CN115063145A

CN115063145A - Transaction risk factor prediction method and device, electronic equipment and storage medium

Info

Publication number: CN115063145A
Application number: CN202210732690.4A
Authority: CN
Inventors: 齐可昕; 陈茜茜; 朱佳宁
Original assignee: Industrial and Commercial Bank of China Ltd ICBC
Current assignee: Industrial and Commercial Bank of China Ltd ICBC
Priority date: 2022-06-24
Filing date: 2022-06-24
Publication date: 2022-09-16

Abstract

The disclosure provides a method and a device for predicting transaction risk factors, electronic equipment and a storage medium, which can be applied to the technical field of artificial intelligence and the financial field. The transaction risk factor prediction method comprises the following steps: in response to the received transaction risk factor prediction request, acquiring transaction risk factor prediction parameters corresponding to-be-predicted transaction data in the transaction risk factor prediction request, wherein the transaction risk factor prediction parameters comprise a concentration risk factor, a risk weight and initial sensitivity; inputting the transaction risk factor prediction parameters into a support vector machine module in a trained transaction risk factor prediction model, and outputting an initial transaction risk factor prediction value; and inputting the initial transaction risk factor predicted value into a radial basis function neural network module in the trained transaction risk factor prediction model, and outputting the transaction risk factor predicted value.

Description

Transaction risk factor prediction method and device, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of artificial intelligence technology and the field of finance, and more particularly, to a method and apparatus for predicting a transaction risk factor, an electronic device, a computer-readable storage medium, and a computer program product.

Background

With the development of artificial intelligence technology, the transaction risk factor with the relationship network as the object is optimized and calculated, and a more reliable calculation result of the transaction risk factor can be obtained, so that more persuasive data support is provided for financial decision-making personnel.

In implementing the disclosed concept, the inventors found that there are at least the following problems in the related art: the conventional transaction risk factor prediction method cannot guarantee the prediction accuracy under the environment of a rapidly changing financial market.

Disclosure of Invention

In view of the above, the present disclosure provides a method, an apparatus, an electronic device, a computer-readable storage medium, and a computer program product for predicting a transaction risk factor.

According to one aspect of the present disclosure, there is provided a method for predicting a transaction risk factor, including:

in response to receiving a transaction risk factor prediction request, acquiring transaction risk factor prediction parameters corresponding to transaction data to be predicted in the transaction risk factor prediction request, wherein the transaction risk factor prediction parameters comprise the concentration risk factor, the risk weight and the initial sensitivity;

inputting the transaction risk factor prediction parameters into a support vector machine module in a trained transaction risk factor prediction model, and outputting an initial transaction risk factor prediction value; and

and inputting the initial transaction risk factor predicted value to a radial basis function neural network module in a trained transaction risk factor prediction model, and outputting the transaction risk factor predicted value.

According to an embodiment of the present disclosure, the method for predicting a transaction risk factor further includes:

according to the transaction risk factor predicted value, evaluating the transaction to be predicted corresponding to the transaction data to be predicted to obtain the guarantee fund amount of the transaction to be predicted;

under the condition that the guaranteed amount of money meets a preset early warning condition, outputting prompt information representing that the transaction to be predicted is allowed to be executed; and

and under the condition that the guaranteed amount of money does not meet the preset early warning condition, outputting early warning information representing that the execution of the transaction to be predicted is forbidden.

According to an embodiment of the present disclosure, the training method of the trained transaction risk factor prediction model includes:

extracting training sample data corresponding to sample transaction data from a source database, wherein the training sample data comprises a sample concentration degree risk factor, a sample risk weight, a sample initial sensitivity and a transaction risk factor true value;

inputting the training sample data into a transaction risk factor prediction model, and outputting a sample transaction risk factor prediction value; and

and adjusting the model parameters of the transaction risk factor prediction model by using the sample transaction risk factor predicted value and the actual value of the transaction risk factor to obtain the trained transaction risk factor prediction model.

According to an embodiment of the present disclosure, the transaction risk factor prediction model includes the support vector machine module and the radial basis function neural network module;

the inputting of the training sample data into the transaction risk factor prediction model and the outputting of the sample transaction risk factor prediction value comprise:

inputting the training sample data to the support vector machine module, and outputting an initial sample transaction risk factor predicted value; and

inputting the initial sample transaction risk factor predicted value to the radial basis function neural network module, and outputting the sample transaction risk factor predicted value;

the adjusting the model parameters of the transaction risk factor prediction model by using the sample transaction risk factor prediction value and the transaction risk factor true value to obtain the trained transaction risk factor prediction model comprises:

adjusting the model parameters of the support vector machine module by using the predicted value of the transaction risk factor of the initial sample and the true value of the transaction risk factor to obtain the support vector machine module in the trained transaction risk factor prediction model; and

under the condition that model parameters of a support vector machine module in the trained transaction risk factor prediction model are kept unchanged, model parameters of the radial basis function neural network module are adjusted by using the sample transaction risk factor predicted value and the transaction risk factor real value, and the radial basis function neural network module in the trained transaction risk factor prediction model is obtained.

According to an embodiment of the present disclosure, the radial basis function neural network module in the transaction risk factor prediction model includes an input layer, a hidden layer, and an output layer, and a kernel function of the hidden layer includes a gaussian function.

According to an embodiment of the present disclosure, the adjusting the model parameters of the radial basis function neural network module by using the predicted value of the sample transaction risk factor and the true value of the transaction risk factor to obtain the radial basis function neural network module in the trained transaction risk factor prediction model includes:

determining a central parameter of the kernel function according to an orthogonal least square method, wherein the central parameter comprises the number of central nodes of the hidden layer and a position parameter of the central nodes;

determining a variance parameter of the kernel function according to the central parameter;

determining a weight parameter between the hidden layer and the output layer according to a least mean square algorithm and a gradient descent method;

determining whether the error parameters of the true value of the transaction risk factor and the predicted value of the sample transaction risk factor meet preset conditions according to at least one of the average absolute error, the mean square error, the average absolute percentage error and the root mean square error; and

and determining the model obtained when the error parameters meet preset conditions as a radial basis function neural network module in the trained transaction risk factor prediction model.

According to an embodiment of the present disclosure, the method further includes:

in response to the error parameter not meeting the preset condition, updating the target learning rate of the radial basis function neural network module;

updating the predicted value of the sample transaction risk factor according to the target learning rate; and

and determining an updated error parameter according to the real value of the transaction risk factor and the updated predicted value of the sample risk factor.

