CN113052703A - Transaction risk early warning method and device - Google Patents
Transaction risk early warning method and device Download PDFInfo
- Publication number
- CN113052703A CN113052703A CN202110422483.4A CN202110422483A CN113052703A CN 113052703 A CN113052703 A CN 113052703A CN 202110422483 A CN202110422483 A CN 202110422483A CN 113052703 A CN113052703 A CN 113052703A
- Authority
- CN
- China
- Prior art keywords
- transaction
- data
- transaction risk
- risk
- training
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000012549 training Methods 0.000 claims abstract description 85
- 238000013058 risk prediction model Methods 0.000 claims abstract description 80
- 230000009467 reduction Effects 0.000 claims abstract description 51
- 238000012545 processing Methods 0.000 claims abstract description 47
- 238000007781 pre-processing Methods 0.000 claims abstract description 26
- 238000012795 verification Methods 0.000 claims description 41
- 238000004590 computer program Methods 0.000 claims description 19
- 238000012706 support-vector machine Methods 0.000 claims description 10
- 238000010606 normalization Methods 0.000 claims description 4
- 238000000638 solvent extraction Methods 0.000 claims description 3
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000004422 calculation algorithm Methods 0.000 description 20
- 238000010586 diagram Methods 0.000 description 17
- 230000008569 process Effects 0.000 description 9
- 230000000694 effects Effects 0.000 description 8
- 230000008676 import Effects 0.000 description 7
- 230000009471 action Effects 0.000 description 6
- 238000013475 authorization Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000010200 validation analysis Methods 0.000 description 3
- 239000000463 material Substances 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000000513 principal component analysis Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Educational Administration (AREA)
- Technology Law (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a transaction risk early warning method and device, and relates to the technical field of artificial intelligence. The method comprises the following steps: acquiring transaction data; preprocessing the transaction data to obtain transaction characteristic data; performing dimensionality reduction processing on the transaction characteristic data to obtain transaction risk prediction data; obtaining a transaction risk prediction result based on the transaction risk prediction data and a transaction risk prediction model; wherein the transaction risk prediction model is obtained based on transaction risk training data and corresponding risk label training. The device is used for executing the method. The transaction risk early warning method and device provided by the embodiment of the invention improve the accuracy of transaction risk identification.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a transaction risk early warning method and device.
Background
Currently, transactions in the financial market require monitoring and inspection to reduce transaction risk.
Now, for the transaction in the financial market, it is required to be implemented by manually checking the authorization check item. That is, before the transaction flows in, the corresponding authorization check item is checked, and if the check is not passed, the manual review is performed. And then, according to the service requirement, adjusting the authorization check item corresponding to the transaction so as to adapt to different rules and different environments. If the checking items are set too much, a large amount of false alarm information is easily generated, and a large amount of manpower is wasted for screening; if the setting of the checking items is too few, the report missing risk is increased, and the operation risk of the system is increased.
Disclosure of Invention
Aiming at the problems in the prior art, the embodiment of the invention provides a transaction risk early warning method and a transaction risk early warning device, which can at least partially solve the problems in the prior art.
In one aspect, the invention provides a transaction risk early warning method, which includes:
acquiring transaction data;
preprocessing the transaction data to obtain transaction characteristic data;
performing dimensionality reduction processing on the transaction characteristic data to obtain transaction risk prediction data;
obtaining a transaction risk prediction result based on the transaction risk prediction data and a transaction risk prediction model; wherein the transaction risk prediction model is obtained based on transaction risk training data and corresponding risk label training.
In another aspect, the present invention provides a transaction risk early warning device, including:
the acquisition module is used for acquiring transaction data;
the preprocessing module is used for preprocessing the transaction data to obtain transaction characteristic data;
the dimension reduction processing module is used for carrying out dimension reduction processing on the transaction characteristic data to obtain transaction risk prediction data;
the prediction module is used for obtaining a transaction risk prediction result based on the transaction risk prediction data and the transaction risk prediction model; wherein the transaction risk prediction model is obtained based on transaction risk training data and corresponding risk label training.
In another aspect, the present invention provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the computer program to implement the steps of the transaction risk early warning method according to any of the above embodiments.
In yet another aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the steps of the transaction risk pre-warning method according to any of the above embodiments.
