CN115860916A - Risk prediction method and device, electronic equipment and storage medium - Google Patents
Risk prediction method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN115860916A CN115860916A CN202211543533.5A CN202211543533A CN115860916A CN 115860916 A CN115860916 A CN 115860916A CN 202211543533 A CN202211543533 A CN 202211543533A CN 115860916 A CN115860916 A CN 115860916A
- Authority
- CN
- China
- Prior art keywords
- index data
- risk
- standard
- original
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000012545 processing Methods 0.000 claims abstract description 51
- 230000007246 mechanism Effects 0.000 claims abstract description 37
- 238000013058 risk prediction model Methods 0.000 claims abstract description 29
- 238000007781 pre-processing Methods 0.000 claims description 27
- 238000012549 training Methods 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 16
- 230000015654 memory Effects 0.000 claims description 12
- 230000002159 abnormal effect Effects 0.000 claims description 9
- 238000004891 communication Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000008901 benefit Effects 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a risk prediction method, a risk prediction device, electronic equipment and a storage medium. The method comprises the following steps: acquiring original economic index data, original combination net value and original risk index data of an investment product; based on a multi-head attention mechanism model, respectively processing original economic index data and original risk index data, and determining standard economic index data and standard risk index data; discretizing the original combined net value to determine a standard combined net value; and determining target economic index data, target combined net value and target risk index data of the investment product in a preset time period based on a risk prediction model according to the standard economic index data, the standard combined net value and the standard risk index data. According to the method, data are processed in a multi-head attention mechanism model, discretization and other modes, the risk of the investment product in a preset time period is predicted based on the risk prediction model, the accuracy of risk prediction is improved, and the use experience of a user is improved.
Description
Technical Field
The present invention relates to the field of risk prediction technologies, and in particular, to a risk prediction method and apparatus, an electronic device, and a storage medium.
Background
With the continuous development of financial markets, more and more investment modes are used for measuring investment income and risk warning, and different total investment modes including equity, solid income, liability and mobile influence the overall earning rate, so that the traditional single prediction model cannot meet the requirements of investors.
At present, in the prior art, a sequence model based on an attention mechanism is mainly used for realizing rapid parallel or carrying out risk prediction by a prediction method of a Long Short Term Memory (LSTM) neural network model, but for time sequence data which is not completely formed according to a time sequence, the problem of low prediction accuracy rate exists.
Disclosure of Invention
The invention provides a risk prediction method, a risk prediction device, electronic equipment and a storage medium, solves the problems that risk indexes are scattered and cannot be judged visually, improves the accuracy of risk prediction, and improves the use experience of a user.
According to an aspect of the present invention, an embodiment of the present invention provides a risk prediction method, including: acquiring original economic index data, original combination net value and original risk index data of an investment product; based on a multi-head attention mechanism model, respectively processing original economic index data and original risk index data to determine standard economic index data and standard risk index data; discretizing the original combination net value to determine a standard combination net value; and determining target economic index data, target combined net worth and target risk index data of the investment product in a preset time period based on a risk prediction model according to the standard economic index data, the standard combined net worth and the standard risk index data.
Optionally, based on the multi-head attention mechanism model, processing the original economic index data, and determining standard economic index data, including: performing first preprocessing on original economic index data, wherein the first preprocessing comprises abnormal value processing and standardization processing; inputting the original economic index data after the first pretreatment into a multi-head attention mechanism model for training, and determining standard economic index data.
Optionally, obtaining the original risk indicator data includes: acquiring a prediction parameter; and determining original risk index data according to the prediction parameters.
Optionally, based on the multi-head attention mechanism model, processing the original risk indicator data, and determining standard risk indicator data, includes: performing second preprocessing on the original risk index data, wherein the second preprocessing is standardization processing; and inputting the original risk index data subjected to the second preprocessing into a multi-head attention mechanism model for training, and determining standard risk index data.
Optionally, determining target economic indicator data, target combined net worth and target risk indicator data of the investment product in a preset time period based on the risk prediction model according to the standard economic indicator data, the standard combined net worth and the standard risk indicator data, including: splicing the standard economic index data, the standard combination net value and the standard risk index data to determine combined data; and inputting the combined data into a risk prediction model for training, and determining target economic index data, target combined net value and target risk index data.