According to another aspect of the present disclosure, there is provided a prediction apparatus of a transaction risk factor, including:

the system comprises an acquisition module, a processing module and a display module, wherein the acquisition module is used for responding to a received transaction risk factor prediction request and acquiring transaction risk factor prediction parameters corresponding to transaction data to be predicted in the transaction risk factor prediction request, and the transaction risk factor prediction parameters comprise concentration risk factors, risk weights and initial sensitivity;

the first processing module is used for inputting the transaction risk factor prediction parameters into a support vector machine module in a trained transaction risk factor prediction model and outputting initial transaction risk factor prediction values; and

and the second processing module is used for inputting the initial transaction risk factor predicted value into a radial basis function neural network module in the trained transaction risk factor prediction model and outputting the transaction risk factor predicted value.

According to another aspect of the present disclosure, there is provided an electronic device including:

one or more processors;

a memory to store one or more instructions that,

wherein the one or more instructions, when executed by the one or more processors, cause the one or more processors to implement the method as described above.

According to another aspect of the present disclosure, there is provided a computer-readable storage medium having stored thereon executable instructions that, when executed by a processor, cause the processor to implement the method as described above.

According to another aspect of the present disclosure, there is provided a computer program product comprising computer executable instructions for implementing the method as described above when executed.

According to the embodiment of the disclosure, the transaction risk factor prediction value is obtained by processing the concentration risk factor, the risk weight and the initial sensitivity of the transaction data to be predicted by using a transaction risk factor prediction model comprising a support vector machine and a radial basis function neural network. Through the technical means, the technical problems that the transaction risk factors have historical limitations due to manual calculation in the related technology and the prediction accuracy cannot be guaranteed in the rapidly changing financial market environment are at least partially solved, and the prediction mode of the transaction risk factors is optimized by using the trained transaction risk factor prediction model based on the artificial intelligence technology, so that the prediction efficiency of the transaction risk factors can be improved, and the accuracy of the prediction results of the transaction risk factors can be guaranteed.

Drawings

The above and other objects, features and advantages of the present disclosure will become more apparent from the following description of embodiments of the present disclosure with reference to the accompanying drawings, in which:

FIG. 1 schematically illustrates a system architecture diagram to which a prediction method of transaction risk factors may be applied, according to an embodiment of the disclosure;

FIG. 2 schematically illustrates a flow chart of a method of predicting a transaction risk factor according to an embodiment of the present disclosure;

FIG. 3 schematically illustrates a flow chart of a method of training a transaction risk factor prediction model according to an embodiment of the present disclosure;

FIG. 4 schematically illustrates a flow chart of a method of training a transaction risk factor prediction model according to another embodiment of the present disclosure;

FIG. 5 schematically illustrates a flow chart of a method of determining a transaction risk factor predictive model according to an embodiment of the disclosure;

FIG. 6 schematically illustrates a flow chart of a method of determining whether an error parameter satisfies a preset condition according to an embodiment of the present disclosure;

fig. 7 schematically shows a block diagram of a structure of a prediction apparatus of a transaction risk factor according to an embodiment of the present disclosure;

FIG. 8 is a block diagram schematically illustrating the structure of a training apparatus for a transaction risk factor prediction model according to an embodiment of the present disclosure; and

fig. 9 schematically shows a block diagram of an electronic device adapted to implement a prediction method of a transaction risk factor according to an embodiment of the present disclosure.

Detailed Description

Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It should be understood that the description is illustrative only and is not intended to limit the scope of the present disclosure. In the following detailed description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the disclosure. It may be evident, however, that one or more embodiments may be practiced without these specific details. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present disclosure.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The terms "comprises," "comprising," and the like, as used herein, specify the presence of stated features, steps, operations, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.

All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art unless otherwise defined. It is noted that the terms used herein should be interpreted as having a meaning that is consistent with the context of this specification and should not be interpreted in an idealized or overly formal sense.

Where a convention analogous to "at least one of A, B and C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B and C" would include but not be limited to systems that have a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.). Where a convention analogous to "A, B or at least one of C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B or C" would include but not be limited to systems that have a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.).

In the technical scheme of the disclosure, the acquisition, storage, application and the like of the personal information of the related user all accord with the regulations of related laws and regulations, necessary security measures are taken, and the customs of the public order is not violated.

In the technical scheme of the disclosure, before the personal information of the user is acquired or collected, the authorization or the consent of the user is acquired.

With the development of artificial intelligence technology, the risk factor optimization calculation research taking the relationship network as the object can obtain more reliable risk factor calculation results, thereby providing more persuasive data support for decision-makers.

In the traditional calculation of the initial deposit of the transaction, a plurality of risk factors are involved, and the calculation method of the risk factors is relatively original. In the prior art, a Heston random fluctuation rate model is generally adopted to obtain a historical fluctuation rate, and relevant parameters required for calculating the weighting sensitivity are obtained through simulation under a 99% confidence interval.

However, the parameters obtained by using the Heston model only refer to 10-day historical fluctuation, and actually, the relevant parameters are usually updated once a quarter or half a year, and the Heston model cannot meet the rapidly changing financial market and cannot be frequently and rapidly corrected through the change of historical data risks. And the correction of the related sub-curve correlation and term correlation parameters is generally completed by manual updating of developers from parameter release, parameter correction and calculation of parameters for deposit during production, so that the judgment of the overall trend of financial derivatives is not accurate, and the calculation error of the deposit is easily caused, thereby causing potential credit risk.

In order to at least partially solve the technical problems in the related art, the present disclosure provides a method, an apparatus, an electronic device, and a storage medium for predicting a transaction risk factor, which can be applied to the technical field of artificial intelligence and the financial field. The transaction risk factor prediction method comprises the following steps: in response to the received transaction risk factor prediction request, acquiring transaction risk factor prediction parameters corresponding to-be-predicted transaction data in the transaction risk factor prediction request, wherein the transaction risk factor prediction parameters comprise a concentration risk factor, a risk weight and initial sensitivity; inputting the empirical risk factor prediction parameters corresponding to the transaction data to be predicted into a support vector machine module in a trained transaction risk factor prediction model, and outputting an initial transaction risk factor prediction value; and inputting the initial transaction risk factor predicted value into a radial basis function neural network module in the trained transaction risk factor prediction model, and outputting the transaction risk factor predicted value.

It should be noted that the method and the device for predicting the transaction risk factor provided by the embodiment of the disclosure can be applied to the technical field of artificial intelligence and the financial field, for example, can be applied to risk factor calculation of deposit. The method and the device for predicting the transaction risk factor provided by the embodiment of the disclosure can also be used in any fields except the technical field of artificial intelligence and the financial field, and can be applied to insurance claims. The application fields of the prediction method and the prediction device for the transaction risk factors provided by the embodiment of the disclosure are not limited.

Fig. 1 schematically shows a system architecture diagram to which a prediction method of transaction risk factors may be applied according to an embodiment of the present disclosure. It should be noted that fig. 1 is only an example of a system architecture to which the embodiments of the present disclosure may be applied to help those skilled in the art understand the technical content of the present disclosure, and does not mean that the embodiments of the present disclosure may not be applied to other devices, systems, environments or scenarios.

