CN109272396A - Customer risk method for early warning, device, computer equipment and medium - Google Patents
Customer risk method for early warning, device, computer equipment and medium Download PDFInfo
- Publication number
- CN109272396A CN109272396A CN201810949530.9A CN201810949530A CN109272396A CN 109272396 A CN109272396 A CN 109272396A CN 201810949530 A CN201810949530 A CN 201810949530A CN 109272396 A CN109272396 A CN 109272396A
- Authority
- CN
- China
- Prior art keywords
- risk
- data
- index
- related risks
- customer
- 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.)
- Granted
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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
This application involves a kind of customer risk method for early warning, device, computer equipment and storage medium based on big data analysis.The described method includes: obtaining the basic risk data of target customer, the basis risk data includes profession identity；Extract the basic risk indicator of the basic risk data；Obtain the co-related risks data of the target customer；The corresponding co-related risks index of the target customer is determined according to the co-related risks data；According to the profession identity, corresponding risk forecast model is obtained；The basic risk indicator and the co-related risks index are inputted into the risk forecast model, output obtains corresponding risk score, carries out customer risk early warning based on the risk score.Risk-warning accuracy can be improved using this method.
Description
Technical field
This application involves field of computer technology, set more particularly to a kind of customer risk method for early warning, device, computer
Standby and medium.
Background technique
In order to avoid risk, the financial institution for being related to loan transaction needs to carry out customer risk early warning to client after loan.
Customer risk early warning refers to uses qualitatively and quantitatively analysis to combine by inspection after the loan such as site inspection or non-at-scene inspection
Method finds credit risk as early as possible, and carries out early warning in time, so that business personnel presses defined permission and program to problem
Loan takes targetedly treatment measures.
Financial institution often carries out Risk-warning by computer to improve Risk-warning timeliness.But current computer
Data for risk analysis are that risk control personnel are carrying out client's correlation that risk tracking process is recognized to client mostly
Information.Since the client-related information angle of different risk control personnel concern is different, and the factor that can manually consider simultaneously
It is limited, often make the data dimension for risk analysis single, it is final to influence customer risk early warning accuracy.
Summary of the invention
Based on this, it is necessary in view of the above technical problems, provide a kind of client's wind that can be improved Risk-warning accuracy
Dangerous method for early warning, device, computer equipment and medium.
A kind of customer risk method for early warning, which comprises obtain the basic risk data of target customer, the basis
Risk data includes profession identity；Extract the basic risk indicator of the basic risk data；Obtain the pass of the target customer
Join risk data；The corresponding co-related risks index of the target customer is determined according to the co-related risks data；According to the row
Industry mark, obtains corresponding risk forecast model；The basic risk indicator and the co-related risks index are inputted into the wind
Dangerous prediction model, output obtain corresponding risk score, carry out customer risk early warning based on the risk score.
The co-related risks data include that there are the passes of incidence relation with the target customer in one of the embodiments,
Join the identification field of object；It is described to determine the corresponding co-related risks index of the target customer according to the co-related risks data,
It include: that the risk data of the affiliated partner is obtained according to the identification field；Risk data based on the affiliated partner with
And preset risk forecast model, calculate the risk score of the affiliated partner；Calculate each affiliated partner and the mesh
Mark the cohesion of client；According to the risk score and cohesion of the affiliated partner, determine the target customer by the pass
The risk shift rate for joining object influences, using the risk shift rate as a co-related risks index.
The method also includes the public sentiment datas of: monitoring network platform publication in one of the embodiments, by the carriage
Feelings data are split as multiple short texts；Profession identity is extracted in the short text, by the profession identity and corresponding short text
Association；The corresponding affection index of each short text is calculated using preset the analysis of public opinion model；Determine multiple short essays
This corresponding influence power weight；According to the affection index of associated short text and influence power weight, every kind of industry is calculated
Corresponding public opinion index is identified, the target customer is corresponded into the public opinion index of profession identity as a co-related risks index.
In one of the embodiments, before the corresponding risk forecast model of the acquisition profession identity, further includes:
Obtain the Sample Risk data and the corresponding profession identity of each sample client of multiple sample clients；To the Sample Risk
Data are pre-processed, and a variety of Sample Risk indexs are obtained；The Sample Risk index has corresponding data source category；More
The corresponding Industry risk index of each profession identity is screened in a Sample Risk index；It is instructed based on the Industry risk index
Get the corresponding object module of every kind of profession identity difference data source category；It is corresponding using every kind of profession identity
The corresponding risk forecast model of different target model foundation.
It is corresponding that each profession identity is screened in multiple Sample Risk indexs described in one of the embodiments,
Industry risk index, comprising: obtain the corresponding risk score of multiple sample clients；According to the risk score, statistically analyze
To the prediction force parameter of Sample Risk index described in every kind；Calculate the relevance parameter between a variety of Sample Risk indexs；
According to the prediction force parameter, relevance parameter and data source category, a variety of Sample Risk indexs are screened, are obtained
Target risk index；The corresponding Industry risk index of each profession identity is screened in multiple target risk indexs.
It is described in one of the embodiments, that every kind of profession identity difference institute is obtained based on Industry risk index training
State the corresponding object module of data source category, comprising: obtain the corresponding initial model of the difference data source category；
One or more of corresponding a variety of Industry risk indexs of same industry mark identical data source category are added to respective counts
According to the corresponding initial model of source category；Calculate the predictablity rate that the initial model of new Industry risk index is added；When described
When predictablity rate is greater than or equal to threshold value, retain the Industry risk index being newly added；Described in being less than when the predictablity rate
When threshold value, the Industry risk index being newly added is rejected；According to the corresponding profession identity of Industry risk Index Establishment and data of reservation
The corresponding object module of source category.
A kind of customer risk prior-warning device, which is characterized in that described device includes: basic risk identification module, obtains mesh
The basic risk data of client is marked, the basis risk data includes profession identity；Extract the basis of the basic risk data
Risk indicator；Co-related risks identification module, for obtaining the co-related risks data of the target customer；According to the co-related risks
Data determine the corresponding co-related risks index of the target customer；Customer risk warning module is used for according to the profession identity,
Obtain corresponding risk forecast model；The basic risk indicator and the co-related risks index are inputted into the risk profile mould
Type, output obtain corresponding risk score, carry out customer risk early warning based on the risk score.
The co-related risks data include that there are the passes of incidence relation with the target customer in one of the embodiments,
Join the identification field of object；The co-related risks identification module is also used to the risk data based on the affiliated partner and presets
Risk forecast model, calculate the risk score of the affiliated partner；Calculate each affiliated partner and the target customer
Cohesion；According to the risk score and cohesion of the affiliated partner, determine the target customer by the affiliated partner
The risk shift rate of influence, using the risk shift rate as a co-related risks index.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
Device realizes the customer risk early-warning processing method provided in any one embodiment of the application when executing the computer program
Step.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
The step of customer risk method for early warning provided in any one embodiment of the application is provided when row.