Optionally, after determining the target economic indicator data, the target combined net worth, and the target risk indicator data of the investment product in the preset time period, the method further includes: and if the value of at least one of the target economic index data, the target combination net value and the target risk index data is located in the corresponding risk interval, sending out early warning information.
Optionally, the risk prediction model is a Transformer model.
According to another aspect of the present invention, an embodiment of the present invention further provides a risk prediction apparatus, including: the data acquisition module is used for acquiring original economic index data, original combined net worth and original risk index data of the investment product; the first processing module is used for respectively processing the original economic index data and the original risk index data based on the multi-head attention mechanism model and determining standard economic index data and standard risk index data; the second processing module is used for carrying out discretization processing on the original combined net value to determine a standard combined net value; and the risk prediction module is used for determining target economic index data, target combined net value and target risk index data of the investment product in a preset time period based on the risk prediction model according to the standard economic index data, the standard combined net value and the standard risk index data.
According to another aspect of the present invention, an embodiment of the present invention further provides an electronic device, including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform the risk prediction method of any of the embodiments of the invention.
According to another aspect of the present invention, an embodiment of the present invention further provides a computer-readable storage medium, in which computer instructions are stored, and the computer instructions are used for enabling a processor to implement the risk prediction method according to any embodiment of the present invention when executed.
According to the technical scheme of the embodiment of the invention, original economic index data, original combined net worth and original risk index data of investment products are obtained; based on a multi-head attention mechanism model, respectively processing original economic index data and original risk index data to determine standard economic index data and standard risk index data; discretizing the original combined net value to determine a standard combined net value; and determining target economic index data, target combined net value and target risk index data of the investment product in a preset time period based on a risk prediction model according to the standard economic index data, the standard combined net value and the standard risk index data. On the basis of the embodiment, the standard economic index data, the standard combination net value and the standard risk index data are processed and determined in a multi-head attention mechanism model, discretization and other modes, then the target economic index data, the target combination net value and the target risk index data of the investment product in a preset time period are determined based on the risk prediction model, the stability of risk prediction is guaranteed, the accuracy of the risk prediction is improved, and the use experience of a user is improved.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present invention, nor do they necessarily limit the scope of the invention. Other features of the present invention will become apparent from the following description.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a flowchart of a risk prediction method provided in a first embodiment of the present invention;
fig. 2 is a flowchart of a risk prediction method provided in the second embodiment of the present invention;
fig. 3 is a schematic structural diagram of a risk prediction apparatus provided in the third embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device according to a fourth embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in other sequences than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example one
Fig. 1 is a flowchart of a risk prediction method provided in one embodiment of the present invention, which may be applied to a risk prediction situation of an endowment investment product, and the method may be performed by a risk prediction apparatus, which may be implemented in a form of hardware and/or software, and in one specific embodiment, the risk prediction apparatus may be configured in an electronic device. As shown in fig. 1, the method of the embodiment of the present invention specifically includes the following steps:
s110, acquiring original economic index data, original combined net value and original risk index data of the investment product.
Wherein, the investment product can be, for example, stocks, bonds, financial derivatives, etc.; the raw economic indicator data typically includes interest rate (%), deposit reserve (%), inter-bank industry loan rate (%), currency supply M0 (billion), currency supply M1 (billion), currency supply M2 (billion), bank balance sheet (billion), foreign exchange reserve (million dollars), center bank balance sheet (CNY-HML), private department loan (CNY-HML), deposit interest rate (%), loan growth (%), reverse buyback rate (%), liquidity by reverse buyback (billion), bank loan (CNY-HML), and loan interest rate (%). Wherein the money supply amount M0 (billion) is cash, the money supply amount M1 (billion) is cash and a business term deposit, and the money supply amount M2 (billion) is a sum of the money supply amount M1 (billion), a resident deposit and a business term deposit. CNY-HML is the exchange rate of China's bank for dollar exchange rate; the original net value of the combination is historical data of the net value of the combination of the selected investment products, and the net value of the combination is calculated by the difference value of assets of the investment products and liabilities of the investment products; the original risk index data comprise the rate of return, the fluctuation rate, the sharp ratio Sharpe, alpha, beta, and the sharp ratio Sharpe describes the excess return which can be obtained by the strategy under the unit total risk; alpha is an excess revenue that is independent of market fluctuations, i.e., does not derive revenue from a systematic rise; beta represents the sensitivity of the strategy performance to the change of the large disk, namely the correlation between the strategy and the large disk, which is not limited by the embodiment.