As shown in fig. 1, a system architecture 100 according to this embodiment may include

terminal devices

101, 102, 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the

terminal devices

101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired and/or wireless communication links, and so forth.

The user may use the

terminal devices

101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. The

terminal devices

101, 102, 103 may have installed thereon various communication client applications, such as a shopping-like application, a web browser application, a search-like application, an instant messaging tool, a mailbox client, and/or social platform software, etc. (by way of example only).

The

terminal devices

101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.

The server 105 may be a server providing various services, such as a background management server (for example only) providing support for websites browsed by users using the

terminal devices

101, 102, 103. The background management server may analyze and perform other processing on the received data such as the user request, and feed back a processing result (e.g., a webpage, information, or data obtained or generated according to the user request) to the terminal device.

It should be noted that the prediction method of the transaction risk factor provided by the embodiment of the present disclosure may be generally executed by the server 105. Accordingly, the prediction device of the transaction risk factor provided by the embodiment of the present disclosure may be generally disposed in the server 105. The transaction risk factor prediction method provided by the embodiment of the present disclosure may also be executed by a server or a server cluster that is different from the server 105 and is capable of communicating with the

terminal devices

101, 102, 103 and/or the server 105. Accordingly, the prediction device of the transaction risk factor provided by the embodiment of the present disclosure may also be disposed in a server or a server cluster different from the server 105 and capable of communicating with the

terminal devices

101, 102, 103 and/or the server 105. Alternatively, the prediction method of the transaction risk factor provided by the embodiment of the present disclosure may also be executed by the

terminal device

101, 102, or 103, or may also be executed by another terminal device different from the

terminal device

101, 102, or 103. Accordingly, the prediction device of the transaction risk factor provided by the embodiment of the present disclosure may also be disposed in the

terminal device

101, 102, or 103, or in another terminal device different from the

terminal device

101, 102, or 103.

For example, the training sample data and/or the transaction risk factor prediction parameters may be originally stored in any of the

terminal devices

101, 102, or 103 (e.g., the terminal device 101, but not limited thereto), or stored on an external storage device and may be imported into the terminal device 101. Then, the terminal device 101 may locally perform the prediction method of the transaction risk factor provided by the embodiment of the present disclosure, or send the training sample data and/or the prediction parameter of the transaction risk factor to another terminal device, a server, or a server cluster, and perform the prediction method of the transaction risk factor provided by the embodiment of the present disclosure by another terminal device, a server, or a server cluster that receives the training sample data and/or the prediction parameter of the transaction risk factor.

It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

Fig. 2 schematically shows a flow chart of a method of predicting a transaction risk factor according to an embodiment of the present disclosure.

As shown in fig. 2, the method for predicting a transaction risk factor includes operations S201 to S203.

In operation S201, in response to receiving the transaction risk factor prediction request, a transaction risk factor prediction parameter corresponding to the transaction data to be predicted in the transaction risk factor prediction request is obtained. The transaction risk factor prediction parameters include a concentration risk factor, a risk weight, and an initial sensitivity.

In operation S202, the transaction risk factor prediction parameter is input to the support vector machine module in the trained transaction risk factor prediction model, and an initial transaction risk factor prediction value is output.

In operation S203, the initial transaction risk factor prediction value is input to the radial basis function neural network module in the trained transaction risk factor prediction model, and the transaction risk factor prediction value is output.

According to the embodiment of the disclosure, the transaction risk factor prediction request may be a request message sent to the server through the client when the user initiates a transaction to be predicted. The transaction risk factor prediction request may include transaction data to be predicted corresponding to a transaction to be predicted.

According to embodiments of the present disclosure, financial instruments may include financial assets such as stocks, futures, gold, foreign exchange, and insurance policies that can be traded in a financial market. The transaction data to be predicted may include written proofs that demonstrate the financial instrument's ability to negotiate a monetary surplus between a lender and a borrower, for example, the transaction data to be predicted may include a transaction amount and transaction conditions, and the like.

According to the embodiment of the disclosure, the transaction risk factor prediction parameter corresponding to the transaction data to be predicted can be obtained through calculation according to the transaction data to be predicted.

According to the embodiment of the disclosure, the initial transaction risk factor prediction value can be obtained by calculating the transaction data to be predicted according to a formula and the like. The initial transaction risk factor predicted value can also be obtained by processing transaction data to be predicted based on a machine learning method.

For example, a support vector machine module in the trained transaction risk factor prediction model may be utilized to process the concentration risk factor of the transaction data to be predicted, the risk weight of the transaction data to be predicted, and the initial sensitivity of the transaction data to be predicted, so as to obtain an initial transaction risk factor prediction value.

According to the embodiment of the disclosure, the initial transaction risk factor predicted value can be processed by using the radial basis function neural network module in the trained transaction risk factor prediction model, so as to obtain the transaction risk factor predicted value.

According to the embodiment of the disclosure, the transaction risk factor predicted value is the fitting value of the weighting sensitivity K, and the fitting value can be substituted into the risk type inter-currency polymerization formula to obtain the Delta mode deposit amount.

The method shown in fig. 2 is further described with reference to fig. 3-6 in conjunction with specific embodiments.

According to an embodiment of the present disclosure, the method for predicting a transaction risk factor may further include the following operations.

And evaluating the transaction to be predicted corresponding to the transaction data to be predicted according to the transaction risk factor predicted value to obtain the guarantee fund amount of the transaction to be predicted. And under the condition that the fund limit meets the preset early warning condition, outputting prompt information representing that the transaction to be predicted is allowed to be executed. And under the condition that the guarantee fund limit does not meet the preset early warning condition, outputting early warning information representing that the execution of the transaction to be predicted is forbidden.

According to the embodiment of the disclosure, the transaction risk factor predicted value can be substituted into the currency aggregation formula of the risk type, so that the transaction to be predicted corresponding to the transaction data to be predicted can be evaluated conveniently, and the guarantee fund amount in the Delta mode can be obtained.

According to the embodiment of the disclosure, the specific content of the preset early warning condition can be flexibly set by a person skilled in the art according to the actual application situation, and the embodiment of the disclosure does not limit the specific content of the preset early warning condition.

For example, the preset pre-warning condition may include being greater than a preset threshold. Under the condition, under the condition that the guarantee fund amount meets the preset early warning condition, namely the guarantee fund amount is larger than the preset threshold value, prompt information can be output and can be used for representing that the transaction to be predicted is allowed to be executed. Under the condition that the guarantee fund limit does not meet the preset early warning condition, namely the guarantee fund limit is smaller than or equal to the preset threshold value, the early warning information can be output and can be used for representing that the execution of the transaction to be predicted is forbidden.

