by train combined crosswise feature to be trained linear LR models with
Build credit evaluation model so that the credit evaluation model had both possessed the high-performance of nonlinear model, but also with linear model
Interpretation.
The application also proposed a kind of method of credit evaluation, and the credit described in any of the above-described embodiment can be used to comment for this method
Estimate model and credit evaluation is carried out to user.
Fig. 6 is the flow chart of the method for the credit evaluation according to the application one embodiment.As shown in fig. 6, the credit evaluation
Method can include：
S610, obtains primitive behavior data of the targeted customer in operation system.
Specifically, the user profile of targeted customer can be first obtained, afterwards, the targeted customer can be obtained according to user profile in industry
Primitive behavior data in business system.It should be noted that in embodiments herein, the operation system can be had
The system of credit product, can also be system with purchase function or with can embody user credit function
System.
Wherein, in embodiments herein, the primitive behavior data may include but be not limited to website or webpage click behavior (such as
Click time, number of times, frequency etc.), the transaction data of targeted customer and behavior be (as paid product information, payment, branch
Pay mode etc.), fund incremental data and behavior (flow direction of such as fund, the funds flow amount of money) etc..
In addition, user profile may include but be not limited to user name or ID, account name etc..That is, for example working as business
When system recognizes the uniqueness of targeted customer by using user name, the user name of targeted customer can be now obtained, and according to
The user name obtains all primitive behavior data of the targeted customer in the operation system；When operation system is by using account name
During uniqueness to recognize targeted customer, the account name of targeted customer can be now obtained, and target is obtained according to account name and is used
Primitive behavior data of the family in current business system.
S620, extracts the primitive character in primitive behavior data.
Specifically, it can will be extracted from primitive behavior data with the data that feature is showed, and this is had into feature performance
Data as the primitive behavior data primitive character.For example, the primitive character may include the purchase amount of money, web page/site point
Hit number of times, web page/site click frequency, funds flow etc..
S630, carries out combinations of features to generate corresponding combined crosswise feature according to GBDT models to primitive character.
Specifically, in embodiments herein, first GBDT models can be trained according to primitive character has to build
The GBDT models of N tree, wherein, N is positive integer, afterwards, can excavate primitive character according to the tree of N in GBDT models
Between incidence relation, and combinations of features is carried out to primitive character to generate combined crosswise feature according to incidence relation.
It is appreciated that GBDT is a kind of decision Tree algorithms of iteration, the algorithm is made up of many decision trees, the conclusion of all trees
Add up and do final result, for example, each tree can be gone to the residual error of K tree before being fitted, it is possible to understand that into every one tree
The result of one tree before being dependent on, therefore, between tree needs to ensure certain order.So, by many in GBDT models
Decision tree carries out Decision Classfication to primitive character, is closed so as to find out the incidence relation between primitive character, and will have
The feature of connection relation is combined, and obtains combined crosswise feature.
In one embodiment of the application, the process that implements of generation combined crosswise feature may include：By primitive character pair
The sample data answered passes sequentially through N tree in GBDT models, until each sample data divides equally the leaf section for being assigned to each tree
Point, and for each tree in GBDT models, will be corresponding from the root node of each tree to leaf node paths traversed
Primitive character be combined, to generate combined crosswise feature.It is appreciated that the method for the credit evaluation of the embodiment of the present application
The side of the mode of middle generation combined crosswise feature and generation training combined crosswise feature in the training method of above-mentioned credit evaluation model
The realization principle of formula is identical, and the realization that can refer to the above-mentioned generating mode to training combined crosswise feature is described, and is no longer gone to live in the household of one's in-laws on getting married herein
State.
S640, is predicted to obtain the credit information of targeted customer according to credit evaluation model to combined crosswise feature.
Specifically, after generation combined crosswise feature, combined crosswise feature can be trained using LR models to obtain
Credit evaluation model.
, further, can be according to credit evaluation in one embodiment of the application in order to improve the accuracy of assessment result
Model is predicted to obtain the credit information of targeted customer to primitive character and combined crosswise feature.Specifically, handed over
Pitch after assemblage characteristic, combined crosswise feature can be put into credit evaluation model together with primitive character and carry out credit prediction, obtained
Go out it is final predict the outcome, i.e. the credit information of the targeted customer.
It should be noted that the method for the credit evaluation of the embodiment of the present application is based on using C language and across the communication association of language
MPI parallel computation frames are discussed come what is realized, better performance can be so reached.