The transaction risk early warning method and device provided by the embodiment of the invention can acquire transaction data, preprocess the transaction data to acquire transaction characteristic data, perform dimensionality reduction processing on the transaction characteristic data to acquire transaction risk prediction data, acquire a transaction risk prediction result based on the transaction risk prediction data and a transaction risk prediction model, and predict the risk of the transaction data through the transaction risk prediction model, so that the accuracy of transaction risk identification is improved.
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 some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts. In the drawings:
fig. 1 is a flowchart illustrating a transaction risk early warning method according to an embodiment of the present invention.
Fig. 2 is a flowchart illustrating a transaction risk early warning method according to another embodiment of the present invention.
Fig. 3 is a flowchart illustrating a transaction risk early warning method according to another embodiment of the present invention.
Fig. 4 is a schematic structural diagram of a transaction risk early warning device according to an embodiment of the present invention.
Fig. 5 is a schematic structural diagram of a transaction risk early warning device according to another embodiment of the present invention.
Fig. 6 is a schematic structural diagram of a transaction risk early warning device according to another embodiment of the present invention.
Fig. 7 is a schematic physical structure diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention are further described in detail below with reference to the accompanying drawings. The exemplary embodiments and descriptions of the present invention are provided to explain the present invention, but not to limit the present invention. It should be noted that the embodiments and features of the embodiments in the present application may be arbitrarily combined with each other without conflict.
In order to facilitate understanding of the technical solutions provided in the present application, the following first describes relevant contents of the technical solutions in the present application.
The financial market, also known as the capital market, includes the monetary market and the capital market, is the financing market. The capital fusion refers to the activity of regulating capital surplus by using various financial instruments by capital supply and demand parties in the process of economic operation, and is a general term of all financial transaction activities. Traded on financial markets are various financial instruments such as stocks, bonds, savings slips, etc. Financing is called financing for short, and is generally divided into direct financing and indirect financing. The direct financing is the activity of directly carrying out fund financing by fund supply and demand parties, namely, a fund demander directly finances the institutions and individuals with fund surplus in the society through a financial market; in contrast, indirect financing refers to financing activities performed by banks, that is, financing in a manner that a fund demander applies for loan from a financial intermediary such as a bank. The financial market has direct and profound influence on all aspects of economic activities, such as personal wealth, enterprise operation and economic operation efficiency, which are directly dependent on the activities of the financial market.
Fig. 1 is a schematic flow diagram of a transaction risk early warning method according to an embodiment of the present invention, and as shown in fig. 1, the transaction risk early warning method according to the embodiment of the present invention includes:
s101, acquiring transaction data;
in particular, the server may obtain transaction data, which may be data generated during a transaction in a financial market. The transaction data may include data corresponding to each field, where the field includes, but is not limited to, an import manner, a transaction inflow action, a business category, a trade mark, an amount, a currency, whether to authorize or not to check through a flag, and the like, and is set according to actual needs, which is not limited in the embodiment of the present invention. The execution subject of the transaction risk early warning method provided by the embodiment of the invention includes but is not limited to a server.
S102, preprocessing the transaction data to obtain transaction characteristic data;
specifically, after the server obtains the transaction data, the server preprocesses the transaction data, converts the transaction data into numerical data, and obtains transaction characteristic data. Here, the value such as the amount of money may be normalized. Data such as import mode, transaction inflow action, business class, trading mark, currency, whether authorization check passes identification and the like can be converted into numerical data by one-hot coding and the like. The specific process of converting the transaction data into numerical data is set according to actual needs, and the embodiment of the invention is not limited.
S103, performing dimensionality reduction processing on the transaction characteristic data to obtain transaction risk prediction data;
specifically, after the server obtains the transaction characteristic data, dimension reduction processing can be performed on the transaction characteristic data through a dimension reduction algorithm, so that transaction risk prediction data can be obtained. The dimension reduction algorithm is selected according to actual needs, and the embodiment of the invention is not limited.
For example, the dimension reduction algorithm is one of a Relief algorithm, a Principal Component Analysis (PCA) algorithm, a supervised Linear dimension reduction algorithm (LDA) algorithm, a nonlinear dimension reduction algorithm (LLE) algorithm, and a Laplacian eigenmap algorithm (LE).
S104, obtaining a transaction risk prediction result based on the transaction risk prediction data and the transaction risk prediction model; wherein the transaction risk prediction model is obtained based on transaction risk training data and corresponding risk label training.