According to the embodiment of the disclosure, by using the transaction risk factor predicted value for the evaluation of the deposit amount, since the transaction risk factor predicted value is output via the trained transaction risk factor prediction model, the evaluation accuracy of the deposit amount is improved. In addition, the output information is determined according to the relation between the obtained guarantee fund amount of the transaction to be predicted and the preset early warning condition, so that the output information can indicate whether the transaction to be predicted can be executed by related personnel, and the safety of the transaction is guaranteed.

Fig. 3 schematically shows a flow chart of a training method of a transaction risk factor prediction model according to an embodiment of the present disclosure.

As shown in fig. 3, the training method of the prediction model of transaction risk factors includes operations S301 to S303.

In operation S301, training sample data corresponding to the sample transaction data is extracted from the source database, where the training sample data includes a sample concentration degree risk factor, a sample risk weight, a sample initial sensitivity, and a true value of the transaction risk factor.

According to the embodiment of the disclosure, training sample data corresponding to sample transaction data can be stored in a source database in a persistent mode, and when a prediction model of a transaction risk factor is trained, the training sample data can be trained from the source database in a mode of calling a source database interface.

According to an embodiment of the present disclosure, the option deposit mode may include a legacy mode, a Delta mode, and a Span mode. Sensitivity S (i, r) of financial instrument i with respect to the term t of risk-free curve r in Delta-mode guarantees _t ) Can be defined as:

S(i，r _t )＝V _i (r _t +1bp，CS _t )-V _i (r _t ，CS _t ) (1)

wherein, S (i, r) _t ) Sensitivity of financial instrument i relative to risk factor rt; r is _t Representing risk free interest rate at time t; CS _t Represents the credit difference at the time of the deadline t; v _i Representing the market value of financial instrument i as a function of the risk-free interest rate and the credit difference curve; 1bp represents 1 base point and may comprise 0.0001 or 0.01%.

According to an embodiment of the present disclosure, each set of training sample data may include a sample concentration risk factor CR, a sample risk weight W _K And sample initial sensitivity S _k，i 。

In operation S302, training sample data is input to the transaction risk factor prediction model, and a sample transaction risk factor prediction value is output.

According to the embodiment of the disclosure, the predicted value of the sample transaction risk factor can be obtained by calculating the training sample data according to a formula and the like. The sample transaction risk factor predicted value can be obtained by processing training sample data based on a machine learning method.

According to an embodiment of the present disclosure, the transaction risk factor prediction model may be a model constructed based on different machine learning methods.

In operation S303, the model parameters of the transaction risk factor prediction model are adjusted by using the predicted value of the sample transaction risk factor and the true value of the transaction risk factor, so as to obtain a trained transaction risk factor prediction model.

According to the embodiment of the disclosure, training sample data is processed by using the transaction risk factor prediction model, a sample transaction risk factor prediction value is output, and then the model parameters of the transaction risk factor prediction model are adjusted by using the sample transaction risk factor prediction value and a corresponding transaction risk factor true value to obtain a trained transaction risk factor prediction model. By the technical means, the adaptability, the calculation efficiency and the calculation accuracy of the transaction risk factor are improved.

Fig. 4 schematically shows a flow chart of a training method of a transaction risk factor prediction model according to another embodiment of the present disclosure.

According to an embodiment of the present disclosure, a transaction risk factor prediction model includes a support vector machine module and a radial basis function neural network module.

According to an embodiment of the present disclosure, inputting training sample data to the transaction risk factor prediction model, and outputting a sample transaction risk factor prediction value may include the following operations.

And inputting the training sample data to a support vector machine module, and outputting the predicted value of the transaction risk factor of the initial sample. And inputting the initial sample transaction risk factor predicted value to the radial basis function neural network module, and outputting the sample transaction risk factor predicted value.

According to an embodiment of the present disclosure, adjusting model parameters of the transaction risk factor prediction model using the sample transaction risk factor predicted value and the transaction risk factor true value to obtain the trained transaction risk factor prediction model may include the following operations.

And adjusting the model parameters of the support vector machine module by using the predicted value of the transaction risk factor and the true value of the transaction risk factor of the initial sample to obtain the support vector machine module in the trained transaction risk factor prediction model. Under the condition that the model parameters of the support vector machine module in the trained transaction risk factor prediction model are kept unchanged, the model parameters of the radial basis function neural network module are adjusted by using the sample transaction risk factor predicted value and the transaction risk factor true value, and the radial basis function neural network module in the trained transaction risk factor prediction model is obtained.

According to the embodiment of the disclosure, a first output value can be obtained by using the initial sample transaction risk factor predicted value and the transaction risk factor true value based on the first loss function. And adjusting the model parameters of the support vector machine module according to the first output value until a preset condition is met. And determining the support vector machine module obtained under the condition that the preset condition is met as the support vector machine module in the trained transaction risk factor prediction model. The specific form of the first loss function may be set by a worker in the art according to actual needs, and the embodiment of the present disclosure is not limited thereto.

According to the embodiment of the disclosure, a second output value can be obtained by using the sample transaction risk factor predicted value and the transaction risk factor true value based on the second loss function. And adjusting the model parameters of the radial basis function neural network module according to the second output value until a preset condition is met. And determining the radial basis function neural network module obtained under the condition that the preset condition is met as the radial basis function neural network module in the trained transaction risk factor prediction model. The specific form of the second loss function can be set by a worker in the art according to actual needs, and the embodiment of the present disclosure does not limit this.

According to the embodiment of the disclosure, a Support Vector Machine (SVM) is a Machine learning method developed on the basis of a statistical learning theory, and can be used for solving the learning rule of a small sample. The SVM avoids the traditional process from induction to deduction, realizes high-efficiency conducted reasoning from a training sample to a prediction sample, simplifies the conventional classification and regression and other problems, well solves the problems of small samples, nonlinearity, overfitting, local minimum and the like, and has the advantages of complete mathematical theory, good global optimization performance, strong generalization capability, independence of algorithm complexity and feature space dimension and the like.

According to the embodiment of the disclosure, the true value of the transaction risk factor can be obtained by calculating the training sample data according to a formula and the like.

According to embodiments of the present disclosure, for each sample risk factor (k, i), a sample concentration risk factor CR and a sample risk weight RW of the sample risk factor k may be utilized _K Weighting to sample initial sensitivity S _k，i ：

WS _k，i ＝RW _K S _k，i CR (2)

Wherein WS _k，i The weight representing the net sensitivity of the sample risk weight to the sample may be referred to simply as the sample weighted sensitivity.