The method of the credit evaluation of the embodiment of the present application, when carrying out credit evaluation prediction to targeted customer, can first obtain the mesh
Primitive behavior data of the user in operation system are marked, and extract the primitive character in primitive behavior data, afterwards, will be original
Feature is trained by GBDT tree-model to obtain corresponding combined crosswise feature, finally, and the combined crosswise feature is put
It is predicted into credit evaluation model, draws the user profile of the targeted customer, i.e., by using both possesses higher solve
The property released carries out credit evaluation but also with high performance credit evaluation model to targeted customer so that assessment result is relatively reliable, effect
Fruit more preferably, improves the accuracy of assessment result.
Method with the credit evaluation that above-mentioned several embodiments are provided is corresponding, and a kind of embodiment of the application also provides a kind of letter
With the device of assessment, because the credit that the device and above-mentioned several embodiments of the credit evaluation of the embodiment of the present application offer are provided is commented
The method estimated is corresponding, thus the method in foregoing credit evaluation embodiment be also applied for the present embodiment offer credit comment
The device estimated, is not described in detail in the present embodiment.Fig. 7 is the device of the credit evaluation according to the application one embodiment
Structured flowchart.It should be noted that the device of the credit evaluation of the embodiment of the present application is by using any of the above-described embodiment
Described credit evaluation model carries out credit evaluation to targeted customer.
As shown in fig. 7, the device of the credit evaluation can include：Acquisition module 210, extraction module 220, generation module 230
With prediction module 240.
Wherein, acquisition module 210 can be used for obtaining primitive behavior data of the targeted customer in operation system.
Extraction module 220 can be used for extracting the primitive character in primitive behavior data.
Generation module 230 can be used for carrying out combinations of features to primitive character to generate corresponding combined crosswise according to GBDT models
Feature.
Specifically, in one embodiment of the application, as shown in figure 8, on the basis of as shown in Figure 7, the generation
Module 230 may include：Training unit 231 and generation unit 232.
Wherein, training unit 231 can be used for being trained GBDT models according to primitive character what is set with N to build
GBDT models, wherein, N is positive integer.
The incidence relation that generation unit 232 can be used between the N tree excavation primitive character in GBDT models, and according to
Incidence relation carries out combinations of features to generate combined crosswise feature to primitive character.
Specifically, in embodiments herein, generation unit 232 can lead to the corresponding sample data of primitive character successively
The N tree crossed in GBDT models, until each sample data divides equally the leaf node for being assigned to each tree, and for GBDT moulds
Each tree in type, by the primitive character carry out group corresponding from the root node of each tree to leaf node paths traversed
Close, to generate combined crosswise feature.
Prediction module 240 can be used for combined crosswise feature is predicted according to credit evaluation model to obtain the letter of targeted customer
Use information.
In order to improve the accuracy of assessment result, further, in one embodiment of the application, prediction module 240 is also
Believed available for being predicted according to credit evaluation model to primitive character and combined crosswise feature with the credit for obtaining targeted customer
Breath.
The device of the credit evaluation of the embodiment of the present application, can be by obtaining mould when carrying out credit evaluation prediction to targeted customer
Block obtains primitive behavior data of the targeted customer in operation system, and extraction module extracts the original spy in primitive behavior data
Levy, primitive character is trained to obtain corresponding combined crosswise feature by generation module by GBDT tree-model, predicts mould
The combined crosswise feature is put into credit evaluation model and is predicted by block, draws the user profile of the targeted customer, that is, passes through
Using both possess higher interpretation but also with high performance credit evaluation model to targeted customer carry out credit evaluation so that
Assessment result is relatively reliable, better, improves the accuracy of assessment result.
In the description of the present application, in the description of the present application, " multiple " are meant that at least two, such as two, three
Deng unless otherwise specifically defined.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specific example ",
Or the description of " some examples " etc. means to combine specific features, structure, material or the feature that the embodiment or example are described
It is contained at least one embodiment of the application or example.In this manual, need not to the schematic representation of above-mentioned term
Identical embodiment or example must be directed to.Moreover, specific features, structure, material or the feature of description can be with office
Combined in an appropriate manner in one or more embodiments or example.In addition, in the case of not conflicting, this area
Technical staff can be tied the not be the same as Example or the feature of example and non-be the same as Example or example described in this specification
Close and combine.
Any process described otherwise above or method description are construed as in flow chart or herein, and expression includes one
Or more be used for executable instruction the step of realize specific logical function or process code module, fragment or part,
And the scope of the preferred embodiment of the application includes other realization, wherein order that is shown or discussing can not be pressed,
Including according to involved function by it is basic simultaneously in the way of or in the opposite order, carry out perform function, this should be by the application's
Embodiment person of ordinary skill in the field is understood.
