CN111582878A - Transaction risk prediction method, device and system - Google Patents
Transaction risk prediction method, device and system Download PDFInfo
- Publication number
- CN111582878A CN111582878A CN202010392844.0A CN202010392844A CN111582878A CN 111582878 A CN111582878 A CN 111582878A CN 202010392844 A CN202010392844 A CN 202010392844A CN 111582878 A CN111582878 A CN 111582878A
- Authority
- CN
- China
- Prior art keywords
- transaction
- risk
- node
- risk prediction
- data
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/38—Payment protocols; Details thereof
- G06Q20/40—Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
- G06Q20/401—Transaction verification
- G06Q20/4016—Transaction verification involving fraud or risk level assessment in transaction processing
-
- 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
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/38—Payment protocols; Details thereof
- G06Q20/381—Currency conversion
-
- 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
-
- 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
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Technology Law (AREA)
- Computer Security & Cryptography (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention discloses a transaction risk prediction method, a device and a system, which are used for carrying out transaction node feature extraction on acquired transaction behavior data to obtain a first feature data set, wherein the first feature data set comprises: and carrying out risk prediction on the first characteristic data set by using the node name and the node execution sequence of each transaction node through the constructed risk assessment model to obtain a risk prediction result. Therefore, the risk prediction of the transaction node in the transaction operation is realized, and the transaction risk brought by the risk transaction behavior is reduced by reminding business personnel to verify and correct the risk transaction behavior.
Description
Technical Field
The invention relates to the technical field of computer data processing, in particular to a transaction risk prediction method, a device and a system.
Background
Bank counter services usually have a series of operating specification requirements, and a service scene is composed of a series of transaction nodes and transaction data. Taking the example of a client transacting foreign currency exchange business, a teller needs to sequentially operate the following transaction nodes in a banking system: the method comprises the steps of automatically reading identity card information, initiating identity information networking check transaction, creating temporary customers, exchanging foreign currency, authorizing and auditing and taking out foreign currency. In the process, for example, initiating an identity information networking check transaction and authorizing to check two transaction nodes are missed, or a teller illegally operates other transaction nodes, for example, operates other transfer transaction nodes to transfer customer funds, and the like, which causes a great risk to the whole transaction.
The business data of the bank is dispersed in different background business systems, and the accident risk control of the current bank counter business is usually that a single background business system carries out rule judgment on the transaction data to find out the transaction risk. For example, when foreign currency is exchanged, the bank system recognizes that the customer does not have the customer number of the bank and performs transaction interception. Although the monitoring of the over-the-counter transaction level can intercept partial illegal transactions or error operations to a certain extent, the monitoring mode can only realize risk prediction of transaction data, and cannot realize risk prediction of transaction nodes in transaction operations.
Disclosure of Invention
In view of this, the invention discloses a transaction risk prediction method, a transaction risk prediction device and a transaction risk prediction system, so as to realize risk prediction of transaction nodes in transaction operation, thereby reducing transaction risks brought by risk transaction behaviors by reminding business personnel to verify and correct the risk transaction behaviors.
A transaction risk prediction method, comprising:
acquiring transaction behavior data;
performing transaction node feature extraction on the transaction behavior data to obtain a first feature data set, wherein the first feature data set comprises: the node name and the node execution sequence of each transaction node;
and performing risk prediction on the first characteristic data set by using the constructed risk assessment model to obtain a risk prediction result.
Optionally, the risk assessment model is: the method comprises the following steps of training a model obtained based on marked transaction node data in historical transaction node data under different service scenes, wherein the marked transaction node data is transaction node data of a risk label in the historical transaction node data, and the risk label comprises the following components: risk events and non-risk events.
Optionally, the constructing process of the risk assessment model includes:
acquiring historical transaction node data under different service scenes;
marking the historical transaction node data according to a normal operation sequence of the service determined based on service rules under different service scenes to obtain marked transaction node data;
performing transaction node feature extraction on the marked transaction node data to obtain a second feature data set;
and training the second characteristic data set to obtain a risk assessment model.
Optionally, the method further includes:
determining a transaction risk monitoring mode according to the risk prediction result, wherein the risk prediction result comprises: the abnormal probability or the risk degree, the transaction risk monitoring mode comprises: prompting and/or intercepting the transaction.