Above-mentioned customer risk method for early warning, device, computer equipment and storage medium, according to the basic risk of target customer
Data can extract the basic risk indicator of the basic risk data；It, can according to the co-related risks data of the target customer
With the corresponding co-related risks index of the determination target customer；According to the profession identity carried in basic risk data, can obtain
Take corresponding risk forecast model；The basic risk indicator and the co-related risks index are inputted into the risk profile mould
Type can export to obtain corresponding risk score, and then carry out customer risk early warning based on the risk score.Due to acquiring mesh
The risk data for marking the multiple dimensions of client carries out big data analysis to risk data based on risk forecast model, can integrate and examine
Consider multiple risk factors, improves Risk-warning accuracy；Group's division is carried out to client, different wind is set based on different industries
Dangerous prediction model fully considers the different attribute feature of different industries client, further increases Risk-warning accuracy.
Detailed description of the invention
Fig. 1 is the application scenario diagram of customer risk method for early warning in one embodiment；
Fig. 2 is the flow diagram of customer risk method for early warning in one embodiment；
Fig. 3 is the flow diagram of one embodiment risk prediction model construction step；
Fig. 4 is the structural block diagram of customer risk prior-warning device in one embodiment；
Fig. 5 is the internal structure chart of computer equipment in one embodiment.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
Customer risk method for early warning provided by the present application, can be applied in application environment as shown in Figure 1.Terminal 102
It is communicated with server 104 by network.Wherein, terminal 102 can be, but not limited to be various personal computers, notebook electricity
Brain, smart phone, tablet computer and portable wearable device, server 104 can be either multiple with independent server
The server cluster of server composition is realized.When needing to carry out risk profile to target customer, user can pass through terminal
102 send risk profile request to server 104.Server 104 responds risk profile request or according to preset time frequency
The basic risk data of target customer is obtained, the basic risk indicator of basic risk data is extracted.In addition to basic risk data, clothes
Business device also deeply excavates the co-related risks data of target customer, and such as there are the wind of the affiliated partner of incidence relation with target customer
Dangerous data etc..Server 104 determines the corresponding co-related risks index of target customer according to co-related risks data.Server 104 is pre-
Store the corresponding risk forecast model of a variety of profession identities.Server 104 is according to the industry mark for including in basic risk data
Know, obtains corresponding risk forecast model.Risk forecast model includes multiple risks and assumptions.Server 104 is according to risks and assumptions
Basic risk indicator and co-related risks index are screened, the basic risk indicator and co-related risks index that screening is obtained are defeated
Enter and get risk forecast model, output obtains the corresponding risk score of target customer.Server 104 compares based on risk score
It whether is more than threshold value, if so, carrying out Risk-warning.Above-mentioned customer risk prealarming process, the acquisition multiple dimensions of target customer
Risk data carries out big data analysis to risk data based on risk forecast model, can comprehensively consider multiple risk factors, mention
High risk early warning accuracy；Group's division is carried out to client, different risk forecast models is set based on different industries, is sufficiently examined
The different attribute feature for considering different industries client, further increases Risk-warning accuracy.
In one embodiment, as shown in Fig. 2, providing a kind of customer risk method for early warning, it is applied to Fig. 1 in this way
In server for be illustrated, comprising the following steps:
Step 202, the basic risk data of target customer is obtained, basic risk data includes profession identity.
The deterioration of target customer's financial index, negative public sentiment dramatically increase, owe taxes and be punished, and often reflect in it
The more serious problem in portion, such as managerial shortcoming, the deficiency of management ability will lead to it after risk is constantly gathered
Move towards promise breaking, it is therefore desirable to monitor in time to its risk data.Target customer can be enterprise, be also possible to individual；It can be
Existing client, is also possible to potential customers.Risk data is the number for referring to characterization target customer and violations possibility occurring
According to, such as credit record, financial data.The data type of risk data includes but is not limited to image, audio, text and number.
Risk data includes basic risk data, such as customer ID, credit data, financial data and silver prison data.Base
Plinth risk data belongs to data in row, can directly pull from specified data library.For example, credit data can be from Chinese personal name
It is pulled in the corresponding database in bank reference center；Financial data can pull in the corresponding database of financial web site；Silver prison
Data can be supervised in database from the Banking Supervision Commission and be pulled.
Step 204, the basic risk indicator of basic risk data is extracted.
Server pre-processes basic risk data, obtains multiple basic risk indicators.The basic wind of different types of data
Dangerous data prediction mode is different.Wherein, the basic risk data of numeric type, such as the financial data of target customer, as commenting
The key data source of the customer risk that sets the goal situation can be split by simple, that is, can be directly to corresponding basic risk
Index, such as the synchronous decline of assets growth rate, rate of gross profit are fallen on a year-on-year basis.But the basic wind of the data types such as image, audio, text
Dangerous data then need to obtain corresponding basic risk indicator, such as mesh through over cleaning, refinement, quantization or standardization etc.
Mark the client nearly 1 year non-performing loan receipt amount of money etc. that is settled.Basic risk indicator can be index index, be also possible to score
Index can also be derivative index.Wherein, derivative index can be is obtained by the logical operation of known risk indicator, such as with
Promise breaking client's similarity, with client's distance etc. of breaking a contract.
Step 206, the co-related risks data of target customer are obtained.
In addition to basic risk data, server also deeply excavates the co-related risks data of target customer, as law data,
Industrial and commercial data, real estate data, industry area data, customs's data etc..Specifically, server is from target customer in financial institution
Basic identification field is extracted in the identity information of retention.Basic identification field can be the parent of target customer and target customer
The identification field of category or friend's (hereinafter referred to as " affiliated partner ").Identification field includes name, identification card number, mobile phone
Number, Email Accounts, financial transaction account number, commonly used equipment information etc..Commonly used equipment information can be IMEI (International
Mobile Equipment Identity, international mobile equipment identification number), IP address, device-fingerprint, operating system version number,
Sequence number etc..
Different internet platforms have been run on different Internet Servers.Target customer is using various kinds of equipment access mechanism
When inside and outside internet platform, access data will be left in corresponding Internet Server.Accessing data can be with log or text
The form of part etc. stores.Internet Server can be communication operator, internet treasury management services quotient (such as bank), capital market
Market provider (such as Wind, finance data and analysis tool service provider), building service device provider, customs service provider,
Legal services provider, provider of industrial and commercial service provider etc. are used for the server of business processing.Server is according to the base of target customer
Plinth identification field generates data retrieval request, data retrieval request is sent to Internet Server.
Internet Server searches the access file comprising basic identification field, and the access file found is back to clothes
Business device.Access the file record associated access data of target customer.Server parses access file, obtains association and visits
Ask data.Associated access data refer to that target customer is based on the hair such as mobile terminal, automobile, intelligent robot, intelligent wearable device
The behavioral data of raw internet access behavior (such as registration behavior logs in behavior, browsing behavior, User behavior).Association is visited
Ask that data include static access data and dynamic access data.Wherein, static access data, which refer to, occurs internet access behavior
When the typing or data used, such as cell-phone number, the address Mac, IP address, device-fingerprint, identity information, Transaction Account number, log in letter
Breath, retrieval information etc..Dynamic access data refers to the data for occurring to generate when internet access behavior, manages money matters and remembers such as asset management
Record, investment securities record, capital market market transaction record, investment in property record, customs's transport record, lawsuit record
Deng.The risk data obtained from different channels has different data source categories, as the corresponding data source category of financial data can
To be " finance ", the corresponding data source category of law data can be " law " etc..
Step 208, the corresponding co-related risks index of target customer is determined according to co-related risks data.
Server pre-processes co-related risks data according to the above-mentioned processing mode to basic risk data, obtains more
A co-related risks index.Co-related risks index can be legal risk index, industrial and commercial risk data, real estate risk indicator, row
Industry Regional Risk index, customs's risk indicator etc..