Represent in flow charts or logic and/or step described otherwise above herein, for example, being considered for real
The order list of the executable instruction of existing logic function, may be embodied in any computer-readable medium, for instruction
Execution system, device or equipment (such as computer based system including the system of processor or other can be performed from instruction
The system of system, device or equipment instruction fetch and execute instruction) use, or combine these instruction execution systems, device or set
It is standby and use.For the purpose of this specification, " computer-readable medium " can any can be included, store, communicating, propagating
Or transmission procedure uses for instruction execution system, device or equipment or with reference to these instruction execution systems, device or equipment
Device.The more specifically example (non-exhaustive list) of computer-readable medium includes following：With one or more cloth
The electrical connection section (electronic installation) of line, portable computer diskette box (magnetic device), random access memory (RAM) is read-only
Memory (ROM), erasable edit read-only storage (EPROM or flash memory), fiber device, and it is portable
Compact disc read-only memory (CDROM).In addition, computer-readable medium, which can even is that, to print the paper of described program thereon
Or other suitable media, because can then enter edlin, solution for example by carrying out optical scanner to paper or other media
Translate or handled electronically to obtain described program with other suitable methods if necessary, be then stored in computer
In memory.
It should be appreciated that each several part of the application can be realized with hardware, software, firmware or combinations thereof.In above-mentioned reality
Apply in mode, software that multiple steps or method can be performed in memory and by suitable instruction execution system with storage or
Firmware is realized.If, and in another embodiment, can be with well known in the art for example, realized with hardware
Any one of row technology or their combination are realized：With the logic gates for realizing logic function to data-signal
Discrete logic, the application specific integrated circuit with suitable combinational logic gate circuit, programmable gate array (PGA) is existing
Field programmable gate array (FPGA) etc..
Those skilled in the art be appreciated that to realize all or part of step that above-described embodiment method is carried is can
To instruct the hardware of correlation to complete by program, described program can be stored in a kind of computer-readable recording medium,
The program upon execution, including one or a combination set of the step of embodiment of the method.
In addition, each functional unit in the application each embodiment can be integrated in a processing module or each
Individual unit is individually physically present, can also two or more units be integrated in a module.Above-mentioned integrated module was both
It can be realized in the form of hardware, it would however also be possible to employ the form of software function module is realized.If the integrated module with
The form of software function module realize and as independent production marketing or in use, can also be stored in one it is computer-readable
Take in storage medium.
Storage medium mentioned above can be read-only storage, disk or CD etc..Although having been shown and described above
Embodiments herein, it is to be understood that above-described embodiment is exemplary, it is impossible to be interpreted as the limitation to the application,
One of ordinary skill in the art can be changed to above-described embodiment, change, replacing and modification within the scope of application.
Claims (16)
1. a kind of training method of credit evaluation model, it is characterised in that comprise the following steps：
Obtain training primitive behavior data of the training user in operation system；
Extract the training primitive character in the training primitive behavior data；
Combinations of features is carried out according to iteration decision tree GBDT models to the training primitive character to generate corresponding training to intersect
Assemblage characteristic；
Logistic regression Logistic Regression models are trained to build letter according to the training combined crosswise feature
Use assessment models.
2. the method as described in claim 1, it is characterised in that it is described according to iteration decision tree GBDT models to the instruction
Practice primitive character to carry out combinations of features to generate corresponding training combined crosswise feature, including：
The iteration decision tree GBDT models are trained according to the training primitive character to build the GBDT with N tree
Model, wherein, N is positive integer；
The incidence relation between the N tree excavation training primitive character in the GBDT models, and according to
The incidence relation carries out combinations of features to generate the training combined crosswise feature to the training primitive character.
3. method as claimed in claim 2, it is characterised in that the N tree in the GBDT models
The incidence relation between the training primitive character is excavated, and spy is carried out to the training primitive character according to the incidence relation
Combination is levied to generate the training combined crosswise feature, including：
The corresponding sample data of the training primitive character is passed sequentially through to the N tree in the GBDT models, until every
The individual sample data divides equally the leaf node for being assigned to each tree；
For each tree in the GBDT models, by what is passed through from the root node of each tree to leaf node
Corresponding training primitive character is combined on path, to generate the training combined crosswise feature.