Optionally, the method further includes:
optimizing the risk assessment model based on the first feature dataset and the risk prediction result.
A transaction risk prediction device comprising:
the acquisition unit is used for acquiring transaction behavior data;
an extraction unit, configured to perform transaction node feature extraction on the transaction behavior data to obtain a first feature data set, where the first feature data set includes: the node name and the node execution sequence of each transaction node;
and the prediction unit is used for performing risk prediction on the first characteristic data set by using the constructed risk assessment model to obtain a risk prediction result.
Optionally, the risk assessment model is: the method comprises the following steps of training a model obtained based on marked transaction node data in historical transaction node data under different service scenes, wherein the marked transaction node data is transaction node data of a risk label in the historical transaction node data, and the risk label comprises the following components: risk events and non-risk events.
Optionally, the method further includes: a model construction unit for constructing the risk assessment model;
the model building unit is specifically configured to:
acquiring historical transaction node data under different service scenes;
marking the historical transaction node data according to a normal operation sequence of the service determined based on service rules under different service scenes to obtain marked transaction node data;
performing transaction node feature extraction on the marked transaction node data to obtain a second feature data set;
and training the second characteristic data set to obtain a risk assessment model.
Optionally, the method further includes:
the monitoring and determining unit is used for determining a transaction risk monitoring mode according to the risk prediction result, and the risk prediction result comprises: the abnormal probability or the risk degree, the transaction risk monitoring mode comprises: prompting and/or intercepting the transaction.
Optionally, the method further includes:
and the optimizing unit is used for optimizing the risk assessment model based on the first characteristic data set and the risk prediction result.
A transaction risk prediction system comprising at least one processor and a memory storing computer executable instructions, the processor executing the instructions to carry out the steps of the method described above.
From the above technical solutions, the present invention discloses a method, an apparatus, and a system for predicting transaction risk, which perform transaction node feature extraction on acquired transaction behavior data to obtain a first feature data set, where the first feature data set includes: and carrying out risk prediction on the first characteristic data set by using the node name and the node execution sequence of each transaction node through the constructed risk assessment model to obtain a risk prediction result. Therefore, the risk prediction of the transaction node in the transaction operation is realized, and the transaction risk brought by the risk transaction behavior is reduced by reminding business personnel to verify and correct the risk transaction behavior.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the disclosed drawings without creative efforts.
FIG. 1 is a flow chart of a transaction risk prediction method according to an embodiment of the present invention;
FIG. 2 is a flow chart of another transaction risk prediction method disclosed in the embodiments of the present invention;
fig. 3 is a schematic structural diagram of a transaction risk prediction apparatus according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of another transaction risk prediction apparatus according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the invention discloses a transaction risk prediction method, a device and a system, which are disclosed by the invention, and are used for performing transaction node feature extraction on acquired transaction behavior data to obtain a first feature data set, wherein the first feature data set comprises: and carrying out risk prediction on the first characteristic data set by using the node name and the node execution sequence of each transaction node through the constructed risk assessment model to obtain a risk prediction result. Therefore, the risk prediction of the transaction node in the transaction operation is realized, and the transaction risk brought by the risk transaction behavior is reduced by reminding business personnel to verify and correct the risk transaction behavior.
Referring to fig. 1, a flowchart of a transaction risk prediction method disclosed in an embodiment of the present invention includes the steps of:
step S101, acquiring transaction behavior data;
wherein, the transaction behavior means: when a bank provides financial services for a client, a teller initiates a series of system transaction operations through a teller front-end system, and the operation process in the whole scene from a first entrance picture to the end of the transaction is started.
The transaction behavior data refers to: data generated during the execution of the transaction.
The transaction behavior data mainly comprises: a transaction node and transaction data.
It should be noted that the transaction behavior data in this embodiment may be real-time transaction behavior data of T day (transaction day), or transaction behavior data after T +1 day.
Step S102, transaction node feature extraction is carried out on the transaction behavior data to obtain a first feature data set;
wherein the first feature set comprises: the node name of each transaction node and the execution order of the nodes.
In practical application, transaction node feature extraction can be performed on the current transaction behavior data based on the business rules to obtain a feature data set.