Specifically, the server inputs the transaction risk prediction data into a transaction risk prediction model, and a transaction risk prediction result can be output through processing of the transaction risk prediction model. The transaction risk prediction result is at risk or no risk. Wherein the transaction risk prediction model is obtained based on transaction risk training data and corresponding risk label training. And each sample data in the transaction risk training data corresponds to a risk label. The risk label is at risk or no risk.
The transaction risk early warning method provided by the embodiment of the invention can acquire transaction data, preprocesses the transaction data to acquire transaction characteristic data, performs dimensionality reduction processing on the transaction characteristic data to acquire transaction risk prediction data, acquires a transaction risk prediction result based on the transaction risk prediction data and a transaction risk prediction model, and predicts the risk of the transaction data through the transaction risk prediction model, so that the accuracy of transaction risk identification is improved.
Fig. 2 is a schematic flow chart of a transaction risk early warning method according to another embodiment of the present invention, and as shown in fig. 2, the step of obtaining the transaction risk prediction model based on the transaction risk training data and the corresponding risk label training includes:
s201, acquiring transaction risk training data and corresponding risk labels, and dividing the transaction risk training data into a training set and a verification set;
specifically, the server may obtain transaction risk training data through historical transaction data, where the transaction risk training data includes a preset number of pieces of sample data, each piece of sample data corresponds to one risk label, and the risk label is risky or risk-free. The server divides the transaction risk training data into a training set and a validation set, wherein the training set comprises a first quantity of sample data, and the validation set comprises a second quantity of sample data. The preset number is set according to actual needs, and the embodiment of the invention is not limited. The first number and the second number are set according to actual needs, and the embodiment of the invention is not limited.
For example, the transaction risk training data includes 10 ten thousand sample data, 70% of the sample data may be divided into a training set, and the rest of the sample data may be divided into a verification set, that is, the training set includes 7 ten thousand sample data, and the verification set includes 3 ten thousand sample data.
S202, training to obtain an initial transaction risk prediction model based on the training set and the corresponding risk labels and the original model;
specifically, the server inputs the sample data in the training set and the risk label corresponding to each sample data into an original model, trains the original model, and can obtain an initial transaction risk prediction model. The original model may adopt a Support Vector Machine (SVM) model, a neural network model, and the like, and is selected according to actual needs, which is not limited in the embodiments of the present invention.
S203, verifying the initial transaction risk prediction model based on the verification set and the corresponding risk label;
specifically, after the server trains and obtains the initial transaction risk prediction model, the effect of the initial transaction risk prediction model can be verified through a verification set and corresponding risk labels. Inputting each sample data of the verification set into the initial transaction risk prediction model to obtain an output result corresponding to each sample data, and verifying the initial transaction risk prediction model based on the output result of each sample data in the verification set and the risk label corresponding to each sample data to obtain a verification result, wherein the verification result is passed or failed.
For example, the initial transaction risk prediction model is verified based on an accuracy rate, the server may count the number of output results corresponding to each sample data of the verification set that is the same as the number of risk labels corresponding to each sample data, if the number of sample data of which the output results are the same as the number of risk labels is a, the total amount of sample data included in the verification set is Q, then the accuracy rate r of the initial transaction risk prediction model is a/Q, and if the accuracy rate r is greater than or equal to an accuracy rate threshold value, then the verification result of the initial transaction risk prediction model is verified; and if the accuracy rate r is smaller than the accuracy rate threshold value, the verification result of the initial transaction risk prediction model is verification failure. The accuracy threshold is set according to actual needs, and the embodiment of the invention is not limited.
And S204, if the initial transaction risk prediction model passes the verification, taking the initial transaction risk prediction model as the transaction risk prediction model.
Specifically, the server may know whether the initial transaction risk prediction model passes verification based on a verification result of the initial transaction risk prediction model, and if the verification result is that the initial transaction risk prediction model passes verification, the server may predict the transaction risk by using the initial transaction risk prediction model as the transaction risk prediction model.