4. the method as described in claim 1, it is characterised in that wherein, according to the training primitive character and the instruction
Practice combined crosswise feature the Logistic Regression models are trained to build the credit evaluation model.
5. a kind of method that credit evaluation model using as any one of Claims 1-4 carries out credit evaluation,
It is characterised in that it includes following steps：
Obtain primitive behavior data of the targeted customer in operation system；
Extract the primitive character in the primitive behavior data；
Carry out combinations of features to the primitive character to generate corresponding combined crosswise feature according to GBDT models；
The combined crosswise feature is predicted according to the credit evaluation model and believed with the credit for obtaining the targeted customer
Breath.
6. method as claimed in claim 5, it is characterised in that described to be carried out according to GBDT models to the primitive character
Combinations of features to generate corresponding combined crosswise feature, including：
The GBDT models are trained according to the primitive character to build the GBDT models with N tree, wherein, N
For positive integer；
The N tree in the GBDT models excavates the incidence relation between the primitive character, and is closed according to described
Primitive character described in connection relation pair carries out combinations of features to generate the combined crosswise feature.
7. method as claimed in claim 6, it is characterised in that the N tree in the GBDT models
Excavate the incidence relation between the primitive character, and according to the incidence relation primitive character is carried out combinations of features with
The combined crosswise feature is generated, including：
The corresponding sample data of the primitive character is passed sequentially through to the N tree in the GBDT models, until each institute
State sample data and divide equally the leaf node for being assigned to each tree；
For each tree in the GBDT models, the road that will be passed through from the root node of each tree to leaf node
Corresponding primitive character is combined on footpath, to generate the combined crosswise feature.
8. method as claimed in claim 5, it is characterised in that wherein, according to the credit evaluation model to described original
Feature and the combined crosswise feature are predicted to obtain the credit information of the targeted customer.
9. a kind of trainer of credit evaluation model, it is characterised in that including：
Acquisition module, for obtaining training primitive behavior data of the training user in operation system；
Extraction module, for extracting the training primitive character in the training primitive behavior data；
Generation module, for being generated according to iteration decision tree GBDT models to the training primitive character progress combinations of features
Corresponding training combined crosswise feature；
Training module, for being entered according to the training combined crosswise feature to logistic regression Logistic Regression models
Row trains to build credit evaluation model.
10. device as claimed in claim 9, it is characterised in that the generation module includes：
Training unit, for being trained the iteration decision tree GBDT models to build tool according to the training primitive character
There are the GBDT models of N tree, wherein, N is positive integer；
Generation unit, the association between the training primitive character is excavated for the N tree in the GBDT models
Relation, and carry out combinations of features to the training primitive character to generate the training combined crosswise spy according to the incidence relation
Levy.
11. device as claimed in claim 10, it is characterised in that the generation unit is additionally operable to：
The corresponding sample data of the training primitive character is passed sequentially through to the N tree in the GBDT models, until every
The individual sample data divides equally the leaf node for being assigned to each tree；
For each tree in the GBDT models, by what is passed through from the root node of each tree to leaf node
Corresponding training primitive character is combined on path, to generate the training combined crosswise feature.
12. device as claimed in claim 9, it is characterised in that the training module is additionally operable to original according to the training
Feature and the training combined crosswise feature are trained to build the credit to the Logistic Regression models
Assessment models.
13. a kind of credit evaluation model using as any one of claim 9 to 12 carries out the device of credit evaluation,
It is characterised in that it includes：
Acquisition module, for obtaining primitive behavior data of the targeted customer in operation system；
Extraction module, for extracting the primitive character in the primitive behavior data；
Generation module, for generating corresponding combined crosswise to primitive character progress combinations of features according to GBDT models
Feature；
Prediction module, for being predicted according to the credit evaluation model to the combined crosswise feature to obtain the target
The credit information of user.
14. device as claimed in claim 13, it is characterised in that the generation module includes：
Training unit, for being trained according to the primitive character to the GBDT models to build the GBDT with N tree
Model, wherein, N is positive integer；
Generation unit, the incidence relation between the primitive character is excavated for the N tree in the GBDT models,
And carry out combinations of features to the primitive character to generate the combined crosswise feature according to the incidence relation.
15. device as claimed in claim 14, it is characterised in that the generation unit is additionally operable to：
The corresponding sample data of the primitive character is passed sequentially through to the N tree in the GBDT models, until each institute
State sample data and divide equally the leaf node for being assigned to each tree；
For each tree in the GBDT models, the road that will be passed through from the root node of each tree to leaf node
Corresponding primitive character is combined on footpath, to generate the combined crosswise feature.