Taking the example of a client transacting foreign currency exchange business, a teller needs to sequentially operate the following transaction nodes in a banking system: the method comprises the steps of automatically reading identity card information, initiating identity information networking check transaction, creating temporary customers, exchanging foreign currency, authorizing and auditing and taking out foreign currency.
And S103, performing risk prediction on the first characteristic data set by using the constructed risk assessment model to obtain a risk prediction result.
In practical application, the characteristic data in the characteristic data set is input into a pre-constructed risk assessment model to obtain a risk prediction result.
The risk assessment model is: and training the obtained model based on marked transaction node data in the historical transaction node data under different service scenes. The marked transaction node data can be transaction node data of existing risk labels in historical transaction node data, and the risk labels can be determined according to user reports after the historical transactions occur, pre-stored historical transaction prediction results and the like. The risk label includes: risk events and non-risk events.
It should be noted that, when constructing the risk assessment model, with the customer as the center and the scene as the unit in advance, the teller is integrated to serve all transaction flows of a single customer, including: transaction information between systems, authorized auditing action, card swiping operation and the like.
In this embodiment, the construction process of the risk assessment model includes:
acquiring historical transaction node data under different service scenes;
marking the historical transaction node data according to a normal operation sequence of the service determined based on service rules under different service scenes to obtain marked transaction node data;
performing transaction node feature extraction on the marked transaction node data to obtain a second feature data set;
and training the second characteristic data set to obtain a risk assessment model.
In practical application, any machine learning model based on big data can be adopted for model training to obtain a risk assessment model. The training samples for training the risk assessment model are as follows: a feature data set and a risk label, wherein the feature data set is: and performing transaction node feature extraction on the historical transaction behavior data to obtain the transaction node feature extraction result.
The training follows the principle: the output result of the risk assessment model can accurately describe whether the transaction behavior data has risks.
To sum up, the method for predicting transaction risk disclosed by the present invention performs transaction node feature extraction on the acquired transaction behavior data to obtain a first feature data set, where the first feature data set includes: and carrying out risk prediction on the first characteristic data set by using the node name and the node execution sequence of each transaction node through the constructed risk assessment model to obtain a risk prediction result. Therefore, the risk prediction of the transaction node in the transaction operation is realized, and the transaction risk brought by the risk transaction behavior is reduced by reminding business personnel to verify and correct the risk transaction behavior.
Because the risk transaction behavior data are possibly continuously changed, a bank generates a new risk event, and the risk evaluation model cannot predict new risk transaction behaviors, the risk evaluation model can be continuously supplemented with the new risk transaction behavior data to train so as to update the risk evaluation model in order to perfect and optimize the risk evaluation model, and the accuracy of prediction of the risk evaluation model is improved.
To further optimize the above embodiment, after step S103, the method may further include:
optimizing the risk assessment model based on the first feature dataset and the risk prediction result.
In order to reduce the transaction risk brought by the risk transaction behavior data, in practical application, the invention can also carry out in-process interception or after-event feedback on the risk behavior so as to remind business personnel to verify and correct the risk transaction behavior.
Specifically, referring to fig. 2, a flowchart of a transaction risk prediction method disclosed in another embodiment of the present invention includes the steps of:
step S101, acquiring transaction behavior data;
wherein, the transaction behavior means: when a bank provides financial services for a client, a teller initiates a series of system transaction operations through a teller front-end system, and the operation process in the whole scene from a first entrance picture to the end of the transaction is started.
The transaction behavior data refers to: data generated during the execution of the transaction.
The transaction behavior data mainly comprises: a transaction node and transaction data.
Step S102, transaction node feature extraction is carried out on the transaction behavior data to obtain a first feature data set;
wherein the first feature set comprises: the node name of each transaction node and the execution order of the nodes.
In practical application, transaction node feature extraction can be performed on the current transaction behavior data based on the business rules to obtain a feature data set.
S103, performing risk prediction on the first characteristic data set by using the constructed risk assessment model to obtain a risk prediction result;
in practical application, the characteristic data in the characteristic data set is input into a pre-constructed risk assessment model to obtain a risk prediction result.