Step 210, according to profession identity, corresponding risk forecast model is obtained.
Risk forecast model is the machine learning model of the Sample Risk data building based on multiple sample clients.Risk is pre-
Surveying model can be Logic Regression Models, be also possible to neural network model.Risk forecast model includes being based on Sample Risk number
According to multiple risks and assumptions that the obtained predictive ability of screening is strong, correlation is small.Risk forecast model is used for according to target customer's
Basic risk data and co-related risks data give a mark to the default risk of target customer.Default risk refers to that target customer sends out
It is raw to delay to refund, lose a possibility that violations such as loan repayment capacity before loan repayment day.
Step 212, basic risk indicator and co-related risks index are inputted into risk forecast model, output obtains corresponding wind
Danger scoring carries out customer risk early warning based on risk score.
Server is according to the risks and assumptions in risk forecast model, the basic risk indicator and co-related risks obtained to extraction
Index is screened, i.e., from extracting that for choosing that risk profile needs in a large amount of basic risk indicator and co-related risks index
Partial risks index.The basic risk indicator and co-related risks index that server obtains screening input risk forecast model, defeated
The probability value of violations occurs in the following set period for target customer out, and probability value is converted to risk score.Wherein,
Probability value to risk score transform mode can there are many, the corresponding of such as preset a variety of probability value sections and risk score is closed
System or preset probability value to risk score conversion factor etc., with no restriction to this.
In the present embodiment, according to the basic risk data of target customer, the basic risk of basic risk data can be extracted
Index；According to the co-related risks data of target customer, the corresponding co-related risks index of target customer can be determined；According to basic wind
The profession identity carried in dangerous data, available corresponding risk forecast model；Basic risk indicator and co-related risks are referred to
Mark input risk forecast model can export to obtain corresponding risk score, and then pre- based on risk score progress customer risk
It is alert.Due to acquiring the risk data of the multiple dimensions of target customer, big data point is carried out to risk data based on risk forecast model
Analysis can comprehensively consider multiple risk factors, improve Risk-warning accuracy；Group's division is carried out to client, based on not going together
Different risk forecast models is arranged in industry, fully considers the different attribute feature of different industries client, it is pre- to further increase risk
Alert accuracy.
In one embodiment, co-related risks data include that there are the marks of the affiliated partner of incidence relation with target customer
Field；The corresponding co-related risks index of target customer is determined according to co-related risks data, comprising: according to identification field, is obtained and is closed
Join the risk data of object；Risk data and preset risk forecast model based on affiliated partner, calculate affiliated partner
Risk score；Calculate each affiliated partner and the cohesion of target customer；According to the risk score and cohesion of affiliated partner, really
The risk shift rate that the client that sets the goal is influenced by affiliated partner, using risk shift rate as a co-related risks index.
Server calculates the risk shift rate of target customer, and using risk shift rate as a co-related risks index, with
Expand risk profile dimension.Specifically, the risk data of server by utilizing affiliated partner, calculates affiliated partner in the manner described above
Risk score.Basic risk data includes customer ID.Server obtains corresponding social network diagram according to customer ID.Society
Handing over network includes the corresponding target customer's node of customer ID and multiple associated client nodes.Social network diagram is according to client
Social networks data generate.Social networks data, which can be, to be crawled from preassigned social network sites.Work as mesh
When mark client is personal, the social networks in social network sites can be interrelated between friend relation, mutually concern etc.
Relationship.Social networks further include the associated data of custom actions, for example, client's publication or sharing information influence good friend
It commented on, thumbed up, forwarded.When target customer is enterprise, social networks can be the subordinate relation between enterprise.It is social
Network includes target customer's node, multiple affiliated partner nodes and the sideline for connecting node.
Server by utilizing presets the cohesion that calculation formula calculates each associated client node and target customer's node.Intimately
Degree calculation formula may is that
Wherein, cohesion of the Q (v, w) between associated client node w and target customer's node v；N (v) indicates target visitor
The adjacent node set of family node v；The mutual abutment number of nodes of target customer's node v and associated client node w is | N (v) ∩ N
(w)|；Adjacent node number is not for target customer's node v and associated client node | N (v) ∪ N (w) |.
Server according to the risk score of each affiliated partner and its with the cohesion of target customer, calculate the affiliated partner
The probability (hereinafter referred to as " risk shift rate ") of risk shift is caused to target customer.Server respectively corresponds multiple affiliated partners
The highest risk shift rate of risk shift rate intermediate value as a co-related risks index.It is readily appreciated that, server can also incite somebody to action
The corresponding average value of the corresponding risk shift rate of multiple affiliated partners does not limit this as a co-related risks index
System.
In the present embodiment, the risk shift rate of target customer is calculated, and receive risk shift rate as co-related risks index
Enter risk measuring and calculating limit of consideration, risk profile dimension can be expanded, and then Risk-warning accuracy can be improved.
In one embodiment, this method further include: the public sentiment data of monitoring network platform publication splits public sentiment data
For multiple short texts；Profession identity is extracted in short text, and profession identity is associated with corresponding short text；Utilize preset public sentiment
Analysis model calculates the corresponding affection index of each short text；Determine the corresponding influence power weight of multiple short texts；According to
The affection index and influence power weight of associated short text calculate the corresponding public opinion index of every kind of profession identity, by target visitor
Family corresponds to the public opinion index of profession identity as a co-related risks index.
Server calculates target customer and corresponds to the public opinion index of industry, and refers to public opinion index as a co-related risks
Mark, to expand risk profile dimension.Specifically, server crawls public sentiment data in the specified network platform.Public sentiment data.It can be
Text, voice, video or picture etc..If public sentiment data is voice, video or picture, it is first converted into text.After conversion
Public sentiment data be include it is multiple split identifiers long text.Each fractionation identifier position is determined as tearing open by server
Quartile is set, and is split in each fractionation position of long text, obtains multiple short texts.Splitting identifier can be with Statement Completion
Symbol, such as fullstop, exclamation mark.Server segments short text, synonymous replacement and name entity replacement are handled.According to preparatory
Replaced one or more participles are determined as by the corresponding public sentiment factor of a variety of influence object types of storage, server
Interim key word.The public sentiment factor refers to the factor that client's emotional attitude may be influenced in such public sentiment data.
The analysis of public opinion model has been stored in advance in server.The analysis of public opinion model can obtain machine learning classification model training
It arrives.Server is based on word2vec model and multiple interim key words is separately converted to corresponding term vector, and term vector is defeated
Enter accordingly to influence the corresponding the analysis of public opinion model of object type, the corresponding affection index of public sentiment data is calculated.
Each public sentiment data has corresponding profile information, such as issuing time, publication medium, publication author.Server
Profile information based on public sentiment data calculates the influence power weight of each public sentiment data.For example, influence power weight can be the time
Weight, media weight and author's weight etc. cumulative and.It is readily appreciated that, multiple short texts pair that same public sentiment data is split
The influence power weight answered is identical.
Server extracts profession identity by dictionary tree (trie) algorithm in short text.Profession identity is to refer to characterize
The keyword of industry attribute, such as finance, insurance.In other words, the interim key word that server extracts in certain short texts
Including profession identity.Server can extract identical or different profession identity in different short texts.Server is by industry
Mark is associated with corresponding short text.Be readily appreciated that, same industry mark may with from the multiple short of multiple public sentiment datas
Textual association.Affection index and corresponding influence power weight of the server according to the corresponding short text of profession identity, calculate corresponding
Industry is corresponding, public opinion index.For example, the corresponding public opinion index of each profession identity can be it is associated complete with the sector mark
The weighted sum of the affection index of portion's short text.