16. device as claimed in claim 13, it is characterised in that the prediction module is additionally operable to according to the credit evaluation
Model is predicted to obtain the credit information of the targeted customer to the primitive character and the combined crosswise feature.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610236701.4A CN107301577A (en) | 2016-04-15 | 2016-04-15 | Training method, credit estimation method and the device of credit evaluation model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610236701.4A CN107301577A (en) | 2016-04-15 | 2016-04-15 | Training method, credit estimation method and the device of credit evaluation model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107301577A true CN107301577A (en) | 2017-10-27 |
Family
ID=60137958
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610236701.4A Pending CN107301577A (en) | 2016-04-15 | 2016-04-15 | Training method, credit estimation method and the device of credit evaluation model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107301577A (en) |
Cited By (36)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108009914A (en) * | 2017-12-19 | 2018-05-08 | 马上消费金融股份有限公司 | Credit risk assessment method, system, equipment and computer storage medium |
| CN108022146A (en) * | 2017-11-14 | 2018-05-11 | 深圳市牛鼎丰科技有限公司 | Characteristic item processing method, device, the computer equipment of collage-credit data |
| CN108229549A (en) * | 2017-12-28 | 2018-06-29 | 杭州大搜车汽车服务有限公司 | A kind of intelligent recognition car trader fits up method, electronic equipment and the storage medium of degree |
| CN108427658A (en) * | 2018-03-12 | 2018-08-21 | 北京奇艺世纪科技有限公司 | A kind of data predication method, device and electronic equipment |
| CN108681750A (en) * | 2018-05-21 | 2018-10-19 | 阿里巴巴集团控股有限公司 | The feature of GBDT models explains method and apparatus |
| CN109035003A (en) * | 2018-07-04 | 2018-12-18 | 北京玖富普惠信息技术有限公司 | Anti- fraud model modelling approach and anti-fraud monitoring method based on machine learning |
| CN109447273A (en) * | 2018-09-30 | 2019-03-08 | 深圳市元征科技股份有限公司 | Model training method, advertisement recommended method, relevant apparatus, equipment and medium |
| CN109754157A (en) * | 2018-11-30 | 2019-05-14 | 畅捷通信息技术股份有限公司 | A kind of methods of marking and system for reflecting enterprise's health management, financing and increasing letter |
| CN109767312A (en) * | 2018-12-10 | 2019-05-17 | 江西师范大学 | A credit evaluation model training and evaluation method and device |
| WO2019128526A1 (en) * | 2017-12-27 | 2019-07-04 | 阿里巴巴集团控股有限公司 | Method, apparatus, and device for training risk control model and risk control |
| CN110008349A (en) * | 2019-02-01 | 2019-07-12 | 阿里巴巴集团控股有限公司 | The method and device for the event risk assessment that computer executes |
| CN110322334A (en) * | 2018-03-29 | 2019-10-11 | 上海麦子资产管理集团有限公司 | Credit rating method and device, computer readable storage medium, terminal |
| CN110335134A (en) * | 2019-04-15 | 2019-10-15 | 梵界信息技术(上海)股份有限公司 | A method of it is converted based on WOE and realizes the classification of credit customer qualification |
| CN110399602A (en) * | 2018-04-25 | 2019-11-01 | 北京京东尚科信息技术有限公司 | A method and device for evaluating text reliability |
| CN110443346A (en) * | 2019-08-12 | 2019-11-12 | 腾讯科技（深圳）有限公司 | A kind of model explanation method and device based on input feature vector importance |
| CN110544165A (en) * | 2019-09-02 | 2019-12-06 | 中诚信征信有限公司 | credit risk score card creating method and device and electronic equipment |
| CN110634060A (en) * | 2018-06-21 | 2019-12-31 | 马上消费金融股份有限公司 | User credit risk assessment method, system, device and storage medium |
| CN110728301A (en) * | 2019-09-09 | 2020-01-24 | 北京镭文科技有限公司 | Credit scoring method, device, terminal and storage medium for individual user |
| CN111275062A (en) * | 2018-12-04 | 2020-06-12 | 北京嘀嘀无限科技发展有限公司 | Model training method, device, server and computer readable storage medium |
| CN111340121A (en) * | 2020-02-28 | 2020-06-26 | 支付宝(杭州)信息技术有限公司 | Target feature determination method and device |
| CN111563810A (en) * | 2020-04-28 | 2020-08-21 | 北京云从科技有限公司 | Credit wind control model generation method, credit evaluation system, machine-readable medium and device |