The risk assessment model is: and training the obtained model based on marked transaction node data in the historical transaction node data under different service scenes. The marked transaction node data can be transaction node data of existing risk labels in historical transaction node data, and the risk labels can be determined according to user reports after the historical transactions occur, pre-stored historical transaction prediction results and the like. The risk label includes: risk events and non-risk events.
And step S104, determining a transaction risk monitoring mode according to the risk prediction result.
Wherein the risk prediction outcome comprises: the abnormal probability or the risk degree, the transaction risk monitoring mode comprises: prompting and/or intercepting the transaction.
To sum up, the method for predicting transaction risk disclosed by the present invention performs transaction node feature extraction on the acquired transaction behavior data to obtain a first feature data set, where the first feature data set includes: and carrying out risk prediction on the first characteristic data set by using the node name and the node execution sequence of each transaction node by using the constructed risk assessment model to obtain a risk prediction result, and determining a transaction envelope monitoring mode according to the risk prediction result. Therefore, the invention realizes risk prediction of transaction nodes in transaction operation, and can prompt and/or intercept transaction behaviors with high abnormal probability or risk degree, thereby reminding business personnel to verify and correct the risk transaction behaviors and reducing transaction risks brought by the risk transaction behaviors.
Corresponding to the embodiment of the method, the invention also discloses a transaction risk prediction device.
Referring to fig. 3, a schematic structural diagram of a transaction risk prediction apparatus according to an embodiment of the present invention includes:
an acquisition unit 201, configured to acquire transaction behavior data;
wherein, the transaction behavior means: when a bank provides financial services for a client, a teller initiates a series of system transaction operations through a teller front-end system, and the operation process in the whole scene from a first entrance picture to the end of the transaction is started.
The transaction behavior data refers to: data generated during the execution of the transaction.
The transaction behavior data mainly comprises: a transaction node and transaction data.
It should be noted that the transaction behavior data in this embodiment may be real-time transaction behavior data of T day (transaction day), or transaction behavior data after T +1 day.
An extracting unit 202, configured to perform transaction node feature extraction on the transaction behavior data to obtain a first feature data set, where the first feature data set includes: the node name and the node execution sequence of each transaction node;
in practical application, transaction node feature extraction can be performed on the current transaction behavior data based on the business rules to obtain a feature data set.
Taking the example of a client transacting foreign currency exchange business, a teller needs to sequentially operate the following transaction nodes in a banking system: the method comprises the steps of automatically reading identity card information, initiating identity information networking check transaction, creating temporary customers, exchanging foreign currency, authorizing and auditing and taking out foreign currency.
And the predicting unit 203 is configured to perform risk prediction on the first feature data set by using the constructed risk assessment model to obtain a risk prediction result.
In practical application, the characteristic data in the characteristic data set is input into a pre-constructed risk assessment model to obtain a risk prediction result.
The risk assessment model is: and training the obtained model based on marked transaction node data in the historical transaction node data under different service scenes. The marked transaction node data can be transaction node data of existing risk labels in historical transaction node data, and the risk labels can be determined according to user reports after the historical transactions occur, pre-stored historical transaction prediction results and the like. The risk label includes: risk events and non-risk events.
It should be noted that, when constructing the risk assessment model, with the customer as the center and the scene as the unit in advance, the teller is integrated to serve all transaction flows of a single customer, including: transaction information between systems, authorized auditing action, card swiping operation and the like.
To sum up, the transaction risk prediction apparatus disclosed in the present invention performs transaction node feature extraction on the acquired transaction behavior data to obtain a first feature data set, where the first feature data set includes: and carrying out risk prediction on the first characteristic data set by using the node name and the node execution sequence of each transaction node through the constructed risk assessment model to obtain a risk prediction result. Therefore, the risk prediction of the transaction node in the transaction operation is realized, and the transaction risk brought by the risk transaction behavior is reduced by reminding business personnel to verify and correct the risk transaction behavior.
It will be appreciated that the risk assessment model first needs to be built before the prediction unit 203 is executed.
Therefore, to further optimize the above embodiment, the transaction risk prediction device may further include:
and the model construction unit is used for constructing the risk assessment model.