Specifically, the raw economic index data of the investment product obtained from the domestic macroscopic economic index database generally includes interest rate (%), deposit reserve rate (%), inter-bank equity interest rate (%), money supply amount M0 (billion), money supply amount M1 (billion), money supply amount M2 (billion), bank balance table (billion), foreign exchange reserve (million), central bank balance table (CNY-HML), private loan (CNY-HML), deposit interest rate (%), loan growth (%), reverse buyback interest rate (%), raw economic index data such as fluidity (billion) by reverse buyback, bank (CNY-HML) and loan interest rate (%), and raw risk index data such as yield, loan rate, sharp rate, alpha (alpha ), beta, and the like, and raw risk index data such as net investment portfolio.
And S120, based on the multi-head attention mechanism model, respectively processing the original economic index data and the original risk index data, and determining standard economic index data and standard risk index data.
The multi-head attention mechanism model is characterized in that the model is divided into a plurality of heads to form a plurality of subspaces, so that information of different aspects of investment products can be paid attention to, the capability of the model concentrating on different positions is expanded, and the model can capture richer characteristic information; the standard economic index data is data obtained by processing the original economic index data and the standard risk index data is data obtained by processing the original risk index data.
Specifically, the original economic index data and the original risk index data are respectively input into a multi-head attention mechanism model, the original economic index data and the original risk index data are respectively trained through the multi-head attention mechanism model, more characteristic information of the original economic index data and the original risk index data is captured, and the standard economic index data and the standard risk index data are determined.
And S130, discretizing the original combined net value to determine a standard combined net value.
The discretization processing mainly maps limited individuals in an infinite space into a limited space, reduces the static time complexity of the original combination through the discretization processing, and improves the operation efficiency.
Specifically, discretization is performed on the original combined net value, so that the time complexity of the original combined net value is reduced, and the standard combined net value is determined.
On the basis of the above embodiment, the execution of S120 and S130 has no sequence, and S120 may be executed first, and then S130 may be executed; s130 may be performed first, and then S120 may be performed; s120 and S130 may also be performed simultaneously.
And S140, determining target economic index data, target combined net value and target risk index data of the investment product in a preset time period based on a risk prediction model according to the standard economic index data, the standard combined net value and the standard risk index data.
The risk prediction model is a Transformer model and a sequence model based on an attention mechanism, and the attention mechanism is a technology which can enable the model to pay attention to important information and fully learn and absorb the important information, and can be used in the sequence model. the transform structure is composed of an encoder and a decoder, wherein the encoder and the decoder are a model architecture, the encoder converts an input sequence into a dense vector with a fixed dimension, and the decoder stage generates a target translation from the activation state. The prediction time period is a preset prediction time, and may be, for example, 3 days, one week, one month, or the like, which is not limited in this embodiment.
Specifically, after the standard economic indicator data, the standard combination net value and the standard risk indicator data are determined, the standard economic indicator data, the standard combination net value and the standard risk indicator data are input into a risk prediction model, training prediction is carried out on the standard economic indicator data, the standard combination net value and the standard risk indicator data based on the risk prediction model, and target economic indicator data, target combination net value and target risk indicator data of the investment product in a preset time period are determined.
On the basis of the above embodiment, optionally, if at least one value of the target economic indicator data, the target combined net value, and the target risk indicator data is located in the risk interval corresponding to the target economic indicator data, the early warning information is sent out.
The risk interval is a safety value range corresponding to each of the preset target economic index data, the preset target net combination value and the preset target risk index data, for example, the risk interval of the profitability in the target risk index data is less than 5% or greater than 90%, which is not limited in this embodiment.
Specifically, after determining target economic index data, target combined net value and target risk index data, determining whether values of the target economic index data, the target combined net value and the target risk index data are within corresponding risk value range, if so, sending alarm information for reminding a user that the data have risks; and if the current time is not within the risk interval range, no alarm information is sent out.