| CN111861750A (en) * | 2020-07-22 | 2020-10-30 | 北京睿知图远科技有限公司 | Feature derivation system based on decision tree method and readable storage medium |
| CN111898675A (en) * | 2020-07-30 | 2020-11-06 | 北京云从科技有限公司 | Credit wind control model generation method and device, scoring card generation method, machine readable medium and equipment |
| CN112035453A (en) * | 2020-08-27 | 2020-12-04 | 平安科技（深圳）有限公司 | GBDT high-order feature combination-based recommendation method and device and storage medium |
| CN112084519A (en) * | 2020-09-18 | 2020-12-15 | 支付宝(杭州)信息技术有限公司 | GBDT model training method and device based on access mode protection |
| CN112184485A (en) * | 2020-09-30 | 2021-01-05 | 深圳供电局有限公司 | Power consumer credit assessment method |
| CN112270547A (en) * | 2020-10-27 | 2021-01-26 | 上海淇馥信息技术有限公司 | Financial risk assessment method and device based on feature construction and electronic equipment |
| CN112363716A (en) * | 2020-10-13 | 2021-02-12 | 杭州城市大数据运营有限公司 | Method, system and device for dynamically assembling evaluation model |
| CN112418520A (en) * | 2020-11-22 | 2021-02-26 | 同济大学 | Credit card transaction risk prediction method based on federal learning |
| CN112598252A (en) * | 2020-12-16 | 2021-04-02 | 中国建设银行股份有限公司 | Rating model training method and device |
| CN112819610A (en) * | 2021-02-26 | 2021-05-18 | 重庆度小满优扬科技有限公司 | Credit evaluation method, credit evaluation model training method and device |
| WO2021098385A1 (en) * | 2019-11-21 | 2021-05-27 | 支付宝(杭州)信息技术有限公司 | Method and apparatus for training gbdt model in trusted execution environment, and device |
| CN113240355A (en) * | 2021-07-12 | 2021-08-10 | 贝壳找房(北京)科技有限公司 | Training method and evaluation method of IM service evaluation model |
| CN113297289A (en) * | 2021-04-28 | 2021-08-24 | 上海淇玥信息技术有限公司 | Method and device for extracting business data from database and electronic equipment |
| CN113763092A (en) * | 2020-11-10 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Method, device, equipment and computer readable medium for recommending commodities |
| CN115271928A (en) * | 2022-08-17 | 2022-11-01 | 中国工商银行股份有限公司 | Credit card user value analysis method and device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030187765A1 (en) * | 2002-03-27 | 2003-10-02 | First Data Corporation | Systems and methods for monitoring credit risk |
| CN101046876A (en) * | 2006-03-31 | 2007-10-03 | 探宇科技股份有限公司 | Credit scoring system and method of using data mining method |
| CN101493913A (en) * | 2008-01-23 | 2009-07-29 | 阿里巴巴集团控股有限公司 | Method and system for assessing user credit in internet |
-
2016
- 2016-04-15 CN CN201610236701.4A patent/CN107301577A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030187765A1 (en) * | 2002-03-27 | 2003-10-02 | First Data Corporation | Systems and methods for monitoring credit risk |
| CN101046876A (en) * | 2006-03-31 | 2007-10-03 | 探宇科技股份有限公司 | Credit scoring system and method of using data mining method |
| CN101493913A (en) * | 2008-01-23 | 2009-07-29 | 阿里巴巴集团控股有限公司 | Method and system for assessing user credit in internet |
Non-Patent Citations (1)
| Title |
|---|
| XINRAN HE等: "Practical Lessons from Predicting Clicks on Ads at Facebook", 《KDD》 * |
Cited By (44)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108022146A (en) * | 2017-11-14 | 2018-05-11 | 深圳市牛鼎丰科技有限公司 | Characteristic item processing method, device, the computer equipment of collage-credit data |
| CN108009914A (en) * | 2017-12-19 | 2018-05-08 | 马上消费金融股份有限公司 | Credit risk assessment method, system, equipment and computer storage medium |
| WO2019128526A1 (en) * | 2017-12-27 | 2019-07-04 | 阿里巴巴集团控股有限公司 | Method, apparatus, and device for training risk control model and risk control |
| CN108229549A (en) * | 2017-12-28 | 2018-06-29 | 杭州大搜车汽车服务有限公司 | A kind of intelligent recognition car trader fits up method, electronic equipment and the storage medium of degree |
| CN108427658A (en) * | 2018-03-12 | 2018-08-21 | 北京奇艺世纪科技有限公司 | A kind of data predication method, device and electronic equipment |
| CN110322334A (en) * | 2018-03-29 | 2019-10-11 | 上海麦子资产管理集团有限公司 | Credit rating method and device, computer readable storage medium, terminal |