Fig. 3 is a schematic flow chart of a transaction risk early warning method according to another embodiment of the present invention, as shown in fig. 3, based on the foregoing embodiments, further, the acquiring transaction risk training data includes:
s301, acquiring historical transaction data and corresponding risk labels;
specifically, previous transaction data may be collected as historical transaction data, each piece of transaction data in the historical transaction data may correspond to a risk tag, and the risk tag may be manually identified. The server may obtain historical transaction data and corresponding risk tags. The historical transaction data may include data corresponding to different fields, where the fields include, but are not limited to, an import manner, a transaction inflow action, a business category, a trade mark, an amount, a currency, whether to authorize or not to check through a flag, and the like, and are set according to actual needs, which is not limited in the embodiment of the present invention. It will be appreciated that the fields included in the historical transaction data are the same as the fields included in the transaction data.
S302, preprocessing the historical transaction data to obtain historical transaction characteristic data;
specifically, after obtaining the historical transaction data, the server preprocesses the historical transaction data, converts the historical transaction data into numerical data, and obtains historical transaction characteristic data. The specific process of preprocessing the historical transaction data is similar to the process of preprocessing the transaction data in step S102, and is not described herein again.
And S303, performing dimension reduction processing on the historical transaction characteristic data to obtain transaction risk training data.
Specifically, after obtaining the historical transaction characteristic data, the server may perform dimension reduction processing on the historical transaction characteristic data through a dimension reduction algorithm to obtain transaction risk training data. The dimension reduction algorithm is selected according to actual needs, and the embodiment of the invention is not limited. It can be understood that the dimension reduction algorithm used for performing the dimension reduction processing on the historical transaction characteristic data is the same as the dimension reduction algorithm used for performing the dimension reduction processing on the transaction characteristic data. Through dimension reduction processing, noise in historical transaction characteristic data can be removed, data required by subsequent training is reduced, and the efficiency of model training is improved.
On the basis of the above embodiments, further, the original model adopts a support vector machine model.
The support vector machine is a two-classification model, and aims to find a hyperplane to segment a sample, wherein the segmentation principle is interval maximization, and the hyperplane is finally converted into a convex quadratic programming problem to be solved. The models from simple to complex include: (1) when the training samples are linearly separable, learning a linearly separable support vector machine through hard interval maximization; (2) when the training samples are approximately linearly separable, a linear support vector machine is learned through soft interval maximization; (3) when the training samples are linearly infeasible, a nonlinear support vector machine is learned through kernel skills and soft interval maximization. The original model adopts a support vector machine model, is easy to realize, and can improve the training efficiency of the model.
On the basis of the foregoing embodiments, further, the preprocessing the transaction data includes:
and carrying out numerical processing and normalization processing on the transaction data.
Specifically, the server may perform a digitization process and a normalization process on the transaction data in a process of preprocessing the transaction data.
For example, data such as an import method, a transaction inflow operation, a business category, a trade mark, a currency, whether or not to authorize the check, and the like, can be converted into numerical data by a one-hot coding method, and the numerical processing of the transaction data is realized. For numerical values such as money amount, normalization processing can be carried out, data are mapped to the range of 0-1, and subsequent data processing efficiency is improved.
According to the transaction risk early warning method provided by the embodiment of the invention, historical transaction data is preprocessed and subjected to dimension reduction processing, a transaction risk prediction model is obtained through model training, and risk identification of transactions is realized through the transaction risk prediction model. The problem of missing alarm or alarm storm caused by manually setting an authorization check item is solved, and the monitoring is lost after the transaction flows in, so that the labor cost of the service is reduced, the accuracy and effectiveness of transaction risk alarm are improved, and the possible high-calculation risk is reduced.
Fig. 4 is a schematic structural diagram of a transaction risk early warning apparatus according to an embodiment of the present invention, and as shown in fig. 4, the transaction risk early warning apparatus according to the embodiment of the present invention includes an obtaining module 401, a preprocessing module 402, a dimension reduction processing module 403, and a prediction module 404, where:
the obtaining module 401 is configured to obtain transaction data; the preprocessing module 402 is configured to preprocess the transaction data to obtain transaction characteristic data; the dimension reduction processing module 403 is configured to perform dimension reduction processing on the transaction characteristic data to obtain transaction risk prediction data; the prediction module 404 is configured to obtain a transaction risk prediction result based on the transaction risk prediction data and a transaction risk prediction model; wherein the transaction risk prediction model is obtained based on transaction risk training data and corresponding risk label training.