Exemplarily, if the yield in the target risk index data is determined to be 50%, and the yield 50% in the target risk index data is not within the risk interval of less than 5% or more than 90%, the yield is determined to be safe, and no alarm information is sent out; and if the yield in the target risk index data is determined to be 3%, determining that the yield is unsafe if the yield of 3% in the target risk index data is not less than 5% or more than 90% in the risk interval, and sending alarm information. The method has the advantages that the predicted target economic index data, the target combination net value and the target risk index data are detected and protected by setting the risk interval, and the safety of investment products is improved.
According to the technical scheme of the embodiment of the invention, original economic index data, original combined net value and original risk index data of an investment product are obtained; based on a multi-head attention mechanism model, respectively processing original economic index data and original risk index data to determine standard economic index data and standard risk index data; discretizing the original combined net value to determine a standard combined net value; and determining target economic index data, target combined net value and target risk index data of the investment product in a preset time period based on a risk prediction model according to the standard economic index data, the standard combined net value and the standard risk index data. On the basis of the embodiment, the standard economic index data, the standard combination net value and the standard risk index data are determined through a multi-head attention mechanism model and discretization, and then the target economic index data, the target combination net value and the target risk index data of the investment product in a preset time period are determined on the basis of a risk prediction model, so that the stability of risk prediction is ensured, the accuracy of risk prediction is improved, and the use experience of a user is improved.
Example two
Fig. 2 is a flowchart of a risk prediction method provided in the second embodiment of the present invention, which may be applied to a risk prediction situation of an endowment investment product, and the method may be executed by a risk prediction apparatus, which may be implemented in a form of hardware and/or software, and in a specific embodiment, the risk prediction apparatus may be configured in an electronic device. On the basis of the embodiment, original economic index data are processed on the basis of a multi-head attention mechanism model, and standard economic index data are determined; acquiring original risk index data; based on a multi-head attention mechanism model, processing the original risk index data, determining standard risk index data and the like for further optimization, as shown in fig. 2, the method specifically comprises the following steps:
s210, acquiring original economic index data, original combination net value and prediction parameters of the investment product.
The prediction parameters comprise strategy daily yield, benchmark daily yield variance, strategy and benchmark daily yield covariance, strategy annual yield, risk-free yield and benchmark annual yield, and are used for calculating original risk index data.
Specifically, the original economic index data of the investment product and the prediction parameters such as the strategy daily rate of return, the benchmark daily rate of return variance, the strategy and the covariance of the benchmark daily rate of return, the strategy annual rate of return, the risk-free rate of return, the benchmark annual rate of return and the like are directly obtained from the domestic macroscopic economic index database, and the original combination net value is obtained from the investment product net value database.
And S220, determining original risk index data according to the prediction parameters.
Specifically, after prediction parameters such as the strategy daily profitability, the reference daily profitability, the covariance of the strategy and the reference daily profitability, the strategy annual profitability, the risk-free profitability and the reference annual profitability are obtained, the sharp ratios sharp, alpha and beta are calculated and determined according to the strategy daily profitability, the reference daily profitability, the covariance of the strategy and the reference daily profitability, the strategy annual profitability, the risk-free profitability and the reference annual profitability. Further, in the above-mentioned case,
wherein p is n For strategic daily profitability, B n Based on the daily gain->
To benchmark daily gain variance, cov (p) n ,B n ) Is the covariance of the strategy and the benchmark daily rate of return. α = p r -r f -β(B r -r f ) Wherein p is r To make the annual profitability of the strategy, r f For risk-free profitability, B r When alpha is more than 0, obtaining excess income for the benchmark annual income rate; when alpha is equal to 0, the strategy obtains proper benefits relative to risks; when α is less than 0, the strategy yields less benefit relative to risk. The profitability is determined by calculating the ratio of the difference value of the end-term asset value and the initial-term asset value to the initial-term asset value; the fluctuation rate is the standard deviation of the yield; sharpe ratio Sharpe is based on strategy yield and risk-free rate of return survey of initial trading daysAnd (4) calculating and determining the ratio of the difference value of (A) to the strategy gain fluctuation rate.
And S230, carrying out second preprocessing on the original risk index data.
The second preprocessing is a standardization processing, and original economic index data are reduced according to a certain proportion, so that the reduction range of the original economic index data falls within a specified interval.
Specifically, after the original risk index data is obtained, the risk index data is subjected to standardization processing.