Wherein the model construction unit is specifically configured to:
acquiring historical transaction node data under different service scenes;
marking the historical transaction node data according to a normal operation sequence of the service determined based on service rules under different service scenes to obtain marked transaction node data;
performing transaction node feature extraction on the marked transaction node data to obtain a second feature data set;
and training the second characteristic data set to obtain a risk assessment model.
In practical application, any machine learning model based on big data can be adopted for model training to obtain a risk assessment model. The training samples for training the risk assessment model are as follows: a feature data set and a risk label, wherein the feature data set is: and performing transaction node feature extraction on the historical transaction behavior data to obtain the transaction node feature extraction result.
The training follows the principle: the output result of the risk assessment model can accurately describe whether the transaction behavior data has risks.
Because the risk transaction behavior data are possibly continuously changed, a bank generates a new risk event, and the risk evaluation model cannot predict new risk transaction behaviors, the risk evaluation model can be continuously supplemented with the new risk transaction behavior data to train so as to update the risk evaluation model in order to perfect and optimize the risk evaluation model, and the accuracy of prediction of the risk evaluation model is improved.
To further optimize the above embodiment, the transaction risk prediction device may further include:
and the optimizing unit is used for optimizing the risk assessment model based on the first characteristic data set and the risk prediction result.
In order to reduce the transaction risk brought by the risk transaction behavior data, in practical application, the invention can also carry out in-process interception or after-event feedback on the risk behavior so as to remind business personnel to verify and correct the risk transaction behavior.
Specifically, referring to fig. 4, a schematic structural diagram of a transaction risk prediction apparatus according to an embodiment of the present invention includes:
an acquisition unit 201, configured to acquire transaction behavior data;
wherein, the transaction behavior means: when a bank provides financial services for a client, a teller initiates a series of system transaction operations through a teller front-end system, and the operation process in the whole scene from a first entrance picture to the end of the transaction is started.
The transaction behavior data refers to: data generated during the execution of the transaction.
The transaction behavior data mainly comprises: a transaction node and transaction data.
An extracting unit 202, configured to perform transaction node feature extraction on the transaction behavior data to obtain a first feature data set, where the first feature data set includes: the node name and the node execution sequence of each transaction node;
in practical application, transaction node feature extraction can be performed on the current transaction behavior data based on the business rules to obtain a feature data set.
The prediction unit 203 is configured to perform risk prediction on the first feature data set by using the constructed risk assessment model to obtain a risk prediction result;
in practical application, the characteristic data in the characteristic data set is input into a pre-constructed risk assessment model to obtain a risk prediction result.
A monitoring determining unit 204, configured to determine a transaction risk monitoring manner according to the risk prediction result, where the risk prediction result includes: the abnormal probability or the risk degree, the transaction risk monitoring mode comprises: prompting and/or intercepting the transaction.
To sum up, the transaction risk prediction apparatus disclosed in the present invention performs transaction node feature extraction on the acquired transaction behavior data to obtain a first feature data set, where the first feature data set includes: and carrying out risk prediction on the first characteristic data set by using the node name and the node execution sequence of each transaction node by using the constructed risk assessment model to obtain a risk prediction result, and determining a transaction envelope monitoring mode according to the risk prediction result. Therefore, the invention realizes risk prediction of transaction nodes in transaction operation, and can prompt and/or intercept transaction behaviors with high abnormal probability or risk degree, thereby reminding business personnel to verify and correct the risk transaction behaviors and reducing transaction risks brought by the risk transaction behaviors.
The invention also provides a transaction risk prediction system, which can be an independent transaction risk prediction processing system and can also be applied to various transaction analysis processing systems. The system may be a single server, or may include a server cluster, a system (including a distributed system), software (applications), an actual operation device, a logic gate device, a quantum computer, etc. using one or more of the methods or one or more of the example devices of the present specification, in combination with a terminal device implementing hardware as necessary. The transaction risk prediction processing system may comprise at least one processor and a memory storing computer executable instructions which, when executed by the processor, implement the steps of the method of any one or more of the embodiments described above.