According to an embodiment of the disclosure, K may represent pair WS _k，i For further aggregation, the original service calculation formula of the sample weighted sensitivity K may be:

according to an embodiment of the present disclosure, the obtained WS _k，i Reference samples as support vector machine modules

Sensitivity squared by sample weight ² As a dependent variable f (x) of the support vector machine module, establishing the support vector machine module for the square of the weighted sensitivity of the sample:

K ² ＝f(x)＝wφ(x)+b (4)

wherein w and b represent coefficients of a maximum split plane;

representation of the dependence phi for modeling a sub-curve _i，j And a term dependence parameter ρ _k，l The weight vector of (2).

According to the embodiment of the disclosure, an optimization function can be adopted to optimize the target value of the support vector machine module:

wherein C represents a constant; xi _i ^* Representing the original slack variable before a certain iteration; xi _i Representing the slack variable after a certain iteration.

According to the embodiment of the present disclosure, the above optimization problem can be converted into a convex quadratic optimization problem by introducing lagrange multipliers:

wherein alpha is ^* And gamma ^* Is constant and represents the original value before a certain iteration, 0 < alpha ^* ，γ ^* < C; α and γ are variables representing values after a certain iteration, 0 < α, γ < C.

According to the embodiment of the disclosure, the fitting value of the weighted sensitivity can be obtained by solving the optimized convex quadratic optimization problem

The risk factor prediction value can be traded as an initial sample.

According to the embodiment of the disclosure, a series of initial transaction risk factor predicted values having errors with the true values of the transaction risk factors can be obtained by inputting training sample data to the support vector machine module in the risk factor prediction model.

According to the embodiment of the disclosure, the initial transaction risk factor predicted value can be used as an input sample, the transaction risk factor real value can be used as an output sample, the neural network model is trained, and the weight and the threshold of a series of nodes can be obtained and used for simulating the deviation relation between the initial transaction risk factor predicted value and the transaction risk factor real value and the mutual relation between the sequences.

According to the embodiment of the disclosure, the predicted value of the support vector machine module at the next moment or the predicted values at a plurality of moments can be used as the input of the neural network model, and the final predicted value at the next moment or a plurality of moments can be used as the output of the neural network model.

According to an embodiment of the present disclosure, the neural network model may include a radial basis function neural network module. The local approximation capability of the radial basis function neural network enables the neural network to approximate any continuous function with arbitrary accuracy.

According to the embodiment of the disclosure, the initial sample transaction risk factor predicted value obtained by the support vector machine module can be used as an input parameter of the radial basis function neural network module.

According to the embodiment of the disclosure, the support vector machine module and the radial basis function neural network module can be utilized for combination and prediction, so that a more optimized transaction risk factor prediction result is obtained, and calculation of the deposit is optimized.

As shown in fig. 4, the transaction risk factor prediction model 402 may include a support vector machine module 402_1 and a radial basis function neural network module 402_ 2.

In the training process of the transaction risk factor prediction model, the training sample data 401 may be input to the support vector machine module 402_1, and the initial sample transaction risk factor prediction value 403 may be output. The initial sample transaction risk factor prediction value 403 is input to the radial basis function neural network module 402_2, and a sample transaction risk factor prediction value 404 is output.

And adjusting the model parameters of the support vector machine module 402_1 by using the predicted value 403 of the transaction risk factor of the initial sample and the true value 405 of the transaction risk factor to obtain the support vector machine module in the trained transaction risk factor prediction model.

Under the condition that model parameters of a support vector machine module in the trained transaction risk factor prediction model are kept unchanged, model parameters of the radial basis function neural network module 402_2 are adjusted by using the sample transaction risk factor predicted value 404 and the transaction risk factor true value 405, and the radial basis function neural network module in the trained transaction risk factor prediction model is obtained.

According to the embodiment of the disclosure, the model parameters of the radial basis function neural network module are adjusted by using the predicted value of the sample transaction risk factor and the true value of the transaction risk factor under the condition of keeping the model parameters of the trained support vector machine module unchanged, so that the radial basis function neural network module in the trained transaction risk factor prediction model is obtained. Therefore, the trained transaction risk factor prediction model is obtained, and the combined model comprises the trained support vector machine module and the trained radial basis function neural network module, so that the deviation between the transaction risk factor predicted value and the transaction risk factor true value can be reduced, and a better fitting result can be obtained, so that the efficiency and the accuracy of the transaction risk factor prediction can be improved.

Fig. 5 schematically illustrates a flow chart of a method of determining a transaction risk factor predictive model according to an embodiment of the disclosure.

As shown in fig. 5, the method of determining a transaction risk factor prediction model includes operations S501 to S505.

In operation S501, a center parameter of a kernel function is determined according to an orthogonal least square method, where the center parameter includes a number of center nodes of a hidden layer and a position parameter of the center nodes.

According to the embodiment of the disclosure, the radial basis function neural network module in the transaction risk factor prediction model comprises an input layer, a hidden layer and an output layer, wherein the kernel function of the hidden layer comprises a Gaussian function.

According to the embodiment of the present disclosure, since a Gaussian (Gaussian) function monotonically decreases from the center to both sides, the response of the function is locally limited, and more realistic features can be obtained. Thus, a gaussian function may be selected as the radial basis function of the radial basis function neural network:

according to an embodiment of the present disclosure, the method of determining the center parameter of the kernel function may include a fixed center method, a self-organizing selection method, a supervised center selection method, and the like.

According to the embodiment of the disclosure, the fixed center method can randomly select a center from a training sample data set, and is suitable for the case that the distribution of training data is representative, and the disadvantage is that the network performance is not ideal or the network size is too large.

According to an embodiment of the present disclosure, the self-organizing selection method may include a K-means clustering method, by clustering a training sample data set, and taking a center of the cluster as a center of a network. The K-means clustering method has the advantages that the center of the radial basis function neural network can be set as an important data point, and the defect that the final prediction result can be a local optimal solution if the center of the initial clustering is accurate.

According to an embodiment of the present disclosure, a supervised central selection method requires determining a cost function in a network learning process, and the determination process of the center is a process for minimizing the cost function.

According to the embodiment of the disclosure, the method for determining the central parameter of the kernel function may further include an orthogonal least square method, and the accuracy of the output prediction value of the radial basis function neural network module may be improved through training.

In operation S502, a variance parameter of the kernel function is determined according to the center parameter.

According to the embodiment of the disclosure, the number of nodes of the hidden layer of the radial basis function neural network can be determined firstly, the central parameter c is determined by using the orthogonal least square method, and the variance delta is calculated ² 。

In operation S503, a weight parameter between the hidden layer and the output layer is determined according to a least mean square algorithm and a gradient descent method.