And S240, inputting the original risk index data subjected to the second preprocessing into a multi-head attention mechanism model for training, and determining standard risk index data.
Specifically, the original risk index data after the second preprocessing is input into a multi-head attention mechanism model for training, and standard risk index data are determined.
And S250, performing first preprocessing on the original economic index data.
The first preprocessing comprises abnormal value processing and standardization processing, wherein the abnormal value processing refers to abnormal data processing of original economic indicator data, such as the phenomena of missing of the original economic indicator data; the standardization process is to reduce the original economic index data according to a certain proportion so that the reduction range falls within a specified interval.
Specifically, after the original economic indicator data is acquired, abnormal value processing is performed on the original economic indicator data, and after the abnormal value processing is performed, the data after the abnormal value processing is further subjected to standardization processing.
And S260, inputting the original economic index data subjected to the first preprocessing into a multi-head attention mechanism model for training, and determining standard economic index data.
Specifically, the original economic index data after the first preprocessing is input into a multi-head attention mechanism model for training, and standard economic index data are determined.
And S270, discretizing the original combined net value to determine a standard combined net value.
Specifically, the original combined net value is discretized, the time complexity of the original combined net value is reduced through the discretization, and then the standard combined net value is determined.
On the basis of the above embodiment, the execution of S220-S240, S250-S260 and S270 has no sequence, and S220-S240, S250-S260 and S270 may be executed first; or executing S220-S240, then executing S270, and then executing S250-S260; or executing S250-S260, then executing S220-S240, and then executing S270; or executing S250-S260, then executing S270, and then executing S220-S240; or executing S250-S260, then executing S220-S240, and then executing S270; or executing S270, then executing S220-S240, and then executing S250-S260; or S270, then S250-S260 is executed, and then S220-S240 is executed; S220-S240, S250-S260, and S270 may also be performed simultaneously.
And S280, splicing the standard economic index data, the standard combined net value and the standard risk index data to determine combined data.
And the combined data is obtained by splicing the standard economic index data, the standard combined net value and the standard risk index data.
Specifically, after the standard economic indicator data, the standard combination net worth and the standard risk indicator data are determined, the standard economic indicator data, the standard combination net worth and the standard risk indicator data are randomly spliced to determine the combined data.
And S290, inputting the combined data into a risk prediction model for training, and determining target economic index data, target combined net value and target risk index data.
Specifically, the combined data is input into a risk prediction model, the combined data is calculated through the risk prediction model, a vector matrix corresponding to the combined data is determined, then the vector matrix is input into an Encoder, after 6 Encoder blocks, all words in the vector matrix are coding information matrices, finally the coding information matrices are output and transmitted to a Decoder, the trained combined data is determined, and the trained combined data is split to determine target economic index data, target combined net value and target risk index data.
According to the technical scheme of the embodiment of the invention, original economic index data, original combination net value and prediction parameters of investment products are obtained; determining original risk index data according to the prediction parameters; carrying out first preprocessing on original economic index data; inputting the original economic index data subjected to the first pretreatment into a multi-head attention mechanism model for training, and determining standard economic index data; performing second preprocessing on the original risk index data; inputting the original risk index data subjected to the second preprocessing into a multi-head attention mechanism model for training, and determining standard risk index data; discretizing the original combined net value to determine a standard combined net value; splicing the standard economic index data, the standard combination net value and the standard risk index data to determine combined data; and inputting the combined data into a risk prediction model for training, and determining target economic index data, target combined net value and target risk index data. On the basis of the embodiment, before the original economic index data, the original combined net value and the original risk index data are input into the multi-head attention mechanism model, the original economic index data are subjected to first preprocessing, the original risk index data are subjected to second preprocessing, meanwhile, the determined standard economic index data, the determined standard combined net value and the determined standard risk index data are spliced to determine combined data, and then the combined data are input into the risk prediction model for training, so that the accuracy of risk prediction is improved, and the efficiency of the risk prediction model is improved.
EXAMPLE III
Fig. 3 is a schematic structural diagram of a risk prediction apparatus provided in a third embodiment of the present invention, where the apparatus includes: a data acquisition module 310, a first processing module 320, a second processing module 330, and a risk prediction module 340. Wherein,
the data obtaining module 310 is configured to obtain original economic indicator data, original net value of combination, and original risk indicator data of the investment product.