In particular, the acquisition module 401 may acquire transaction data, which may be data generated during a transaction in a financial market. The transaction data may include data corresponding to each field, where the field includes, but is not limited to, an import manner, a transaction inflow action, a business category, a trade mark, an amount, a currency, whether to authorize or not to check through a flag, and the like, and is set according to actual needs, which is not limited in the embodiment of the present invention.
After obtaining the transaction data, the preprocessing module 402 preprocesses the transaction data, converts the transaction data into numerical data, and obtains transaction characteristic data. Here, the value such as the amount of money may be normalized. Data such as import mode, transaction inflow action, business class, trading mark, currency, whether authorization check passes identification and the like can be converted into numerical data by one-hot coding and the like. The specific process of converting the transaction data into numerical data is set according to actual needs, and the embodiment of the invention is not limited.
After obtaining the transaction characteristic data, the dimension reduction processing module 403 may perform dimension reduction processing on the transaction characteristic data through a dimension reduction algorithm to obtain transaction risk prediction data. The dimension reduction algorithm is selected according to actual needs, and the embodiment of the invention is not limited.
The prediction module 404 inputs the transaction risk prediction data into a transaction risk prediction model, and the transaction risk prediction result can be output after the transaction risk prediction model is processed. The transaction risk prediction result is at risk or no risk. Wherein the transaction risk prediction model is obtained based on transaction risk training data and corresponding risk label training. And each sample data in the transaction risk training data corresponds to a risk label. The risk label is at risk or no risk.
The transaction risk early warning device provided by the embodiment of the invention can acquire transaction data, preprocess the transaction data to acquire transaction characteristic data, perform dimensionality reduction processing on the transaction characteristic data to acquire transaction risk prediction data, acquire a transaction risk prediction result based on the transaction risk prediction data and a transaction risk prediction model, and predict the risk of the transaction data through the transaction risk prediction model, so that the accuracy of transaction risk identification is improved.
Fig. 5 is a schematic structural diagram of a transaction risk early warning device according to another embodiment of the present invention, as shown in fig. 5, on the basis of the foregoing embodiments, further, the transaction risk early warning device according to the embodiment of the present invention further includes a dividing module 405, a training module 406, a verification module 407, and a determining module 408, where:
the dividing module 405 is configured to obtain transaction risk training data, and divide the transaction risk training data into a training set and a verification set; the training module 406 is configured to train to obtain an initial transaction risk prediction model based on the training set and the corresponding risk labels and the original model; the verification module 407 is configured to verify the initial transaction risk prediction model based on the verification set and the corresponding risk label; the determining module 408 is configured to use the initial transaction risk prediction model as the transaction risk prediction model after the initial transaction risk prediction model is verified.
Specifically, the partitioning module 405 may obtain transaction risk training data through historical transaction data, where the transaction risk training data includes a preset number of pieces of sample data, each piece of sample data corresponds to a risk label, and the risk label is risky or risk-free. The partitioning module 405 partitions the transaction risk training data into a training set comprising a first number of pieces of sample data and a validation set comprising a second number of pieces of sample data. The preset number is set according to actual needs, and the embodiment of the invention is not limited. The first number and the second number are set according to actual needs, and the embodiment of the invention is not limited.
The training module 406 inputs the sample data in the training set and the risk label corresponding to each sample data into the original model, and trains the original model to obtain an initial transaction risk prediction model. The original model may be an SVM model, a neural network model, or the like, and is selected according to actual needs, which is not limited in the embodiments of the present invention.
After training to obtain the initial transaction risk prediction model, the verification module 407 may verify the effect of the initial transaction risk prediction model through a verification set and corresponding risk labels. Inputting each sample data of the verification set into the initial transaction risk prediction model to obtain an output result corresponding to each sample data, and verifying the initial transaction risk prediction model based on the output result of each sample data in the verification set and the risk label corresponding to each sample data to obtain a verification result, wherein the verification result is passed or failed.
The determining module 408 may obtain whether the initial transaction risk prediction model passes the verification based on the verification result of the initial transaction risk prediction model, and if the verification result is that the initial transaction risk prediction model passes the verification, the determining module 408 may use the initial transaction risk prediction model as the transaction risk prediction model to predict the transaction risk.