According to the embodiment of the disclosure, the weight calculation can be performed through a least mean square algorithm, and the network learning can be performed through a gradient descent method. The gradient descent method may gradually adjust the weights in a direction opposite to the gradient of the objective function to find an optimal value of the weights to optimize the network. The process of adjusting the weights can be expressed as:

in operation S504, it is determined whether the error parameter of the true value of the transaction risk factor and the predicted value of the sample transaction risk factor satisfies a preset condition according to at least one of the mean absolute error, the mean square error, the mean absolute percentage error, and the root mean square error.

According to embodiments of the present disclosure, the error parameter may be determined using a variety of error evaluation methods. The error evaluation method may include Mean Absolute Error (MAE), Mean Square Error (MSE), Mean Absolute Percentage Error (MAPE), Root Mean Square Error (RMSE), and the like, and the calculation method of each error evaluation method is as follows:

wherein N represents the number of samples; x is the number of _i Representing the true value of the risk factor;

representing the risk factor prediction value.

According to the embodiment of the disclosure, a plurality of error evaluation methods are adopted in the fitting process, so that a better fitting result can be obtained, and the problem of data blind spots caused by using a single error evaluation method is prevented.

In operation S505, the model obtained when the error parameter satisfies the preset condition is determined as a radial basis function neural network module in the trained transaction risk factor prediction model.

According to the embodiment of the disclosure, the central parameter and the variance parameter of the kernel function are determined by using an orthogonal least square method, the weight parameter between the hidden layer and the output layer is determined by using a least mean square algorithm and a gradient descent method, and the error parameter analysis is performed on the true value of the transaction risk factor and the predicted value of the sample transaction risk factor, so that the optimal value of the weight parameter can be obtained, a better fitting result is obtained, and the prediction accuracy of the transaction risk factor is improved.

Fig. 6 schematically illustrates a flowchart of a method of determining whether an error parameter satisfies a preset condition according to an embodiment of the present disclosure.

As shown in fig. 6, the method of determining whether the error parameter satisfies the preset condition includes operations S601 to S603.

In operation S601, in response to the error parameter not satisfying the preset condition, the target learning rate of the radial basis function neural network module is updated.

In operation S602, the sample transaction risk factor prediction value is updated according to the target learning rate.

In operation S603, an updated error parameter is determined according to the true value of the transaction risk factor and the updated predicted value of the sample transaction risk factor.

According to the embodiment of the disclosure, in the use of the radial basis function neural network, the learning rate is usually artificially set to a fixed value and is kept unchanged in the whole network learning process. However, if the learning rate is set too large, although the convergence rate of the network can be increased, the network may be unstable or even unable to learn; if the learning rate is set to be too small, the network convergence speed is slow, a large amount of calculation time is consumed, and the aging requirement of practical application cannot be met.

According to the embodiment of the disclosure, a dynamic optimal learning rate is provided, by which a target learning rate of a radial basis function neural network module can be updated, so that the target learning rate is applicable to each step of iterative learning of a network.

According to embodiments of the present disclosure, the following model may be established:

wherein, phi (| | x-c) _i | |) represents a gaussian function; omega _i Representing the connection weight.

Based on the above model, the cost function of the t-th time can be obtained, namely:

wherein e (t) ═ e (t-1) - η (t) Φ ^T e (t-1) representing an output error; η (t) represents the learning rate; phi represents a matrix constructed from the input samples; phi ^T Representing the transposed matrix of phi.

The cost function can be regarded as a function of the learning rate, and the optimal value of the learning rate can be obtained by minimization, and the second-order condition is as follows:

based on the above conditions, the dynamic optimal learning rate η can be obtained ^* (t) is:

according to an embodiment of the present disclosure, the learning precision rmse may be set ^* And maximum number of iterations max of the network learning _t (ii) a The initial connection weight ω from the hidden layer to the output layer can be set ₀ Calculating the network output value

Calculating the root mean square error rmse of the actual output value and the network output value; the variance δ can be calculated from the central parameter c ² And the matrix phi is solved.

According to embodiments of the present disclosure, it may be determined that rmse < rmse ^* Whether it is true, or whether the maximum number of iterations max has been reached _t If one of the two is true, the network learning can be completed; if both are not true, the target learning rate can be obtained by calculating the dynamic optimum learning rate by equation (16).

According to an embodiment of the present disclosure, a network output value may be updated according to a target learning rate

And updating the root mean square error rmse between the actual output value and the network output value, and then outputting the final root mean square error rmse and the network outputValue of

And calculating the final number of iterations.

According to the embodiment of the disclosure, when the error parameter does not meet the preset condition, the target learning rate of the radial basis function neural network module is updated, and the sample transaction risk factor prediction value is updated according to the updated target learning rate. By the technical means, the learning rate can be optimized and calculated in each iteration step, and the dynamic optimal learning rate can be obtained in real time, so that the convergence speed of the network can be considered while the stable learning of the radial basis function neural network is ensured, and the operation efficiency of the network is improved.

Fig. 7 schematically shows a block diagram of a structure of a prediction apparatus of a transaction risk factor according to an embodiment of the present disclosure.

As shown in fig. 7, the prediction apparatus 700 for transaction risk factor includes a first obtaining module 701, a first processing module 702 and a second processing module 703.

The first obtaining module 701 is configured to, in response to receiving a transaction risk factor prediction request, obtain a transaction risk factor prediction parameter corresponding to transaction data to be predicted in the transaction risk factor prediction request, where the transaction risk factor prediction parameter includes a concentration risk factor, a risk weight, and an initial sensitivity.

The first processing module 702 is configured to input the transaction risk factor prediction parameter into a support vector machine module in the trained transaction risk factor prediction model, and output an initial transaction risk factor prediction value.

The second processing module 703 is configured to input the initial transaction risk factor predicted value to the radial basis function neural network module in the trained transaction risk factor prediction model, and output the transaction risk factor predicted value.

According to an embodiment of the present disclosure, the prediction apparatus 700 of transaction risk factors may further include an evaluation module, a first output module, and a second output module.

And the evaluation module is used for evaluating the transaction to be predicted corresponding to the transaction data to be predicted according to the transaction risk factor predicted value to obtain the guarantee fund amount of the transaction to be predicted.

And the first output module is used for outputting prompt information representing that the transaction to be predicted is allowed to be executed under the condition that the fund limit meets the preset early warning condition.

And the second output module is used for outputting the early warning information representing that the execution of the transaction to be predicted is forbidden under the condition that the guarantee fund limit does not meet the preset early warning condition.

Fig. 8 schematically shows a block diagram of a training apparatus of a transaction risk factor prediction model according to an embodiment of the present disclosure.

As shown in fig. 8, the training device 800 of the transaction risk factor prediction model includes a second obtaining module 801, a third processing module 802 and a first training module 803.

A second obtaining module 801, configured to extract training sample data corresponding to the sample transaction data from the source database, where the training sample data includes a sample concentration risk factor, a sample risk weight, and a sample initial sensitivity.