| CN110399602A (en) * | 2018-04-25 | 2019-11-01 | 北京京东尚科信息技术有限公司 | A method and device for evaluating text reliability |
| CN108681750A (en) * | 2018-05-21 | 2018-10-19 | 阿里巴巴集团控股有限公司 | The feature of GBDT models explains method and apparatus |
| US11205129B2 (en) | 2018-05-21 | 2021-12-21 | Advanced New Technologies Co., Ltd. | GBDT model feature interpretation method and apparatus |
| CN110634060A (en) * | 2018-06-21 | 2019-12-31 | 马上消费金融股份有限公司 | User credit risk assessment method, system, device and storage medium |
| CN109035003A (en) * | 2018-07-04 | 2018-12-18 | 北京玖富普惠信息技术有限公司 | Anti- fraud model modelling approach and anti-fraud monitoring method based on machine learning |
| CN109447273A (en) * | 2018-09-30 | 2019-03-08 | 深圳市元征科技股份有限公司 | Model training method, advertisement recommended method, relevant apparatus, equipment and medium |
| CN109754157A (en) * | 2018-11-30 | 2019-05-14 | 畅捷通信息技术股份有限公司 | A kind of methods of marking and system for reflecting enterprise's health management, financing and increasing letter |
| CN111275062A (en) * | 2018-12-04 | 2020-06-12 | 北京嘀嘀无限科技发展有限公司 | Model training method, device, server and computer readable storage medium |
| CN109767312A (en) * | 2018-12-10 | 2019-05-17 | 江西师范大学 | A credit evaluation model training and evaluation method and device |
| CN109767312B (en) * | 2018-12-10 | 2023-05-09 | 江西师范大学 | A credit evaluation model training, evaluation method and device |
| CN110008349A (en) * | 2019-02-01 | 2019-07-12 | 阿里巴巴集团控股有限公司 | The method and device for the event risk assessment that computer executes |
| CN110335134A (en) * | 2019-04-15 | 2019-10-15 | 梵界信息技术(上海)股份有限公司 | A method of it is converted based on WOE and realizes the classification of credit customer qualification |
| CN110443346A (en) * | 2019-08-12 | 2019-11-12 | 腾讯科技（深圳）有限公司 | A kind of model explanation method and device based on input feature vector importance |
| CN110443346B (en) * | 2019-08-12 | 2023-05-02 | 腾讯科技（深圳）有限公司 | Model interpretation method and device based on importance of input features |
| CN110544165A (en) * | 2019-09-02 | 2019-12-06 | 中诚信征信有限公司 | credit risk score card creating method and device and electronic equipment |
| CN110544165B (en) * | 2019-09-02 | 2022-06-03 | 中诚信征信有限公司 | Credit risk score card creating method and device and electronic equipment |
| CN110728301A (en) * | 2019-09-09 | 2020-01-24 | 北京镭文科技有限公司 | Credit scoring method, device, terminal and storage medium for individual user |
| WO2021098385A1 (en) * | 2019-11-21 | 2021-05-27 | 支付宝(杭州)信息技术有限公司 | Method and apparatus for training gbdt model in trusted execution environment, and device |
| CN111340121A (en) * | 2020-02-28 | 2020-06-26 | 支付宝(杭州)信息技术有限公司 | Target feature determination method and device |
| CN111340121B (en) * | 2020-02-28 | 2022-04-12 | 支付宝(杭州)信息技术有限公司 | Target feature determination method and device |
| CN111563810A (en) * | 2020-04-28 | 2020-08-21 | 北京云从科技有限公司 | Credit wind control model generation method, credit evaluation system, machine-readable medium and device |
| CN111861750A (en) * | 2020-07-22 | 2020-10-30 | 北京睿知图远科技有限公司 | Feature derivation system based on decision tree method and readable storage medium |
| CN111898675A (en) * | 2020-07-30 | 2020-11-06 | 北京云从科技有限公司 | Credit wind control model generation method and device, scoring card generation method, machine readable medium and equipment |
| CN112035453B (en) * | 2020-08-27 | 2024-03-12 | 平安科技（深圳）有限公司 | Recommendation method, device and storage medium based on GBDT high-order feature combination |
| CN112035453A (en) * | 2020-08-27 | 2020-12-04 | 平安科技（深圳）有限公司 | GBDT high-order feature combination-based recommendation method and device and storage medium |
| WO2021147568A1 (en) * | 2020-08-27 | 2021-07-29 | 平安科技（深圳）有限公司 | Gbdt high-order feature combination-based recommendation method, apparatus, and storage medium |
| CN112084519A (en) * | 2020-09-18 | 2020-12-15 | 支付宝(杭州)信息技术有限公司 | GBDT model training method and device based on access mode protection |
| CN112184485A (en) * | 2020-09-30 | 2021-01-05 | 深圳供电局有限公司 | Power consumer credit assessment method |
| CN112363716A (en) * | 2020-10-13 | 2021-02-12 | 杭州城市大数据运营有限公司 | Method, system and device for dynamically assembling evaluation model |