Fig. 6 is a schematic structural diagram of a transaction risk early warning apparatus according to another embodiment of the present invention, as shown in fig. 6, on the basis of the foregoing embodiments, further, the dividing module 405 includes an obtaining unit 4051, a preprocessing unit 4052, and a dimension reducing unit 4053, where:
the obtaining unit 4051 is configured to obtain historical transaction data and a corresponding risk label; the preprocessing unit 4052 is configured to preprocess the historical transaction data to obtain historical transaction characteristic data; the dimension reduction unit 4053 is configured to perform dimension reduction processing on the historical transaction characteristic data to obtain transaction risk training data.
Specifically, previous transaction data may be collected as historical transaction data, each piece of transaction data in the historical transaction data may correspond to a risk tag, and the risk tag may be manually identified. The obtaining unit 4051 may obtain historical transaction data and corresponding risk tags. The historical transaction data may include data corresponding to different fields, where the fields include, but are not limited to, an import manner, a transaction inflow action, a business category, a trade mark, an amount, a currency, whether to authorize or not to check through a flag, and the like, and are set according to actual needs, which is not limited in the embodiment of the present invention. It will be appreciated that the fields included in the historical transaction data are the same as the fields included in the transaction data.
After obtaining the historical transaction data, the preprocessing unit 4052 may preprocess the historical transaction data, convert the historical transaction data into numerical data, and obtain historical transaction characteristic data.
After obtaining the historical transaction characteristic data, the dimension reduction unit 4053 may perform dimension reduction processing on the historical transaction characteristic data through a dimension reduction algorithm to obtain transaction risk training data. The dimension reduction algorithm is selected according to actual needs, and the embodiment of the invention is not limited. It can be understood that the dimension reduction algorithm used for performing the dimension reduction processing on the historical transaction characteristic data is the same as the dimension reduction algorithm used for performing the dimension reduction processing on the transaction characteristic data. Through dimension reduction processing, noise in historical transaction characteristic data can be removed, data required by subsequent training is reduced, and the efficiency of model training is improved.
The embodiment of the apparatus provided in the embodiment of the present invention may be specifically configured to execute the processing flows of the above method embodiments, and the functions of the apparatus are not described herein again, and refer to the detailed description of the above method embodiments.
Fig. 7 is a schematic physical structure diagram of an electronic device according to an embodiment of the present invention, and as shown in fig. 7, the electronic device may include: a processor (processor)701, a communication Interface (Communications Interface)702, a memory (memory)703 and a communication bus 704, wherein the processor 701, the communication Interface 702 and the memory 703 complete communication with each other through the communication bus 704. The processor 701 may call logic instructions in the memory 703 to perform the following method: acquiring transaction data; preprocessing the transaction data to obtain transaction characteristic data; performing dimensionality reduction processing on the transaction characteristic data to obtain transaction risk prediction data; obtaining a transaction risk prediction result based on the transaction risk prediction data and a transaction risk prediction model; wherein the transaction risk prediction model is obtained based on transaction risk training data and corresponding risk label training.
In addition, the logic instructions in the memory 703 can be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The present embodiment discloses a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, enable the computer to perform the method provided by the above-mentioned method embodiments, for example, comprising: acquiring transaction data; preprocessing the transaction data to obtain transaction characteristic data; performing dimensionality reduction processing on the transaction characteristic data to obtain transaction risk prediction data; obtaining a transaction risk prediction result based on the transaction risk prediction data and a transaction risk prediction model; wherein the transaction risk prediction model is obtained based on transaction risk training data and corresponding risk label training.
The present embodiment provides a computer-readable storage medium, which stores a computer program, where the computer program causes the computer to execute the method provided by the above method embodiments, for example, the method includes: acquiring transaction data; preprocessing the transaction data to obtain transaction characteristic data; performing dimensionality reduction processing on the transaction characteristic data to obtain transaction risk prediction data; obtaining a transaction risk prediction result based on the transaction risk prediction data and a transaction risk prediction model; wherein the transaction risk prediction model is obtained based on transaction risk training data and corresponding risk label training.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In the description herein, reference to the description of the terms "one embodiment," "a particular embodiment," "some embodiments," "for example," "an example," "a particular example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are only exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. A transaction risk early warning method is characterized by comprising the following steps:
acquiring transaction data;
preprocessing the transaction data to obtain transaction characteristic data;
performing dimensionality reduction processing on the transaction characteristic data to obtain transaction risk prediction data;
obtaining a transaction risk prediction result based on the transaction risk prediction data and a transaction risk prediction model; wherein the transaction risk prediction model is obtained based on transaction risk training data and corresponding risk label training.