The third processing module 802 inputs the training sample data to the transaction risk factor prediction model and outputs the sample transaction risk factor prediction value.

And the training module 803 is configured to adjust model parameters of the transaction risk factor prediction model by using the sample transaction risk factor predicted value and the transaction risk factor true value, so as to obtain a trained transaction risk factor prediction model.

According to an embodiment of the present disclosure, the third processing module 802 includes a first processing unit and a second processing unit.

And the first processing unit is used for inputting the training sample data to the support vector machine module and outputting the predicted value of the transaction risk factor of the initial sample.

And the second processing unit is used for inputting the initial sample transaction risk factor predicted value to the radial basis function neural network module and outputting the sample transaction risk factor predicted value.

According to an embodiment of the present disclosure, the training module 803 includes a first adjustment unit and a second adjustment unit.

And the first adjusting unit is used for adjusting the model parameters of the support vector machine module by utilizing the predicted value of the transaction risk factor and the true value of the transaction risk factor of the initial sample to obtain the support vector machine module in the trained transaction risk factor prediction model.

And the second adjusting unit is used for adjusting the model parameters of the radial basis function neural network module by utilizing the predicted value of the sample transaction risk factor and the true value of the transaction risk factor under the condition of keeping the model parameters of the support vector machine module in the trained transaction risk factor prediction model unchanged, so as to obtain the radial basis function neural network module in the trained transaction risk factor prediction model.

According to an embodiment of the present disclosure, the second adjusting unit includes a first determining subunit, a second determining subunit, a third determining subunit, a fourth determining subunit, and a fifth determining subunit.

The first determining subunit is configured to determine a central parameter of the kernel function according to an orthogonal least square method, where the central parameter includes the number of central nodes of the hidden layer and a position parameter of the central node.

And the second determining subunit is used for determining the variance parameter of the kernel function according to the central parameter.

And the third determining subunit is used for determining the weight parameter between the hidden layer and the output layer according to a least mean square algorithm and a gradient descent method.

And the fourth determining subunit is used for determining whether the error parameters of the real transaction risk factor value and the predicted transaction risk factor value of the sample meet the preset conditions according to at least one of the average absolute error, the mean square error, the average absolute percentage error and the root mean square error.

And the fifth determining subunit is used for determining the model obtained when the error parameter meets the preset condition as the radial basis function neural network module in the trained transaction risk factor prediction model.

According to an embodiment of the present disclosure, the second adjusting unit may further include a first updating subunit, a second updating subunit, and a first determining subunit.

And the first updating subunit is used for responding to the error parameter not meeting the preset condition and updating the target learning rate of the radial basis function neural network module.

And the second updating subunit is used for updating the sample transaction risk factor predicted value according to the target learning rate.

And the sixth determining subunit is used for determining the updated error parameter according to the real transaction risk factor value and the updated sample transaction risk factor predicted value.

Any number of modules, sub-modules, units, sub-units, or at least part of the functionality of any number thereof according to embodiments of the present disclosure may be implemented in one module. Any one or more of the modules, sub-modules, units, and sub-units according to the embodiments of the present disclosure may be implemented by being split into a plurality of modules. Any one or more of the modules, sub-modules, units, sub-units according to embodiments of the present disclosure may be implemented at least in part as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or may be implemented in any other reasonable manner of hardware or firmware by integrating or packaging a circuit, or in any one of or a suitable combination of software, hardware, and firmware implementations. Alternatively, one or more of the modules, sub-modules, units, sub-units according to embodiments of the disclosure may be at least partially implemented as a computer program module, which when executed may perform the corresponding functions.

For example, any plurality of the first obtaining module 701, the first processing module 702, the second processing module 703, the second obtaining module 801, the third processing module 802, and the training module 803 may be combined and implemented in one module/unit/sub-unit, or any one module/unit/sub-unit thereof may be split into a plurality of modules/units/sub-units. Alternatively, at least part of the functionality of one or more of these modules/units/sub-units may be combined with at least part of the functionality of other modules/units/sub-units and implemented in one module/unit/sub-unit. According to the embodiment of the present disclosure, at least one of the first obtaining module 701, the first processing module 702, the second processing module 703, the second obtaining module 801, the third processing module 802, and the training module 803 may be at least partially implemented as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or may be implemented by hardware or firmware in any other reasonable manner of integrating or packaging a circuit, or implemented by any one of three implementations of software, hardware, and firmware, or by a suitable combination of any several of them. Alternatively, at least one of the first obtaining module 701, the first processing module 702, the second processing module 703, the second obtaining module 801, the third processing module 802 and the training module 803 may be at least partially implemented as a computer program module, which when executed, may perform a corresponding function.

It should be noted that, the prediction device portion of the transaction risk factor in the embodiment of the present disclosure corresponds to the prediction method portion of the transaction risk factor in the embodiment of the present disclosure, and the description of the prediction device portion of the transaction risk factor specifically refers to the prediction method portion of the transaction risk factor, which is not described herein again. The training device part of the transaction risk factor prediction model in the embodiment of the disclosure corresponds to the training method part of the transaction risk factor prediction model in the embodiment of the disclosure, and the description of the training device part of the transaction risk factor prediction model specifically refers to the training method part of the transaction risk factor prediction model, which is not described herein again.

Fig. 9 schematically shows a block diagram of an electronic device adapted to implement a prediction method of a transaction risk factor according to an embodiment of the present disclosure. The electronic device shown in fig. 9 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.

As shown in fig. 9, a computer electronic device 900 according to an embodiment of the present disclosure includes a processor 901 which can perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)902 or a program loaded from a storage section 908 into a Random Access Memory (RAM) 903. Processor 901 may comprise, for example, a general purpose microprocessor (e.g., a CPU), an instruction set processor and/or associated chipset, and/or a special purpose microprocessor (e.g., an Application Specific Integrated Circuit (ASIC)), among others. The processor 901 may also include on-board memory for caching purposes. The processor 901 may comprise a single processing unit or a plurality of processing units for performing the different actions of the method flows according to embodiments of the present disclosure.

In the RAM 903, various programs and data necessary for the operation of the electronic apparatus 900 are stored. The processor 901, ROM902, and RAM 903 are connected to each other by a bus 904. The processor 901 performs various operations of the method flows according to the embodiments of the present disclosure by executing programs in the ROM902 and/or the RAM 903. Note that the programs may also be stored in one or more memories other than the ROM902 and the RAM 903. The processor 901 may also perform various operations of the method flows according to the embodiments of the present disclosure by executing programs stored in the one or more memories.