In the present embodiment, different industries are influenced in conjunction with the influence power weight calculation difference public sentiment data of public sentiment data, i.e.,
The analysis of public opinion accuracy can be improved in public opinion index；It calculates target customer and corresponds to the public opinion index of industry, and public opinion index is made
Risk is included in for co-related risks index and calculates limit of consideration, can expand risk profile dimension, and then Risk-warning can be improved
Accuracy.
In one embodiment, as shown in figure 3, further including wind before obtaining the corresponding risk forecast model of profession identity
The step of dangerous prediction model constructs, specifically includes:
Step 302, the Sample Risk data and the corresponding profession identity of each sample client of multiple sample clients are obtained.
Step 304, Sample Risk data are pre-processed, obtains a variety of Sample Risk indexs；Sample Risk index tool
There is corresponding data source category.
Server obtains the Sample Risk data of multiple sample clients from different data sources in the manner described above, and according to sample
This risk data carries out classification mark to each sample client, that is, determines the corresponding risk score of sample client.Server according to
Aforesaid way pre-processes Sample Risk data, obtains the corresponding multiple Sample Risk indexs of each sample client.Never
There is different data source categories with the Sample Risk data that channel obtains, as the corresponding data source category of financial data can be
" finance ", the corresponding data source category of law data can be " law " etc..According to the corresponding data of respective sample risk data
Source, each Sample Risk index have corresponding data source category.
Step 306, the corresponding Industry risk index of each profession identity is screened in multiple Sample Risk indexs.
Server obtains the corresponding risk score of multiple sample clients, is statisticallyd analyze to obtain every kind of sample according to risk score
The prediction force parameter of risk indicator.Server calculates the relevance parameter between a variety of Sample Risk indexs.Server is according to pre-
Dynamometry parameter and relevance parameter screen a variety of Sample Risk indexs, obtain the corresponding Industry risk of each profession identity
Index.
Step 308, based on the training of Industry risk index, to obtain every kind of profession identity different data source category corresponding
Object module.
Step 310, the corresponding corresponding risk forecast model of different target model foundation of every kind of profession identity is utilized.
The corresponding risk forecast model of each profession identity of server construction.Each risk forecast model includes multiple data
The corresponding object module of source category.Specifically, server obtains the corresponding initial model of different data source category, it will
It is corresponding that the corresponding multiple Industry risk indexs of same industry mark identical data source category are added to corresponding data source category one by one
Initial model.Per an Industry risk index is newly added, server calculates the introductory die after new Industry risk index is added
The predictablity rate of type, and whether comparison prediction accuracy rate is greater than or equal to threshold value.If so, retaining the Industry risk being newly added
Index；Conversely, rejecting the Industry risk index being newly added；It so repeats, until corresponding profession identity and data source category is complete
Whether portion's Industry risk index is identified retains.Server according to the corresponding profession identity of Industry risk Index Establishment of reservation and
The corresponding object module of data source category.
Server identifies corresponding multiple data sources classification for different industries and presets corresponding default weight respectively.Change speech
It, the object module that same industry identifies corresponding different data source category is respectively provided with different default weights；Different industries
The object module for identifying corresponding same data source category has different default weights.For example, corresponding " reference " mesh of industry M
Mark model A1, " finance " object module B1, " law " object module C1, " industry and commerce " object module D1, " real estate " object module
E1, " customs " object module F1 default weight can be followed successively by 0.2,0.2,0.1,0.1,0.3,0.1；Corresponding " the sign of industry N
Letter " object module A2, " finance " object module B2, " law " object module C2, " industry and commerce " object module D2, " real estate " target
Model E 2, the default weight of " customs " object module F2 can be followed successively by 0.2,0.1,0.4,0.1,0.1,0.1.With one of them
For industry, server logic-based regression algorithm identifies the object module of corresponding multiple data sources classification using the sector
With default weight, corresponding risk forecast model is constructed.
In the present embodiment, the Sample Risk data based on target customer's multiple data sources construct risk forecast model, so that
Risk forecast model, which can integrate, measures multiple risk factors, improves Risk-warning accuracy；Fully consider different industries client
Different attribute feature, client's industry is distinguished, different risk forecast models is set based on different industries, is further mentioned
High risk early warning accuracy.
In one embodiment, the corresponding Industry risk of each profession identity is screened in multiple Sample Risk indexs to refer to
Mark, comprising: obtain the corresponding risk score of multiple sample clients；According to risk score, statistical analysis obtains every kind of Sample Risk
The prediction force parameter of index；Calculate the relevance parameter between a variety of Sample Risk indexs；According to prediction force parameter, correlation ginseng
Several and data source category, screens a variety of Sample Risk indexs, obtains target risk index；In multiple target risk indexs
It is middle to screen the corresponding Industry risk index of each profession identity.
Server statisticallys analyze to obtain the prediction force parameter of every kind of Sample Risk index according to risk score.Predictive power refers to
Sample Risk index is for judging that the contribution rate of violations occurs for target customer.Specifically, server will based on risk score
Sample client divides into " good sample " and " bad sample ".Server is by the corresponding a variety of Sample Risk values of every kind of Sample Risk index
Different Sample Risk sections delimited, unitary variant analysis is carried out for every kind of Sample Risk index, counts different Sample Risks
The corresponding good sample probability in index section and bad sample probability.It is readily appreciated that, the corresponding good sample in same Sample Risk index section
This probability and bad sample probability and value be 1.By the way that good sample probability and bad sample probability are carried out difference operation and logarithm fortune
It calculates, and difference operation result and logarithm operation result is subjected to product calculation, obtain predictive power in respective risk index section
Parameter.The predictive power subparameter that Sample Risk index corresponds to multiple Sample Risk indexs section is carried out summation operation by server,
The corresponding prediction force parameter of the Sample Risk index can be obtained.Server calculates the phase between any two Sample Risk index
Closing property parameter.Relevance parameter can be Pearson correlation coefficient, distance correlation coefficient etc..
If the relevance parameter of two Sample Risk indexs is more than threshold value, server marks two Sample Risk indexs respectively
Target risk index is denoted as to be retained.If the relevance parameter of two Sample Risk indexs is more than threshold value, server identification is pre-
Whether the low corresponding data source category of Sample Risk index of dynamometry parameter has other Sample Risk indexs to be retained.If so, clothes
It is engaged in predicting the high Sample Risk index of force parameter in device two Sample Risk indexs of reservation, i.e., will predict the high sample wind of force parameter
Dangerous index is target risk index.Otherwise, server retains two Sample Risk indexs, as much as possible to be related to
Data source category.
Server screens the corresponding risk indicator of each profession identity respectively from multiple target risk indexs, is denoted as industry
Risk indicator.The client of different industries has different attribute feature, is suitable for difference using different target risk index buildings
The risk forecast model of industry, stress to consider when carrying out risk profile so as to the client to different industries different risks because
Element.
In the present embodiment, a variety of Sample Risk indexs are screened, it is strong using predictive power, correlation is weak and is related to more
The Sample Risk index of kind data source category constructs risk forecast model, and risk profile precision can be improved.