The first processing module 320 is configured to process the original economic indicator data and the original risk indicator data respectively based on the multi-head attention mechanism model, and determine standard economic indicator data and standard risk indicator data.
And the second processing module 330 is configured to perform discretization on the original combined net value to determine a standard combined net value.
And the risk prediction module 340 is configured to determine target economic indicator data, target combined net worth and target risk indicator data of the investment product in a preset time period based on a risk prediction model according to the standard economic indicator data, the standard combined net worth and the standard risk indicator data.
Optionally, the first processing module 320 is specifically configured to: performing first pretreatment on original economic index data, wherein the first pretreatment comprises abnormal value treatment and standardization treatment; inputting the original economic index data after the first pretreatment into a multi-head attention mechanism model for training, and determining standard economic index data.
Optionally, the data obtaining module 310 is specifically configured to: obtaining a prediction parameter; and determining original risk index data according to the prediction parameters.
Optionally, the first processing module 320 is specifically configured to: performing second preprocessing on the original risk index data, wherein the second preprocessing is standardization processing; and inputting the original risk index data subjected to the second preprocessing into a multi-head attention mechanism model for training, and determining standard risk index data.
Optionally, the risk prediction module 340 is specifically configured to: splicing the standard economic index data, the standard combination net value and the standard risk index data to determine combined data; and inputting the combined data into a risk prediction model for training, and determining target economic index data, target combined net value and target risk index data.
Optionally, the apparatus further comprises: an early warning module for: after target economic index data, target combined net value and target risk index data of the investment product in a preset time period are determined, if the value of at least one of the target economic index data, the target combined net value and the target risk index data is located in a corresponding risk interval, early warning information is sent out.
Optionally, the risk prediction model is a Transformer model.
The risk prediction device provided by the embodiment of the invention can execute the risk prediction method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method.
Example four
Fig. 4 is a schematic diagram of an electronic device according to a fourth embodiment of the present invention, the electronic device being intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 4, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, and the like, wherein the memory stores a computer program executable by the at least one processor, and the processor 11 can perform various suitable actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from a storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data necessary for the operation of the electronic apparatus 10 may also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.
A number of components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, or the like; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.
The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, or the like. The processor 11 performs the various methods and processes described above, such as risk prediction methods.
In some embodiments, the risk prediction method may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the risk prediction method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the risk prediction method by any other suitable means (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be performed. A computer program can execute entirely on a machine, partly on a machine, as a stand-alone software package partly on a machine and partly on a remote machine or entirely on a remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, 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), an optical fiber, a compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user may provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service are overcome.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present invention may be executed in parallel, sequentially, or in different orders, and are not limited herein as long as the desired results of the technical solution of the present invention can be achieved.
The above-described embodiments should not be construed as limiting the scope of the invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A method of risk prediction, the method comprising:
acquiring original economic index data, original combination net value and original risk index data of an investment product;
based on a multi-head attention mechanism model, respectively processing the original economic index data and the original risk index data to determine standard economic index data and standard risk index data;
discretizing the original combined net value to determine a standard combined net value;
and determining target economic index data, target combined net value and target risk index data of the investment product in a preset time period based on a risk prediction model according to the standard economic index data, the standard combined net value and the standard risk index data.
2. The method of claim 1, wherein the processing the raw economic indicator data based on the multi-head attention mechanism model to determine standard economic indicator data comprises:
performing first preprocessing on the original economic indicator data, wherein the first preprocessing comprises abnormal value processing and standardization processing;
inputting the original economic index data subjected to the first preprocessing into the multi-head attention mechanism model for training, and determining the standard economic index data.
3. The method of claim 1, wherein the obtaining raw risk indicator data comprises:
obtaining a prediction parameter;
and determining original risk index data according to the prediction parameters.
4. The method of claim 3, wherein the processing the raw risk indicator data to determine standard risk indicator data based on a multi-head attention mechanism model comprises:
performing second preprocessing on the original risk indicator data, wherein the second preprocessing is standardization processing;
inputting the original risk index data subjected to the second preprocessing into the multi-head attention mechanism model for training, and determining the standard risk index data.