2. The method of claim 1, wherein the step of deriving the transaction risk prediction model based on transaction risk training data and corresponding risk label training comprises:
acquiring transaction risk training data, and dividing the transaction risk training data into a training set and a verification set;
training to obtain an initial transaction risk prediction model based on the training set and the corresponding risk labels and the original model;
verifying the initial transaction risk prediction model based on the verification set and the corresponding risk label;
and if the initial transaction risk prediction model passes the verification, taking the initial transaction risk prediction model as the transaction risk prediction model.
3. The method of claim 2, wherein the obtaining transaction risk training data comprises:
acquiring historical transaction data and corresponding risk labels;
preprocessing the historical transaction data to obtain historical transaction characteristic data;
and performing dimension reduction processing on the historical transaction characteristic data to obtain transaction risk training data.
4. The method of claim 2, wherein the original model employs a support vector machine.
5. The method of any of claims 1 to 4, wherein the pre-processing the transaction data comprises:
and carrying out numerical processing and normalization processing on the transaction data.
6. A transaction risk early warning device, comprising:
the acquisition module is used for acquiring transaction data;
the preprocessing module is used for preprocessing the transaction data to obtain transaction characteristic data;
the dimension reduction processing module is used for carrying out dimension reduction processing on the transaction characteristic data to obtain transaction risk prediction data;
the prediction module is used for obtaining a transaction risk prediction result based on the transaction risk prediction data and the transaction risk prediction model; wherein the transaction risk prediction model is obtained based on transaction risk training data and corresponding risk label training.
7. The apparatus of claim 6, further comprising:
the system comprises a dividing module, a verification module and a processing module, wherein the dividing module is used for acquiring transaction risk training data and dividing the transaction risk training data into a training set and a verification set;
the training module is used for training to obtain an initial transaction risk prediction model based on the training set and the corresponding risk labels and the original model;
a verification module for verifying the initial transaction risk prediction model based on the verification set and corresponding risk labels;
and the judging module is used for taking the initial transaction risk prediction model as the transaction risk prediction model after the initial transaction risk prediction model passes verification.
8. The apparatus of claim 7, wherein the partitioning module comprises:
the acquisition unit is used for acquiring historical transaction data and corresponding risk labels;
the preprocessing unit is used for preprocessing the historical transaction data to obtain historical transaction characteristic data;
and the dimension reduction unit is used for carrying out dimension reduction processing on the historical transaction characteristic data to obtain transaction risk training data.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method according to any of claims 1 to 5 are implemented when the computer program is executed by the processor.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110422483.4A CN113052703A (en) | 2021-04-20 | 2021-04-20 | Transaction risk early warning method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110422483.4A CN113052703A (en) | 2021-04-20 | 2021-04-20 | Transaction risk early warning method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113052703A true CN113052703A (en) | 2021-06-29 |
Family
ID=76519720
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110422483.4A Pending CN113052703A (en) | 2021-04-20 | 2021-04-20 | Transaction risk early warning method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113052703A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113837764A (en) * | 2021-09-22 | 2021-12-24 | 平安科技(深圳)有限公司 | Risk early warning method and device, electronic equipment and storage medium |
CN114092097A (en) * | 2021-11-23 | 2022-02-25 | 支付宝(杭州)信息技术有限公司 | Training method of risk recognition model, and transaction risk determination method and device |
CN116703184A (en) * | 2023-08-08 | 2023-09-05 | 中信消费金融有限公司 | Data processing method, data processing device, electronic equipment and readable storage medium |