To sum up, the transaction risk prediction system disclosed in the present invention performs transaction node feature extraction on the acquired transaction behavior data to obtain a first feature data set, where the first feature data set includes: and carrying out risk prediction on the first characteristic data set by using the node name and the node execution sequence of each transaction node through the constructed risk assessment model to obtain a risk prediction result. Therefore, the risk prediction of the transaction node in the transaction operation is realized, and the transaction risk brought by the risk transaction behavior is reduced by reminding business personnel to verify and correct the risk transaction behavior.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (11)
1. A transaction risk prediction method, comprising:
acquiring transaction behavior data;
performing transaction node feature extraction on the transaction behavior data to obtain a first feature data set, wherein the first feature data set comprises: the node name and the node execution sequence of each transaction node;
and performing risk prediction on the first characteristic data set by using the constructed risk assessment model to obtain a risk prediction result.
2. The transaction risk prediction method of claim 1, wherein the risk assessment model is: the method comprises the following steps of training a model obtained based on marked transaction node data in historical transaction node data under different service scenes, wherein the marked transaction node data is transaction node data of a risk label in the historical transaction node data, and the risk label comprises the following components: risk events and non-risk events.
3. The transaction risk prediction method according to claim 2, wherein the risk assessment model is constructed by:
acquiring historical transaction node data under different service scenes;
marking the historical transaction node data according to a normal operation sequence of the service determined based on service rules under different service scenes to obtain marked transaction node data;
performing transaction node feature extraction on the marked transaction node data to obtain a second feature data set;
and training the second characteristic data set to obtain a risk assessment model.
4. The transaction risk prediction method of claim 1, further comprising:
determining a transaction risk monitoring mode according to the risk prediction result, wherein the risk prediction result comprises: the abnormal probability or the risk degree, the transaction risk monitoring mode comprises: prompting and/or intercepting the transaction.
5. The transaction risk prediction method of claim 1, further comprising:
optimizing the risk assessment model based on the first feature dataset and the risk prediction result.
6. A transaction risk prediction device, comprising:
the acquisition unit is used for acquiring transaction behavior data;
an extraction unit, configured to perform transaction node feature extraction on the transaction behavior data to obtain a first feature data set, where the first feature data set includes: the node name and the node execution sequence of each transaction node;
and the prediction unit is used for performing risk prediction on the first characteristic data set by using the constructed risk assessment model to obtain a risk prediction result.
7. The transaction risk prediction device of claim 6, wherein the risk assessment model is: the method comprises the following steps of training a model obtained based on marked transaction node data in historical transaction node data under different service scenes, wherein the marked transaction node data is transaction node data of a risk label in the historical transaction node data, and the risk label comprises the following components: risk events and non-risk events.
8. The transaction risk prediction device of claim 7, further comprising: a model construction unit for constructing the risk assessment model;
the model building unit is specifically configured to:
acquiring historical transaction node data under different service scenes;
marking the historical transaction node data according to a normal operation sequence of the service determined based on service rules under different service scenes to obtain marked transaction node data;
performing transaction node feature extraction on the marked transaction node data to obtain a second feature data set;
and training the second characteristic data set to obtain a risk assessment model.
9. The transaction risk prediction device of claim 6, further comprising:
the monitoring and determining unit is used for determining a transaction risk monitoring mode according to the risk prediction result, and the risk prediction result comprises: the abnormal probability or the risk degree, the transaction risk monitoring mode comprises: prompting and/or intercepting the transaction.
10. The transaction risk prediction device of claim 6, further comprising:
and the optimizing unit is used for optimizing the risk assessment model based on the first characteristic data set and the risk prediction result.