In one embodiment, every kind of profession identity different data source category difference is obtained based on the training of Industry risk index
Corresponding object module, comprising: obtain the corresponding initial model of different data source category；Same industry is identified into identical number
The corresponding introductory die of corresponding data source category is added to according to one or more of corresponding a variety of Industry risk indexs of source category
Type；Calculate the predictablity rate that the initial model of new Industry risk index is added；When predictablity rate is greater than or equal to threshold value
When, retain the Industry risk index being newly added；When predictablity rate is less than threshold value, the Industry risk index being newly added is rejected；
According to the corresponding profession identity of Industry risk Index Establishment and the corresponding object module of data source category of reservation.
Server obtains the corresponding initial model of different data source category.Server passes through stepwise regression method, from
Target risk index is chosen in the corresponding multiple target risk indexs of data source category one by one, initial model is added.Server often adds
Enter a target risk index, calculates the predictablity rate that joined the initial model of new target risk index.Prediction is accurate
The calculation of rate can be ROC curve (the receiver operating characteristic by generating initial model
Curve, Receiver operating curve) or confusion matrix etc., the parameter value that can characterize initial model accuracy rate is obtained, such as
AUC (Area Under Curve, the area under ROC curve) value, accurate rate rate etc..When the predictablity rate of initial model is less than
When threshold value, indicate that the target risk index being newly added is not applicable, server rejects the target risk index of the new addition.Originally
When the predictablity rate of beginning model is greater than or equal to threshold value, server retains the target risk index of the new addition.
In another embodiment, server is combined the corresponding target risk index of every kind of data source category, obtains
To the corresponding many indexes set of every kind of data source category；Initial model is trained based on different index sets, is obtained every
The corresponding mid-module of kind index set, calculates the predictablity rate of a variety of mid-modules；By the highest centre of predictablity rate
Model is labeled as the corresponding object module of corresponding data source category；Risk forecast model is established based on multiple object modules.
The quantity of target risk index is unlimited in index set, can be one, is also possible to multiple.Different index sets
The quantity of middle target risk index can not be identical.Server is based on different index sets and is trained to initial model.Specifically
, server obtains the corresponding initial model of multiple data source categories.Initial model can be linear regression model (LRM).With it
In for a data source category, corresponding many indexes set is separately added into initial model by server, is obtained each initial
The corresponding mid-module of model.Server calculates the predictablity rate etc. of mid-module in the manner described above.Screening server is pre-
The highest mid-module of accuracy rate is surveyed as the corresponding object module of the data source category.
In another embodiment, server is by stepwise regression method, from the corresponding multiple target wind of data source category
Target risk index is chosen in dangerous index one by one, initial model is added.Server one target risk index of every addition, according to upper
The mode of stating calculates the accuracy rate that joined the initial model of new target risk index.When the accuracy rate of initial model is less than threshold value
When, indicate that the target risk index being newly added is not applicable, server rejects the target risk index of the new addition.Work as introductory die
When the accuracy rate of type is greater than or equal to threshold value, server retains the target risk index of the new addition.
In the present embodiment, it is more acurrate to continuously attempt to the prediction result which kind of index set obtains, most quasi- using prediction result
The object module building risk forecast model that true index set training obtains, can be improved risk forecast model accuracy.
It should be understood that although each step in the flow chart of Fig. 2 and Fig. 3 is successively shown according to the instruction of arrow,
But these steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly state otherwise herein, these
There is no stringent sequences to limit for the execution of step, these steps can execute in other order.Moreover, in Fig. 2 and Fig. 3
At least part step may include that perhaps these sub-steps of multiple stages or stage are not necessarily same to multiple sub-steps
One moment executed completion, but can execute at different times, and the execution in these sub-steps or stage sequence is also not necessarily
Be successively carry out, but can at least part of the sub-step or stage of other steps or other steps in turn or
Alternately execute.
In one embodiment, as shown in figure 4, providing a kind of customer risk prior-warning device, comprising: basic risk identification
Module 402, co-related risks identification module 404 and customer risk warning module 406, in which:
Basic risk identification module 402, obtains the basic risk data of target customer, and basic risk data includes industry mark
Know；Extract the basic risk indicator of basic risk data；
Co-related risks identification module 404, for obtaining the co-related risks data of target customer；It is true according to co-related risks data
The corresponding co-related risks index of the client that sets the goal；
Customer risk warning module 406, for obtaining corresponding risk forecast model according to profession identity；By basic wind
Dangerous index and co-related risks index input risk forecast model, and output obtains corresponding risk score, are carried out based on risk score
Customer risk early warning.
In one embodiment, co-related risks data include that there are the marks of the affiliated partner of incidence relation with target customer
Field；Co-related risks identification module 404 is also used to risk data and preset risk forecast model based on affiliated partner, meter
Calculate the risk score of affiliated partner；Calculate each affiliated partner and the cohesion of target customer；It is commented according to the risk of affiliated partner
Point and cohesion, determine the risk shift rate that target customer is influenced by affiliated partner, using risk shift rate as one association
Risk indicator.
In one embodiment, co-related risks identification module 404 is also used to the public sentiment data of monitoring network platform publication, will
Public sentiment data is split as multiple short texts；Profession identity is extracted in short text, and profession identity is associated with corresponding short text；Benefit
The corresponding affection index of each short text is calculated with preset the analysis of public opinion model；Determine the corresponding influence of multiple short texts
Power weight；According to the affection index of associated short text and influence power weight, calculates the corresponding public sentiment of every kind of profession identity and refer to
Number, corresponds to the public opinion index of profession identity as a co-related risks index for target customer.
In one embodiment, which further includes prediction model building module 408, for obtaining multiple sample clients'
Sample Risk data and the corresponding profession identity of each sample client；Sample Risk data are pre-processed, a variety of samples are obtained
This risk indicator；Sample Risk index has corresponding data source category；Each industry is screened in multiple Sample Risk indexs
Identify corresponding Industry risk index；Every kind of profession identity different data source category difference is obtained based on the training of Industry risk index
Corresponding object module；Utilize the corresponding corresponding risk forecast model of different target model foundation of every kind of profession identity.
In one embodiment, prediction model building module 408 is also used to obtain the corresponding risk of multiple sample clients and comments
Point；According to risk score, statistical analysis obtains the prediction force parameter of every kind of Sample Risk index；Calculate a variety of Sample Risk indexs
Between relevance parameter；According to prediction force parameter, relevance parameter and data source category, a variety of Sample Risk indexs are carried out
Screening, obtains target risk index；The corresponding Industry risk index of each profession identity is screened in multiple target risk indexs.
In one embodiment, it is corresponding to be also used to obtain different data source category for prediction model building module 408
Initial model；By one or more additions in the corresponding a variety of Industry risk indexs of same industry mark identical data source category
To the corresponding initial model of corresponding data source category；The prediction for calculating the initial model of the new Industry risk index of addition is accurate
Rate；When predictablity rate is greater than or equal to threshold value, retain the Industry risk index being newly added；When predictablity rate is less than threshold value
When, reject the Industry risk index being newly added；According to the corresponding profession identity of Industry risk Index Establishment and data source class of reservation
Not corresponding object module.