| CN112270547A (en) * | 2020-10-27 | 2021-01-26 | 上海淇馥信息技术有限公司 | Financial risk assessment method and device based on feature construction and electronic equipment |
| CN113763092A (en) * | 2020-11-10 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Method, device, equipment and computer readable medium for recommending commodities |
| CN112418520B (en) * | 2020-11-22 | 2022-09-20 | 同济大学 | A credit card transaction risk prediction method based on federated learning |
| CN112418520A (en) * | 2020-11-22 | 2021-02-26 | 同济大学 | Credit card transaction risk prediction method based on federal learning |
| CN112598252A (en) * | 2020-12-16 | 2021-04-02 | 中国建设银行股份有限公司 | Rating model training method and device |
| CN112819610A (en) * | 2021-02-26 | 2021-05-18 | 重庆度小满优扬科技有限公司 | Credit evaluation method, credit evaluation model training method and device |
| CN113297289A (en) * | 2021-04-28 | 2021-08-24 | 上海淇玥信息技术有限公司 | Method and device for extracting business data from database and electronic equipment |
| CN113240355A (en) * | 2021-07-12 | 2021-08-10 | 贝壳找房(北京)科技有限公司 | Training method and evaluation method of IM service evaluation model |
| CN115271928A (en) * | 2022-08-17 | 2022-11-01 | 中国工商银行股份有限公司 | Credit card user value analysis method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107301577A (en) | Training method, credit estimation method and the device of credit evaluation model | |
| CN110659744B (en) | Method and apparatus for training event prediction model and evaluating operational events | |
| CN111080338B (en) | User data processing method and device, electronic equipment and storage medium | |
| CN111709244B (en) | Deep learning method for identifying cause and effect relationship of contradictory dispute | |
| CN112270547A (en) | Financial risk assessment method and device based on feature construction and electronic equipment | |
| CN112037038B (en) | Bank credit risk prediction method and device | |
| CN116861258B (en) | Model processing method, device, equipment and storage medium | |
| CN115511501A (en) | Data processing method, computer equipment and readable storage medium | |
| CN109410036A (en) | A fraud detection model training method and device, and fraud detection method and device | |
| CN110363407A (en) | Risk of fraud appraisal procedure and device based on user behavior track | |
| CN111199474A (en) | A risk prediction method, device and electronic device based on network graph data of both parties | |
| CN111736940A (en) | Business interface display method and device for intelligent counter | |
| CN109829129A (en) | A kind of clicking rate predictor method based on FFM deep neural network | |
| CN110413307A (en) | Correlating method, device and the electronic equipment of code function | |
| CN114138954B (en) | User consultation question recommendation method, system, computer device and storage medium | |
| CN113159778B (en) | Financial fraud detection method and device | |
| Li et al. | Dual convolutional network based on hypergraph and multilevel feature fusion for road extraction from high-resolution remote sensing images | |
| CN116977064A (en) | Wind control model construction method, system and device based on loss function | |
| KR102414823B1 (en) | Method for dividing financial segment for financial service and apparatus for performing the method | |
| Sarigiannidis et al. | A novel lexicon-based approach in determining sentiment in financial data using learning automata | |
| CN111178535A (en) | Method and device for realizing automatic machine learning | |
| CN116933070A (en) | Content identification method, apparatus, device, storage medium, and program product | |
| CN115208775A (en) | Mobile phone bank flow prediction method and device | |
| CN119226024B (en) | Application program fault positioning method and device, electronic equipment and storage medium | |
| KR102414821B1 (en) | Method for generating artificial intelligence model for financial service and apparatus for performing the method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171027 |
|
| RJ01 | Rejection of invention patent application after publication |