WO2023246391A1 (en) * | 2022-06-22 | 2023-12-28 | 支付宝(杭州)信息技术有限公司 | Extraction of risk feature description |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160104163A1 (en) * | 2014-10-14 | 2016-04-14 | Jpmorgan Chase Bank, N.A. | ldentifying Potentially Risky Transactions |
CN110633991A (en) * | 2019-09-20 | 2019-12-31 | 阿里巴巴集团控股有限公司 | Risk identification method and device and electronic equipment |
CN110738564A (en) * | 2019-10-16 | 2020-01-31 | 信雅达系统工程股份有限公司 | Post-loan risk assessment method and device and storage medium |
CN112037012A (en) * | 2020-08-14 | 2020-12-04 | 百维金科(上海)信息科技有限公司 | Internet financial credit evaluation method based on PSO-BP neural network |
-
2021
- 2021-04-20 CN CN202110422483.4A patent/CN113052703A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160104163A1 (en) * | 2014-10-14 | 2016-04-14 | Jpmorgan Chase Bank, N.A. | ldentifying Potentially Risky Transactions |
CN110633991A (en) * | 2019-09-20 | 2019-12-31 | 阿里巴巴集团控股有限公司 | Risk identification method and device and electronic equipment |
CN110738564A (en) * | 2019-10-16 | 2020-01-31 | 信雅达系统工程股份有限公司 | Post-loan risk assessment method and device and storage medium |
CN112037012A (en) * | 2020-08-14 | 2020-12-04 | 百维金科(上海)信息科技有限公司 | Internet financial credit evaluation method based on PSO-BP neural network |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113837764A (en) * | 2021-09-22 | 2021-12-24 | 平安科技(深圳)有限公司 | Risk early warning method and device, electronic equipment and storage medium |
CN113837764B (en) * | 2021-09-22 | 2023-07-25 | 平安科技(深圳)有限公司 | Risk early warning method, risk early warning device, electronic equipment and storage medium |
CN114092097A (en) * | 2021-11-23 | 2022-02-25 | 支付宝(杭州)信息技术有限公司 | Training method of risk recognition model, and transaction risk determination method and device |
CN114092097B (en) * | 2021-11-23 | 2024-05-24 | 支付宝(杭州)信息技术有限公司 | Training method of risk identification model, transaction risk determining method and device |
WO2023246391A1 (en) * | 2022-06-22 | 2023-12-28 | 支付宝(杭州)信息技术有限公司 | Extraction of risk feature description |
CN116703184A (en) * | 2023-08-08 | 2023-09-05 | 中信消费金融有限公司 | Data processing method, data processing device, electronic equipment and readable storage medium |
CN116703184B (en) * | 2023-08-08 | 2023-10-20 | 中信消费金融有限公司 | Data processing method, data processing device, electronic equipment and readable storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113052703A (en) | Transaction risk early warning method and device | |
CN110751557B (en) | Abnormal fund transaction behavior analysis method and system based on sequence model | |
CN112862298A (en) | Credit assessment method for user portrait | |
CN111260189B (en) | Risk control method, risk control device, computer system and readable storage medium | |
WO2019021312A1 (en) | An automated system for default probability prediction of loans and method thereof | |
CN111008896A (en) | Financial risk early warning method and device, electronic equipment and storage medium | |
CN110033365A (en) | A kind of loan on personal security approval system and method | |
CN114265967A (en) | Sensitive data security level marking method and device | |
CN111738762A (en) | Method, device, equipment and storage medium for determining recovery price of poor assets | |
CN111476658A (en) | Loan continuous overdue prediction method and device | |
CN110020939B (en) | Device, method and storage medium for establishing default loss rate prediction model | |
CN111429286A (en) | Financial reliability evaluation method, device, equipment and storage medium | |
CN114998002A (en) | Risk operation prediction method and device | |
CN115860889A (en) | Financial loan big data management method and system based on artificial intelligence | |
Zulkifley et al. | A Survey on Stock Market Manipulation Detectors Using Artificial Intelligence. | |
CN114048330A (en) | Risk conduction probability knowledge graph generation method, device, equipment and storage medium | |
CN110362981B (en) | Method and system for judging abnormal behavior based on trusted device fingerprint | |
CN112634048A (en) | Anti-money laundering model training method and device | |
CN110046200B (en) | Text credible model analysis method, equipment and device | |
Zakowska | A New Credit Scoring Model to Reduce Potential Predatory Lending: A Design Science Approach | |
Horvat et al. | Decision tree approach to discovering fraud in leasing agreements | |
CN110264342B (en) | Business auditing method and device based on machine learning | |
Inal | Importance of Fintechs in Digital Age for Turkey and the Role of Information Technologies | |
CN116976408A (en) | Method and device for calibrating predictive scores of two classification machine learning models | |
CN115131138A (en) | Credit assessment method, device, equipment and medium based on enterprise financial stability |
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 |