Specific about customer risk prior-warning device limits the limit that may refer to above for customer risk method for early warning
Fixed, details are not described herein.Modules in above-mentioned customer risk prior-warning device can fully or partially through software, hardware and its
Combination is to realize.Above-mentioned each module can be embedded in the form of hardware or independently of in the processor in computer equipment, can also be with
It is stored in the memory in computer equipment in a software form, in order to which processor calls the above modules of execution corresponding
Operation.
In one embodiment, a kind of computer equipment is provided, which can be server, internal junction
Composition can be as shown in Figure 5.The computer equipment include by system bus connect processor, memory, network interface and
Database.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory packet of the computer equipment
Include non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program and data
Library.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The database of machine equipment is for storing basic risk data and co-related risks data.The network interface of the computer equipment be used for
External terminal passes through network connection communication.To realize a kind of pre- police of customer risk when the computer program is executed by processor
Method.
It will be understood by those skilled in the art that structure shown in Fig. 5, only part relevant to application scheme is tied
The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme, specific computer equipment
It may include perhaps combining certain components or with different component layouts than more or fewer components as shown in the figure.
A kind of computer readable storage medium is stored thereon with computer program, when computer program is executed by processor
The step of customer risk method for early warning provided in any one embodiment of the application is provided.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Instruct relevant hardware to complete by computer program, computer program to can be stored in a non-volatile computer readable
It takes in storage medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, this Shen
Please provided by any reference used in each embodiment to memory, storage, database or other media, may each comprise
Non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
Above embodiments only express the several embodiments of the application, and the description thereof is more specific and detailed, but can not
Therefore it is construed as limiting the scope of the patent.It should be pointed out that for those of ordinary skill in the art,
Under the premise of not departing from the application design, various modifications and improvements can be made, these belong to the protection scope of the application.
Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (10)
1. a kind of customer risk method for early warning, which comprises
The basic risk data of target customer is obtained, the basis risk data includes profession identity；
Extract the basic risk indicator of the basic risk data；
Obtain the co-related risks data of the target customer；
The corresponding co-related risks index of the target customer is determined according to the co-related risks data；
According to the profession identity, corresponding risk forecast model is obtained；
The basic risk indicator and the co-related risks index are inputted into the risk forecast model, output obtains corresponding wind
Danger scoring carries out customer risk early warning based on the risk score.
2. the method according to claim 1, wherein the co-related risks data include depositing with the target customer
In the identification field of the affiliated partner of incidence relation；It is described to determine that the target customer is corresponding according to the co-related risks data
Co-related risks index, comprising:
According to the identification field, the risk data of the affiliated partner is obtained；
Risk data and preset risk forecast model based on the affiliated partner, the risk for calculating the affiliated partner are commented
Point；
Calculate the cohesion of each affiliated partner and the target customer；
According to the risk score and cohesion of the affiliated partner, determine what the target customer was influenced by the affiliated partner
Risk shift rate, using the risk shift rate as a co-related risks index.
3. the method according to claim 1, wherein the method also includes:
The public sentiment data of monitoring network platform publication, is split as multiple short texts for the public sentiment data；
Profession identity is extracted in the short text, the profession identity is associated with corresponding short text；
The corresponding affection index of each short text is calculated using preset the analysis of public opinion model；
Determine the corresponding influence power weight of multiple short texts；
According to the affection index of associated short text and influence power weight, the corresponding public opinion index of every kind of profession identity is calculated,
The target customer is corresponded into the public opinion index of profession identity as a co-related risks index.
4. the method according to claim 1, wherein described obtain the corresponding risk profile mould of the profession identity
Before type, further includes:
Obtain the Sample Risk data and the corresponding profession identity of each sample client of multiple sample clients；
The Sample Risk data are pre-processed, a variety of Sample Risk indexs are obtained；The Sample Risk index have pair
The data source category answered；
The corresponding Industry risk index of each profession identity is screened in multiple Sample Risk indexs；
The corresponding target of every kind of profession identity difference data source category is obtained based on Industry risk index training
Model；
Utilize the corresponding corresponding risk forecast model of different target model foundation of every kind of profession identity.
5. according to the method described in claim 4, it is characterized in that, described screen each in multiple Sample Risk indexs
The corresponding Industry risk index of profession identity, comprising:
Obtain the corresponding risk score of multiple sample clients；
According to the risk score, statistical analysis obtains the prediction force parameter of every kind of Sample Risk index；
Calculate the relevance parameter between a variety of Sample Risk indexs；
According to the prediction force parameter, relevance parameter and data source category, a variety of Sample Risk indexs are screened,
Obtain target risk index；
The corresponding Industry risk index of each profession identity is screened in multiple target risk indexs.
6. according to the method described in claim 4, it is characterized in that, described obtain every kind based on Industry risk index training
The corresponding object module of the profession identity difference data source category, comprising:
Obtain the corresponding initial model of the difference data source category；
One or more of corresponding a variety of Industry risk indexs of same industry mark identical data source category are added to phase
Answer the corresponding initial model of data source category；
Calculate the predictablity rate that the initial model of new Industry risk index is added；
When the predictablity rate is greater than or equal to threshold value, retain the Industry risk index being newly added；
When the predictablity rate is less than the threshold value, the Industry risk index being newly added is rejected；
According to the corresponding profession identity of Industry risk Index Establishment and the corresponding object module of data source category of reservation.
7. a kind of customer risk prior-warning device, which is characterized in that described device includes:
Basic risk identification module obtains the basic risk data of target customer, and the basis risk data includes profession identity；
Extract the basic risk indicator of the basic risk data；
Co-related risks identification module, for obtaining the co-related risks data of the target customer；According to the co-related risks data
Determine the corresponding co-related risks index of the target customer；
Customer risk warning module, for obtaining corresponding risk forecast model according to the profession identity；By the basic wind
Dangerous index and the co-related risks index input the risk forecast model, and output obtains corresponding risk score, based on described
Risk score carries out customer risk early warning.