Electronic device 900 may also include input/output (I/O) interface 905, input/output (I/O) interface 905 also connected to bus 904, according to an embodiment of the present disclosure. The electronic device 900 may also include one or more of the following components connected to the I/O interface 905: an input portion 906 including a keyboard, a mouse, and the like; an output section 907 including components such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage portion 908 including a hard disk and the like; and a communication section 909 including a network interface card such as a LAN card, a modem, or the like. The communication section 909 performs communication processing via a network such as the internet. The drive 910 is also connected to the I/O interface 905 as necessary. A removable medium 911 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 910 as necessary, so that a computer program read out therefrom is mounted into the storage section 908 as necessary.

According to embodiments of the present disclosure, method flows according to embodiments of the present disclosure may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable storage medium, the computer program containing program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 909, and/or installed from the removable medium 911. The computer program, when executed by the processor 901, performs the above-described functions defined in the system of the embodiment of the present disclosure. The systems, devices, apparatuses, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the present disclosure.

The present disclosure also provides a computer-readable storage medium, which may be contained in the apparatus/device/system described in the above embodiments; or may exist separately and not be assembled into the device/apparatus/system. The computer-readable storage medium carries one or more programs which, when executed, implement the method according to an embodiment of the disclosure.

According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium. Examples may include, but are not limited to: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

For example, according to embodiments of the present disclosure, a computer-readable storage medium may include the ROM902 and/or the RAM 903 described above and/or one or more memories other than the ROM902 and the RAM 903.

Embodiments of the present disclosure also include a computer program product comprising a computer program comprising program code for performing the method provided by embodiments of the present disclosure, when the computer program product is run on an electronic device, for causing the electronic device to implement the method for predicting a transaction risk factor provided by embodiments of the present disclosure.

The computer program, when executed by the processor 901, performs the above-described functions defined in the system/apparatus of the embodiments of the present disclosure. The systems, apparatuses, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the present disclosure.

In one embodiment, the computer program may be hosted on a tangible storage medium such as an optical storage device, a magnetic storage device, or the like. In another embodiment, the computer program may also be transmitted, distributed in the form of a signal on a network medium, and downloaded and installed through the communication section 909 and/or installed from the removable medium 911. The computer program containing program code may be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.

In accordance with embodiments of the present disclosure, program code for executing computer programs provided by embodiments of the present disclosure may be written in any combination of one or more programming languages, and in particular, these computer programs may be implemented using high level procedural and/or object oriented programming languages, and/or assembly/machine languages. The programming language includes, but is not limited to, programming languages such as Java, C + +, python, the "C" language, or the like. The program code may execute entirely on the user's computing device, partly on the user's device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions. It will be appreciated by those skilled in the art that various combinations and/or combinations of the features recited in the various embodiments of the disclosure and/or the claims may be made even if such combinations or combinations are not explicitly recited in the disclosure. In particular, various combinations and/or combinations of the features recited in the various embodiments and/or claims of the present disclosure may be made without departing from the spirit or teaching of the present disclosure. All such combinations and/or associations are within the scope of the present disclosure.

The embodiments of the present disclosure have been described above. However, these examples are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although the embodiments are described separately above, this does not mean that the measures in the embodiments cannot be used in advantageous combination. The scope of the disclosure is defined by the appended claims and equivalents thereof. Various alternatives and modifications can be devised by those skilled in the art without departing from the scope of the present disclosure, and such alternatives and modifications are intended to be within the scope of the present disclosure.

Claims

1. A method of predicting a transaction risk factor, comprising:

in response to receiving a transaction risk factor prediction request, acquiring transaction risk factor prediction parameters corresponding to transaction data to be predicted in the transaction risk factor prediction request, wherein the transaction risk factor prediction parameters comprise a concentration risk factor, the risk weight and initial sensitivity;

2. The method of claim 1, further comprising:

under the condition that the guarantee sum degree meets a preset early warning condition, outputting prompt information representing that the transaction to be predicted is allowed to be executed; and

and under the condition that the guarantee sum degree does not meet the preset early warning condition, outputting early warning information representing that the execution of the transaction to be predicted is forbidden.

3. The method of claim 1 or 2, wherein the training method of the trained transaction risk factor prediction model comprises:

and adjusting model parameters of the transaction risk factor prediction model by using the sample transaction risk factor predicted value and the actual value of the transaction risk factor to obtain the trained transaction risk factor prediction model.

4. The method of claim 3, wherein the transaction risk factor predictive model includes the support vector machine module and the radial basis function neural network module;

inputting the training sample data into a transaction risk factor prediction model, and outputting a sample transaction risk factor prediction value comprises:

the step of adjusting the model parameters of the transaction risk factor prediction model by using the sample transaction risk factor predicted value and the actual value of the transaction risk factor to obtain the trained transaction risk factor prediction model comprises the following steps:

under the condition that model parameters of a support vector machine module in the trained transaction risk factor prediction model are kept unchanged, model parameters of the radial basis function neural network module are adjusted by using the sample transaction risk factor predicted value and the transaction risk factor true value, and the radial basis function neural network module in the trained transaction risk factor prediction model is obtained.

5. The method of claim 4, wherein the radial basis function neural network module in the transaction risk factor prediction model comprises an input layer, a hidden layer, and an output layer, a kernel function of the hidden layer comprising a Gaussian function;

the step of adjusting the model parameters of the radial basis function neural network module by using the sample transaction risk factor predicted value and the transaction risk factor true value to obtain the radial basis function neural network module in the trained transaction risk factor prediction model comprises the following steps:

determining whether error parameters of the real transaction risk factor value and the predicted value of the sample transaction risk factor meet preset conditions according to at least one of the average absolute error, the mean square error, the average absolute percentage error and the root mean square error; and

and determining a model obtained when the error parameter meets a preset condition as a radial basis function neural network module in the trained transaction risk factor prediction model.

6. The method of claim 5, further comprising:

in response to the error parameter not meeting the preset condition, updating a target learning rate of the radial basis function neural network module;

and determining an updated error parameter according to the true value of the transaction risk factor and the updated predicted value of the sample transaction risk factor.

7. A prediction apparatus of a transaction risk factor, comprising:

the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for responding to a received transaction risk factor prediction request and acquiring transaction risk factor prediction parameters corresponding to-be-predicted transaction data in the transaction risk factor prediction request, and the transaction risk factor prediction parameters comprise a concentration risk factor, a risk weight and initial sensitivity;

and the second processing module is used for inputting the initial experience risk factor predicted value into a radial basis function neural network module in the trained transaction risk factor prediction model and outputting the transaction risk factor predicted value.

8. An electronic device, comprising:

one or more processors;

a memory to store one or more instructions that,

wherein the one or more instructions, when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-6.

9. A computer readable storage medium having stored thereon executable instructions which, when executed by a processor, cause the processor to carry out the method of any one of claims 1 to 6.

10. A computer program product comprising computer executable instructions for implementing the method of any one of claims 1 to 6 when executed.