11. A transaction risk prediction system comprising at least one processor and a memory storing computer executable instructions, the processor executing the instructions to carry out the steps of the method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010392844.0A CN111582878A (en) | 2020-05-11 | 2020-05-11 | Transaction risk prediction method, device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010392844.0A CN111582878A (en) | 2020-05-11 | 2020-05-11 | Transaction risk prediction method, device and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111582878A true CN111582878A (en) | 2020-08-25 |
Family
ID=72113296
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010392844.0A Pending CN111582878A (en) | 2020-05-11 | 2020-05-11 | Transaction risk prediction method, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111582878A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111967801A (en) * | 2020-09-23 | 2020-11-20 | 中国建设银行股份有限公司 | Transaction risk prediction method and device |
| CN113052683A (en) * | 2021-04-30 | 2021-06-29 | 中国银行股份有限公司 | Violation prediction method and device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040260602A1 (en) * | 2003-06-19 | 2004-12-23 | Hitachi, Ltd. | System for business service management and method for evaluating service quality of service provider |
| CN109242499A (en) * | 2018-09-19 | 2019-01-18 | 中国银行股份有限公司 | A kind of processing method of transaction risk prediction, apparatus and system |
| CN109543984A (en) * | 2018-11-15 | 2019-03-29 | 上海盛付通电子支付服务有限公司 | Risk control method, device, electronic equipment and medium |
| CN110097451A (en) * | 2019-04-01 | 2019-08-06 | 中国银联股份有限公司 | A kind of monitoring method and device of banking |
| CN110796356A (en) * | 2019-10-22 | 2020-02-14 | 陈华 | Bank counter business monitoring system |
-
2020
- 2020-05-11 CN CN202010392844.0A patent/CN111582878A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040260602A1 (en) * | 2003-06-19 | 2004-12-23 | Hitachi, Ltd. | System for business service management and method for evaluating service quality of service provider |
| CN109242499A (en) * | 2018-09-19 | 2019-01-18 | 中国银行股份有限公司 | A kind of processing method of transaction risk prediction, apparatus and system |
| CN109543984A (en) * | 2018-11-15 | 2019-03-29 | 上海盛付通电子支付服务有限公司 | Risk control method, device, electronic equipment and medium |
| CN110097451A (en) * | 2019-04-01 | 2019-08-06 | 中国银联股份有限公司 | A kind of monitoring method and device of banking |
| CN110796356A (en) * | 2019-10-22 | 2020-02-14 | 陈华 | Bank counter business monitoring system |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111967801A (en) * | 2020-09-23 | 2020-11-20 | 中国建设银行股份有限公司 | Transaction risk prediction method and device |
| CN113052683A (en) * | 2021-04-30 | 2021-06-29 | 中国银行股份有限公司 | Violation prediction method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11783028B2 (en) | Systems and methods for detecting resources responsible for events | |
| CN108596616B (en) | User data authenticity analysis method and device, storage medium and electronic equipment | |
| US20060202012A1 (en) | Secure data processing system, such as a system for detecting fraud and expediting note processing | |
| US11403645B2 (en) | Systems and methods for cross-border ATM fraud detection | |
| US9508057B2 (en) | Automatically updating account information | |
| US20210182850A1 (en) | System and method for assessing a digital interaction with a digital third party account service | |
| US20130185191A1 (en) | Systems and method for correlating transaction events | |
| US20200234307A1 (en) | Systems and methods for detecting periodic patterns in large datasets | |
| CN116128458B (en) | Intelligent automatic auditing system for hospital expense card account reporting | |
| CN111582878A (en) | Transaction risk prediction method, device and system | |
| RU2677384C1 (en) | Way of automatic calculation of the included money in case of failures | |
| CN115836302A (en) | Automatically adjusting rule weights in a profile | |
| US11282135B2 (en) | Onboarding quasi-customers in a disaster zone | |
| US20220138768A1 (en) | Systems and methods for verifying digital payments | |
| US20140089190A1 (en) | Claim rate black box | |
| US20160063404A1 (en) | Universal back office workflow | |
| US11948189B2 (en) | Systems and methods for identifying full account numbers from partial account numbers | |
| US10216830B2 (en) | Multicomputer processing of client device request data using centralized event orchestrator and link discovery engine | |
| CN114546872B (en) | Certificate management testing method and device, computer equipment and storage medium | |
| WO2019168442A1 (en) | Method and system for producing a scoring model | |
| RU2767285C1 (en) | Method and system for automated crediting of funds in case of failures in channel of self-service device at moment of cash deposit | |
| CN112365337B (en) | Method, device, server and storage medium for identifying imposition loan | |
| US20240144728A1 (en) | Fraud detection for signed documents | |
| CN111932368A (en) | Credit card issuing system and construction method and device thereof | |
| EA041491B1 (en) | METHOD AND SYSTEM FOR AUTOMATED CREDIT OF CASH IN THE EVENT OF FAULTS IN THE CHANNEL OF THE SELF-SERVICE DEVICE AT THE TIME OF CASH DEPOSIT |
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 |