8. device according to claim 7, which is characterized in that the co-related risks data include depositing with the target customer
In the identification field of the affiliated partner of incidence relation；The co-related risks identification module is also used to the wind based on the affiliated partner
Dangerous data and preset risk forecast model, calculate the risk score of the affiliated partner；Calculate each affiliated partner
With the cohesion of the target customer；According to the risk score and cohesion of the affiliated partner, determine the target customer by
The risk shift rate influenced to the affiliated partner, using the risk shift rate as a co-related risks index.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In the step of processor realizes any one of claims 1 to 6 the method when executing the computer program.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any one of claims 1 to 6 is realized when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810949530.9A CN109272396B (en) | 2018-08-20 | 2018-08-20 | Customer risk early warning method, device, computer equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810949530.9A CN109272396B (en) | 2018-08-20 | 2018-08-20 | Customer risk early warning method, device, computer equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109272396A true CN109272396A (en) | 2019-01-25 |
| CN109272396B CN109272396B (en) | 2023-05-02 |
Family
ID=65153933
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810949530.9A Active CN109272396B (en) | 2018-08-20 | 2018-08-20 | Customer risk early warning method, device, computer equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109272396B (en) |
Cited By (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110119980A (en) * | 2019-04-23 | 2019-08-13 | 北京淇瑀信息科技有限公司 | A kind of anti-fraud method, apparatus, system and recording medium for credit |
| CN110209725A (en) * | 2019-06-06 | 2019-09-06 | 复旦大学 | Data visualisation system towards entry and exit commodity |
| CN110288483A (en) * | 2019-05-22 | 2019-09-27 | 平安证券股份有限公司 | Account activating method, device, equipment and computer readable storage medium |
| CN110335138A (en) * | 2019-06-21 | 2019-10-15 | 上海淇馥信息技术有限公司 | A kind of method for prewarning risk, device and electronic equipment for predicting objective group's qualification variation |
| CN110490720A (en) * | 2019-07-08 | 2019-11-22 | 深圳壹账通智能科技有限公司 | Financial data analysis and early warning method, apparatus, computer equipment and storage medium |
| CN110659799A (en) * | 2019-08-14 | 2020-01-07 | 深圳壹账通智能科技有限公司 | Attribute information processing method and device based on relational network, computer equipment and storage medium |
| CN110675155A (en) * | 2019-09-12 | 2020-01-10 | 阿里巴巴集团控股有限公司 | Risk identification method and device |
| CN110717814A (en) * | 2019-09-18 | 2020-01-21 | 阿里巴巴集团控股有限公司 | Method and device for generating risk message |
| CN110956391A (en) * | 2019-11-28 | 2020-04-03 | 中信银行股份有限公司 | Information processing method based on finance and electronic equipment |
| CN111177653A (en) * | 2019-12-10 | 2020-05-19 | 中国建设银行股份有限公司 | Credit assessment method and device |
| CN111178675A (en) * | 2019-12-05 | 2020-05-19 | 佰聆数据股份有限公司 | LR-Bagging algorithm-based electric charge recycling risk prediction method, system, storage medium and computer equipment |
| CN111192134A (en) * | 2019-12-16 | 2020-05-22 | 东方微银科技(北京)有限公司 | Risk conduction early warning method based on incidence relation |
| CN111198945A (en) * | 2019-12-03 | 2020-05-26 | 泰康保险集团股份有限公司 | Data processing method, device, medium and electronic equipment |
| CN111210323A (en) * | 2019-12-26 | 2020-05-29 | 大象慧云信息技术有限公司 | Enterprise tax risk monitoring method and system |
| CN111222968A (en) * | 2019-12-26 | 2020-06-02 | 大象慧云信息技术有限公司 | Enterprise tax risk management and control method and system |
| CN111353728A (en) * | 2020-05-06 | 2020-06-30 | 支付宝(杭州)信息技术有限公司 | Risk analysis method and system |
| CN111667356A (en) * | 2020-05-29 | 2020-09-15 | 北京睿知图远科技有限公司 | Multidimensional big data intelligent risk screening system |
| CN111695824A (en) * | 2020-06-16 | 2020-09-22 | 深圳前海微众银行股份有限公司 | Risk tail end client analysis method, device, equipment and computer storage medium |
| CN111950889A (en) * | 2020-08-10 | 2020-11-17 | 中国平安人寿保险股份有限公司 | Client risk assessment method and device, readable storage medium and terminal equipment |
| CN112116164A (en) * | 2020-09-28 | 2020-12-22 | 中国建设银行股份有限公司 | Regional stock right trading market risk early warning method and device |
| WO2021004344A1 (en) * | 2019-07-10 | 2021-01-14 | 平安科技（深圳）有限公司 | Data analysis-based risk identification method and related device |
| CN112613974A (en) * | 2020-12-16 | 2021-04-06 | 平安消费金融有限公司 | Risk early warning method, device, equipment and readable storage medium |
| CN112734566A (en) * | 2021-01-19 | 2021-04-30 | 中国农业银行股份有限公司 | Credit limit acquisition method and device and computer equipment |
| CN113129127A (en) * | 2021-04-21 | 2021-07-16 | 建信金融科技有限责任公司 | Early warning method and device |
| CN114580916A (en) * | 2022-03-07 | 2022-06-03 | 上海安硕企业征信服务有限公司 | Enterprise risk assessment method and device, electronic equipment and storage medium |
| CN115222303A (en) * | 2022-09-20 | 2022-10-21 | 北京共识数信科技有限公司 | Industry risk data analysis method and system based on big data and storage medium |
| CN116187094A (en) * | 2023-04-18 | 2023-05-30 | 中国标准化研究院 | Quality work prediction system based on real-time analysis of working conditions |
| CN117437040A (en) * | 2023-12-21 | 2024-01-23 | 广州平云小匠科技股份有限公司 | Method, equipment and storage medium for updating trust risk level |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110131131A1 (en) * | 2009-12-01 | 2011-06-02 | Bank Of America Corporation | Risk pattern determination and associated risk pattern alerts |
| US20130211983A1 (en) * | 2012-02-15 | 2013-08-15 | Bank Of America Corporation | On-going customer risk assessment of a financial institution customer population |
| CN106033575A (en) * | 2015-03-11 | 2016-10-19 | 阿里巴巴集团控股有限公司 | Risk account identification method and apparatus |
| CN106530078A (en) * | 2016-11-29 | 2017-03-22 | 流量海科技成都有限公司 | Loan risk early warning method and system based on multi-industry data |
| CN106855989A (en) * | 2016-12-29 | 2017-06-16 | 深圳微众税银信息服务有限公司 | Risk monitoring and control method and system after one kind loan |
| US20170193598A1 (en) * | 2015-12-31 | 2017-07-06 | International Business Machines Corporation | Post-lending credit management |
| CN107103548A (en) * | 2011-11-17 | 2017-08-29 | 阿里巴巴集团控股有限公司 | The monitoring method and system and risk monitoring and control method and system of network behavior data |
| CN107945024A (en) * | 2017-12-12 | 2018-04-20 | 厦门市美亚柏科信息股份有限公司 | Identify that internet finance borrowing enterprise manages abnormal method, terminal device and storage medium |
-
2018
- 2018-08-20 CN CN201810949530.9A patent/CN109272396B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110131131A1 (en) * | 2009-12-01 | 2011-06-02 | Bank Of America Corporation | Risk pattern determination and associated risk pattern alerts |
| CN107103548A (en) * | 2011-11-17 | 2017-08-29 | 阿里巴巴集团控股有限公司 | The monitoring method and system and risk monitoring and control method and system of network behavior data |
| US20130211983A1 (en) * | 2012-02-15 | 2013-08-15 | Bank Of America Corporation | On-going customer risk assessment of a financial institution customer population |
| CN106033575A (en) * | 2015-03-11 | 2016-10-19 | 阿里巴巴集团控股有限公司 | Risk account identification method and apparatus |
| US20170193598A1 (en) * | 2015-12-31 | 2017-07-06 | International Business Machines Corporation | Post-lending credit management |
| CN106530078A (en) * | 2016-11-29 | 2017-03-22 | 流量海科技成都有限公司 | Loan risk early warning method and system based on multi-industry data |