5. The method of claim 1, wherein determining target economic indicator data, target net portfolio value, and target risk indicator data for the investment product over a preset time period based on a risk prediction model based on the standard economic indicator data, the standard net portfolio value, and the standard risk indicator data comprises:
splicing the standard economic index data, the standard combined net value and the standard risk index data to determine combined data;
and inputting the combined data into the risk prediction model for training, and determining the target economic index data, the target combined net value and the target risk index data.
6. The method of claim 1, further comprising, after determining target economic indicator data, target net-of-portfolio data, and target risk indicator data for the investment product over a preset time period:
and if the value of at least one of the target economic index data, the target combination net value and the target risk index data is in the corresponding risk interval, sending out early warning information.
7. The method of any one of claims 1-6, wherein the risk prediction model is a Transformer model.
8. A risk prediction device, the device comprising:
the data acquisition module is used for acquiring original economic index data, original combined net value and original risk index data of the investment product;
the first processing module is used for respectively processing the original economic index data and the original risk index data based on a multi-head attention mechanism model and determining standard economic index data and standard risk index data;
the second processing module is used for carrying out discretization processing on the original combined net value to determine a standard combined net value;
and the risk prediction module is used for determining target economic index data, target combined net value and target risk index data of the investment product in a preset time period based on a risk prediction model according to the standard economic index data, the standard combined net value and the standard risk index data.
9. An electronic device, characterized in that the electronic device comprises:
at least one processor; and a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the risk prediction method of any one of claims 1-7.
10. A computer-readable storage medium having stored thereon computer instructions for causing a processor to, when executed, implement the risk prediction method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211543533.5A CN115860916A (en) | 2022-11-29 | 2022-11-29 | Risk prediction method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211543533.5A CN115860916A (en) | 2022-11-29 | 2022-11-29 | Risk prediction method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115860916A true CN115860916A (en) | 2023-03-28 |
Family
ID=85669634
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211543533.5A Pending CN115860916A (en) | 2022-11-29 | 2022-11-29 | Risk prediction method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115860916A (en) |
-
2022
- 2022-11-29 CN CN202211543533.5A patent/CN115860916A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11551305B1 (en) | Methods and systems to quantify and index liquidity risk in financial markets and risk management contracts thereon | |
| Fan et al. | What has driven oil prices since 2000? A structural change perspective | |
| Kartal et al. | The determinants of main stock exchange index changes in emerging countries: evidence from Turkey in COVID-19 pandemic age | |
| Valášková et al. | Assessing credit risk by Moody's KMV model | |
| CN109598606B (en) | Data processing method, device, medium and electronic equipment | |
| Myšková et al. | The effect of managerial sentiment on market-to-book ratio | |
| Braiek et al. | Islamic portfolio optimization under systemic risk: Vine Copula‐CoVaR based model | |
| Akbulaev et al. | Economic analysis of tourism enterprise solvency and the possibility of bankruptcy: The case of the Thomas cook group | |
| CN114997975A (en) | Abnormal enterprise identification method, device, equipment, medium and product | |
| Yahaya et al. | Stock market liquidity and volatility on the Nigerian Exchange Limited (NGX) | |
| CN117333076A (en) | Evaluation method, device, equipment and medium based on mixed expert model | |
| CN111161080A (en) | Information processing method and device | |
| Polanski et al. | Forecasting multidimensional tail risk at short and long horizons | |
| Park et al. | Value at risk forecasting for volatility index | |
| CN115860916A (en) | Risk prediction method and device, electronic equipment and storage medium | |
| Zaychenko et al. | Banks bankruptcy risk forecasting with application of computational intelligence methods | |
| Imana et al. | Analysis of International Index on Indonesian Sharia Stock Index | |
| Jerico et al. | When does inequality freeze an economy? | |
| Rungcharoenkitkul | Risk sharing versus financial contagion in Asia: An asset price perspective | |
| CN114036208B (en) | Model training and sensitivity analysis method, device, equipment and medium | |
| Wang et al. | Kernel‐Based Aggregating Learning System for Online Portfolio Optimization | |
| Wang et al. | Impact of the Adjustment of maximum order volume on pricing efficiency of stock index futures in China | |
| CN116644372B (en) | Account type determining method and device, electronic equipment and storage medium | |
| CN114781480A (en) | Target object evaluation method, evaluation model training method and device | |
| US20230073222A1 (en) | Method of treating asset, electronic device and storage medium |
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 |