| CN106855989A (en) * | 2016-12-29 | 2017-06-16 | 深圳微众税银信息服务有限公司 | Risk monitoring and control method and system after one kind loan |
| CN107945024A (en) * | 2017-12-12 | 2018-04-20 | 厦门市美亚柏科信息股份有限公司 | Identify that internet finance borrowing enterprise manages abnormal method, terminal device and storage medium |
Cited By (32)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110119980A (en) * | 2019-04-23 | 2019-08-13 | 北京淇瑀信息科技有限公司 | A kind of anti-fraud method, apparatus, system and recording medium for credit |
| CN110288483A (en) * | 2019-05-22 | 2019-09-27 | 平安证券股份有限公司 | Account activating method, device, equipment and computer readable storage medium |
| CN110209725A (en) * | 2019-06-06 | 2019-09-06 | 复旦大学 | Data visualisation system towards entry and exit commodity |
| CN110335138A (en) * | 2019-06-21 | 2019-10-15 | 上海淇馥信息技术有限公司 | A kind of method for prewarning risk, device and electronic equipment for predicting objective group's qualification variation |
| CN110490720A (en) * | 2019-07-08 | 2019-11-22 | 深圳壹账通智能科技有限公司 | Financial data analysis and early warning method, apparatus, computer equipment and storage medium |
| WO2021004344A1 (en) * | 2019-07-10 | 2021-01-14 | 平安科技（深圳）有限公司 | Data analysis-based risk identification method and related device |
| WO2021027317A1 (en) * | 2019-08-14 | 2021-02-18 | 深圳壹账通智能科技有限公司 | Relationship network-based attribute information processing method and device, computer apparatus, and storage medium |
| CN110659799A (en) * | 2019-08-14 | 2020-01-07 | 深圳壹账通智能科技有限公司 | Attribute information processing method and device based on relational network, computer equipment and storage medium |
| CN110675155A (en) * | 2019-09-12 | 2020-01-10 | 阿里巴巴集团控股有限公司 | Risk identification method and device |
| CN110717814A (en) * | 2019-09-18 | 2020-01-21 | 阿里巴巴集团控股有限公司 | Method and device for generating risk message |
| CN110717814B (en) * | 2019-09-18 | 2023-05-02 | 创新先进技术有限公司 | Method and device for generating risk message |
| CN110956391A (en) * | 2019-11-28 | 2020-04-03 | 中信银行股份有限公司 | Information processing method based on finance and electronic equipment |
| CN111198945A (en) * | 2019-12-03 | 2020-05-26 | 泰康保险集团股份有限公司 | Data processing method, device, medium and electronic equipment |
| CN111178675A (en) * | 2019-12-05 | 2020-05-19 | 佰聆数据股份有限公司 | LR-Bagging algorithm-based electric charge recycling risk prediction method, system, storage medium and computer equipment |
| CN111177653B (en) * | 2019-12-10 | 2023-05-30 | 中国建设银行股份有限公司 | Credit evaluation method and device |
| CN111177653A (en) * | 2019-12-10 | 2020-05-19 | 中国建设银行股份有限公司 | Credit assessment method and device |
| CN111192134A (en) * | 2019-12-16 | 2020-05-22 | 东方微银科技(北京)有限公司 | Risk conduction early warning method based on incidence relation |
| CN111222968A (en) * | 2019-12-26 | 2020-06-02 | 大象慧云信息技术有限公司 | Enterprise tax risk management and control method and system |
| CN111210323A (en) * | 2019-12-26 | 2020-05-29 | 大象慧云信息技术有限公司 | Enterprise tax risk monitoring method and system |
| CN111353728A (en) * | 2020-05-06 | 2020-06-30 | 支付宝(杭州)信息技术有限公司 | Risk analysis method and system |
| CN111667356A (en) * | 2020-05-29 | 2020-09-15 | 北京睿知图远科技有限公司 | Multidimensional big data intelligent risk screening system |
| CN111695824A (en) * | 2020-06-16 | 2020-09-22 | 深圳前海微众银行股份有限公司 | Risk tail end client analysis method, device, equipment and computer storage medium |
| CN111695824B (en) * | 2020-06-16 | 2024-03-29 | 深圳前海微众银行股份有限公司 | Method, device, equipment and computer storage medium for analyzing risk tail end customer |
| CN111950889A (en) * | 2020-08-10 | 2020-11-17 | 中国平安人寿保险股份有限公司 | Client risk assessment method and device, readable storage medium and terminal equipment |
| CN112116164A (en) * | 2020-09-28 | 2020-12-22 | 中国建设银行股份有限公司 | Regional stock right trading market risk early warning method and device |
| CN112613974A (en) * | 2020-12-16 | 2021-04-06 | 平安消费金融有限公司 | Risk early warning method, device, equipment and readable storage medium |
| CN112734566A (en) * | 2021-01-19 | 2021-04-30 | 中国农业银行股份有限公司 | Credit limit acquisition method and device and computer equipment |
| CN113129127A (en) * | 2021-04-21 | 2021-07-16 | 建信金融科技有限责任公司 | Early warning method and device |
| CN114580916A (en) * | 2022-03-07 | 2022-06-03 | 上海安硕企业征信服务有限公司 | Enterprise risk assessment method and device, electronic equipment and storage medium |
| CN115222303A (en) * | 2022-09-20 | 2022-10-21 | 北京共识数信科技有限公司 | Industry risk data analysis method and system based on big data and storage medium |
| CN116187094A (en) * | 2023-04-18 | 2023-05-30 | 中国标准化研究院 | Quality work prediction system based on real-time analysis of working conditions |
| CN117437040A (en) * | 2023-12-21 | 2024-01-23 | 广州平云小匠科技股份有限公司 | Method, equipment and storage medium for updating trust risk level |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109272396B (en) | 2023-05-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109272396A (en) | Customer risk method for early warning, device, computer equipment and medium | |
| CN109165840A (en) | Risk profile processing method, device, computer equipment and medium | |
| CN108876600B (en) | Early warning information pushing method, device, computer equipment and medium | |
| WO2022126963A1 (en) | Customer profiling method based on customer response corpora, and device related thereto | |
| CN109543925B (en) | Risk prediction method and device based on machine learning, computer equipment and storage medium | |
| CN109829628A (en) | Method for prewarning risk, device and computer equipment based on big data | |
| CN109376237B (en) | Client stability prediction method, device, computer equipment and storage medium | |
| CN109829629A (en) | Generation method, device, computer equipment and the storage medium of risk analysis reports | |
| US11562372B2 (en) | Probabilistic feature engineering technique for anomaly detection | |
| CN109063921A (en) | Optimized treatment method, device, computer equipment and the medium of customer risk early warning | |
| CN112668859A (en) | Big data based customer risk rating method, device, equipment and storage medium | |
| WO2020073727A1 (en) | Risk forecast method, device, computer apparatus, and storage medium | |
| KR102146546B1 (en) | Method for provide enterprise stock forecasting algorithm based on situation cognition | |
| CN112199510A (en) | Fraud probability determination method and device, electronic equipment and storage medium | |
| US20170140301A1 (en) | Identifying social business characteristic user | |
| CN109872234A (en) | Trading activity monitoring method, device, computer equipment and medium | |
| Kumar et al. | Emotion analysis of news and social media text for stock price prediction using svm-lstm-gru composite model | |
| de Oliveira et al. | Absenteeism prediction in call center using machine learning algorithms | |
| US20130173237A1 (en) | Score fusion based on the gravitational force between two objects | |
| CN111582757B (en) | Method, device, equipment and computer readable storage medium for analyzing fraud risk | |
| CN113407734B (en) | Method for constructing knowledge graph system based on real-time big data | |
| CN115099988A (en) | Model training method, data processing method, device and computer medium | |
| Zhao et al. | Innovative mechanism of rural finance: Risk assessment methods and impact factors of agricultural loans based on personal emotion and artificial intelligence | |
| CN114037518A (en) | Risk prediction model construction method and device, electronic equipment and storage medium | |
| Zang | Construction of Mobile Internet Financial Risk Cautioning Framework Based on BP Neural Network |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |