Methods and devices for predicting risks in credit bond investment and trading

Abstract

This invention provides a method and apparatus for predicting the risk of credit bond investment transactions, relating to the field of artificial intelligence technology. The method includes: collecting transaction data during the credit bond investment transaction process, the transaction data including training set data and prediction set data; performing supervised training based on the training set data and a support vector machine algorithm to obtain a credit bond risk prediction model; performing risk prediction on the prediction set data based on the credit bond risk prediction model and determining the prediction accuracy; using the prediction accuracy as the fitness value of a cuckoo search algorithm, iteratively optimizing the penalty factor and kernel parameters in the credit bond risk prediction model using the cuckoo search algorithm to obtain the risk prediction model; and performing risk prediction on target transaction data during the target credit bond investment transaction process based on the risk prediction model. This invention improves the prediction accuracy of the risk prediction model and reduces learning costs, thereby enhancing the accuracy of credit bond investment transaction risk prediction.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, specifically to a method and apparatus for predicting risks in credit bond investment transactions. Background Technology

[0002] Current methods for predicting the risks of credit bond investment and trading mainly rely on establishing risk prediction models based on financial theories. However, there are also methods that use machine learning algorithms, such as neural networks and support vector machines (SVM), to train and build risk prediction models based on historical data of bond investment and trading.

[0003] With the gradual accumulation of bond investment and transaction data and the continuous enrichment of its data warehouse, it is hoped that machine learning can be used to predict the risks of bond investment and transactions. However, the machine learning algorithms currently used have problems such as data overfitting leading to low accuracy, and machine learning parameters mainly rely on human settings, which may result in poor learning efficiency due to unreasonable settings.

[0004] Therefore, there is an urgent need for a new method for predicting the risks of credit bond investment and trading to improve the accuracy of such predictions. Summary of the Invention

[0005] To address the problems in the existing technology, the present invention provides a method and apparatus for predicting the risks of credit bond investment and trading, which can effectively improve the accuracy of predicting the risks of credit bond investment and trading.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0007] In a first aspect, the present invention provides a method for predicting the risks of credit bond investment transactions, including:

[0008] Collect transaction data during the credit bond investment and trading process, including training set data and prediction set data;

[0009] Supervised training is performed using the training set data and the support vector machine algorithm to obtain a credit bond risk prediction model; risk prediction is then performed on the prediction set data based on the credit bond risk prediction model, and the prediction accuracy of the risk prediction is determined.

[0010] The prediction accuracy is used as the fitness value of the Cuckoo Search algorithm. The Cuckoo Search algorithm is used to iteratively optimize the penalty factor and kernel parameters in the credit bond risk prediction model to obtain the risk prediction model.

[0011] Based on the aforementioned risk prediction model, risk prediction is performed on the target transaction data during the target credit bond investment transaction process.

[0012] In one embodiment, after the transaction data in the credit bond investment transaction process, the following is also included:

[0013] The training set data and the prediction set data are normalized.

[0014] The collection of transaction data during the credit bond investment and trading process includes:

[0015] Add a risk registration tag to each piece of data in the transaction data;

[0016] Each risk registration label corresponds to a risk assessment value.

[0017] Wherein, the prediction accuracy is used as the fitness value of the cuckoo search algorithm, and the penalty factor and kernel parameters in the credit bond risk prediction model are iteratively optimized using the cuckoo search algorithm to obtain the risk prediction model, including:

[0018] Initialize the initial parameters of the cuckoo search algorithm, including: the number of nests, the number of iterations, the search range of the penalty factor, and the search range of the kernel parameter;

[0019] The initial bird's nest location is randomly generated; the x-axis of the initial bird's nest location is the penalty factor in the credit bond risk prediction model, and the y-axis is the kernel parameter in the credit bond risk prediction model.

[0020] The location of the bird's nest is updated by Levi's flight;

[0021] The prediction accuracy is used as the fitness value for each bird's nest.

[0022] After reaching the maximum number of iterations, output the penalty factor and kernel parameters of the iterative optimization process.

[0023] The method further includes, after setting the prediction accuracy as the fitness value for each nest:

[0024] Compared to the previous generation of Bird's Nest, this replaces the Bird's Nest with low prediction accuracy;

[0025] Determine if the generated random number is greater than the host discovery probability; if so, randomly change the nest location and replace the discovered nest; calculate the fitness value of each nest and determine the current optimal nest and the optimal risk prediction accuracy; if not, calculate the fitness value of each nest and determine the current optimal nest and the optimal risk prediction accuracy.

[0026] After the optimal risk prediction accuracy is greater than the preset required accuracy, the penalty factor and kernel parameters of the iterative optimization process are output.

[0027] The initial parameters also include: host discovery probability.

[0028] Secondly, the present invention provides a credit bond investment and trading risk prediction device, comprising:

[0029] The data acquisition module is used to collect transaction data during the credit bond investment transaction process. The transaction data includes training set data and prediction set data.

[0030] The training and prediction module is used to perform supervised training based on the training set data and the support vector machine algorithm to obtain a credit bond risk prediction model; and to perform risk prediction on the prediction set data based on the credit bond risk prediction model and determine the prediction accuracy of the risk prediction.

[0031] The iterative optimization module is used to use the prediction accuracy as the fitness value of the cuckoo search algorithm, and to perform iterative optimization on the penalty factor and kernel parameters in the credit bond risk prediction model through the cuckoo search algorithm to obtain the risk prediction model.

[0032] The risk prediction module is used to predict the risk of target transaction data during the target credit bond investment transaction process based on the risk prediction model.

[0033] In one embodiment, it further includes:

[0034] The normalization module is used to normalize the training set data and the prediction set data.

[0035] The data acquisition module includes:

[0036] A risk registration unit is used to add a risk registration tag to each piece of data in the transaction data;

[0037] Each risk registration label corresponds to a risk assessment value.

[0038] The iterative optimization module includes:

[0039] An initialization unit is used to initialize the initial parameters of the cuckoo search algorithm. The initial parameters include: the number of nests, the number of iterations, the search range of the penalty factor, and the search range of the kernel parameter.

[0040] An initial bird's nest unit is used to randomly generate the initial bird's nest position; the horizontal axis of the initial bird's nest position is the penalty factor in the credit bond risk prediction model, and the vertical axis is the kernel parameter in the credit bond risk prediction model.

[0041] Update the nest unit, used to update the nest's location via Levi's flight;

[0042] The setting unit is used to use the prediction accuracy as the fitness value corresponding to each bird's nest;

[0043] The first output unit is used to output the penalty factor and kernel parameters of the iterative optimization process after the maximum number of iterations has been reached.

[0044] The iterative optimization module further includes:

[0045] The bird's nest replacement unit is used to compare with the previous generation of bird's nests and replace bird's nests with low prediction accuracy;

[0046] The judgment unit is used to determine whether the generated random number is greater than the host discovery probability; if so, the nest location is randomly changed and the discovered nest is replaced; the fitness value of each nest is calculated and the current optimal nest and the optimal risk prediction accuracy are determined; if not, the fitness value of each nest is calculated and the current optimal nest and the optimal risk prediction accuracy are determined.

[0047] The second output unit is used to output the penalty factor and kernel parameters of the iterative optimization process after the optimal risk prediction accuracy is greater than the preset required accuracy.

[0048] The initial parameters also include: host discovery probability.

[0049] Thirdly, the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the credit bond investment transaction risk prediction method.

[0050] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the credit bond investment transaction risk prediction method described above.

[0051] As can be seen from the above technical solution, the present invention provides a method and apparatus for predicting the risk of credit bond investment transactions. The method involves collecting transaction data during the credit bond investment transaction process, including training set data and prediction set data; performing supervised training based on the training set data and a support vector machine algorithm to obtain a credit bond risk prediction model; performing risk prediction on the prediction set data based on the credit bond risk prediction model and determining the prediction accuracy; using the prediction accuracy as the fitness value of a cuckoo search algorithm, and iteratively optimizing the penalty factor and kernel parameters in the credit bond risk prediction model using the cuckoo search algorithm to obtain the risk prediction model; and performing risk prediction on target transaction data during the target credit bond investment transaction process based on the risk prediction model. This method improves the prediction accuracy of the risk prediction model and reduces learning costs, thereby enhancing the accuracy of credit bond investment transaction risk prediction. Attached Figure Description

[0052] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0053] Figure 1 This is a schematic diagram of the first process of the credit bond investment and transaction risk prediction method in an embodiment of the present invention.

[0054] Figure 2 This is a schematic diagram of the second process of the credit bond investment and transaction risk prediction method in an embodiment of the present invention.

[0055] Figure 3 This is a schematic diagram of the first process of step S103 in the credit bond investment transaction risk prediction method in this embodiment of the invention.

[0056] Figure 4 This is a schematic diagram of the second process of step S103 in the credit bond investment transaction risk prediction method in this embodiment of the invention.

[0057] Figure 5 This is a schematic diagram of the entire process of the credit bond investment and transaction risk prediction method in this embodiment of the invention.

[0058] Figure 6 This is a first structural schematic diagram of the credit bond investment and trading risk prediction device in an embodiment of the present invention.

[0059] Figure 7 This is a schematic diagram of the second structure of the credit bond investment and trading risk prediction device in an embodiment of the present invention.

[0060] Figure 8 This is a schematic diagram of the structure of an electronic device in an embodiment of the present invention. Detailed Implementation

[0061] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0062] This invention provides an embodiment of a method for predicting risks in credit bond investment transactions. See [link to embodiment]. Figure 1 The method for predicting the risks of credit bond investment transactions specifically includes the following:

[0063] S101: Collect transaction data during the credit bond investment transaction process, the transaction data including: training set data and prediction set data;

[0064] In this step, transaction data from the credit bond investment process is collected to establish a data warehouse. Before being incorporated into the data warehouse, a risk registration tag is added to each piece of transaction data; each risk registration tag corresponds to a risk assessment value, which is a score of {0, 10, 20, ..., 100}.

[0065] It should be noted that risk assessment values ​​are recommended to be derived from scores given by expert systems or traders. Ensure that every piece of data in the data warehouse includes, but is not limited to, the following fields: {Transaction Time, Amount, Bond Type, Issuance Time, Issuance Target, ..., Risk Level}.

[0066] The data in the data warehouse is divided into two subsets by random sampling: the training set data for the Support Vector Machine (SVM) algorithm learner and the prediction set data for the trained model.

[0067] S102: Supervised training is performed based on the training set data and the support vector machine algorithm to obtain a credit bond risk prediction model; risk prediction is performed on the prediction set data based on the credit bond risk prediction model, and the prediction accuracy of the risk prediction is determined;

[0068] S103: The prediction accuracy is used as the fitness value of the cuckoo search algorithm. The penalty factor and kernel parameters in the credit bond risk prediction model are iteratively optimized using the cuckoo search algorithm to obtain the risk prediction model.

[0069] In this step, the Cuckoo Search Algorithm (CS) effectively solves the optimization problem by simulating the parasitic breeding behavior of cuckoos, and employs a related Levy flight search mechanism to improve the local optima problem. The Cuckoo Search Algorithm has stronger global search capabilities and faster iteration speed.

[0070] The Cuckoo Search (CS) algorithm outperforms other algorithms in terms of convergence speed, search stability, and search accuracy. Furthermore, the support vector machine algorithm's learner can more effectively improve learning efficiency by optimizing parameters, thereby achieving the optimal solution in terms of both the accuracy of credit bond trading risk prediction and learning cost, and thus improving the accuracy of bond investment trading risk prediction.

[0071] S104: Based on the risk prediction model, perform risk prediction on the target transaction data during the target credit bond investment transaction process.

[0072] As described above, the credit bond investment transaction risk prediction method provided in this embodiment of the invention collects transaction data during the credit bond investment transaction process. This transaction data includes training set data and prediction set data. Supervised training is performed using the training set data and a support vector machine algorithm to obtain a credit bond risk prediction model. Based on the credit bond risk prediction model, risk prediction is performed on the prediction set data, and the prediction accuracy is determined. The prediction accuracy is used as the fitness value of a cuckoo search algorithm. The cuckoo search algorithm iteratively optimizes the penalty factor and kernel parameters in the credit bond risk prediction model to obtain the risk prediction model. Based on the risk prediction model, risk prediction is performed on target transaction data during the target credit bond investment transaction process. This method improves the prediction accuracy of the risk prediction model and reduces learning costs, thereby increasing the accuracy of credit bond investment transaction risk prediction.

[0073] In one embodiment of the present invention, see Figure 2 Following step S101 of the credit bond investment and trading risk prediction method, the following specific content is included:

[0074] S105: Normalize the training set data and the prediction set data.

[0075] It should be noted that data normalization is a fundamental task in data mining. Different evaluation indicators often have different dimensions and units of measurement. In order to eliminate the influence of dimensions between indicators, data normalization is required to improve the convergence speed and accuracy of the model in subsequent steps.

[0076] In this step, the min-max normalization method is used to process the training set data and the prediction set data to achieve data normalization.

[0077] In one embodiment of the present invention, see Figure 3 Step S103 of the credit bond investment transaction risk prediction method specifically includes the following:

[0078] S1031: Initialize the initial parameters of the cuckoo search algorithm, including: the number of nests, the number of iterations, the search range of the penalty factor, and the search range of the kernel parameter;

[0079] S1032: Randomly generate the initial bird's nest position; the horizontal axis of the initial bird's nest position is the penalty factor c in the credit bond risk prediction model, and the vertical axis is the kernel parameter g in the credit bond risk prediction model;

[0080] S1033: Update the nest location via Levi's flight;

[0081] In this step, the Lévy flight can be viewed as a non-Gaussian random walk behavior, with its step size satisfying a heavy-tailed Lévy stable distribution. During the flight, high-frequency short-distance walks with small strides and occasional long-distance walks with large strides alternate, forming a phenomenon where clusters caused by multiple short-distance walks are separated by occasional large-distance jump walks.

[0082] Applying Levi's flight to intelligent algorithms can expand the search range, enrich population diversity, and reduce the likelihood of getting trapped in local optima.

[0083] S1034: Use the prediction accuracy as the fitness value corresponding to each bird's nest;

[0084] S1035: Output the penalty factor and kernel parameters of the iterative optimization process after reaching the maximum number of iterations.

[0085] In one embodiment of the present invention, see Figure 4 Step S103 of the credit bond investment transaction risk prediction method further includes the following:

[0086] S1036: Compared with the previous generation of Bird's Nest, this replaces the Bird's Nest with low prediction accuracy;

[0087] S1037: Determine whether the generated random number is greater than the host detection probability;

[0088] S1038: If so, randomly change the location of the nest and replace the discovered nest; calculate the fitness value of each nest and determine the current optimal nest and the optimal risk prediction accuracy.

[0089] S1039: If not, calculate the fitness value of each nest and determine the current optimal nest and the optimal risk prediction accuracy.

[0090] S1035: After the optimal risk prediction accuracy is greater than the preset required accuracy, output the penalty factor and kernel parameters of the iterative optimization process;

[0091] The initial parameters also include: host discovery probability.

[0092] It is understandable that optimizing the parameters of SVM based on the CS algorithm involves using the optimal combination of the two SVM parameters, the penalty factor c and the kernel parameter g, as the best solution for the CS algorithm. In the CS algorithm, the parameter pa represents the host discovery probability, which is recommended to be set to 0.25. The maximum number of iterations in the CS algorithm is recommended to be set to 200, and the number of "nests" should be 15.

[0093] In practice, Figure 5 This is a schematic diagram illustrating the entire process of risk prediction methods for credit bond investment and trading. Figure 5In this document, 1-1 is the part that establishes a credit bond risk prediction model and determines the prediction accuracy based on the training set data and the test set data, and 1-2 is the part that optimizes the parameters of the SVM based on the CS algorithm. This is also a schematic diagram of the specific process actually used in step S103 of the credit bond investment and transaction risk prediction method in this embodiment.

[0094] This method for predicting credit bond investment and trading risks based on the CS algorithm for parameter optimization of SVM improves the original SVM model to achieve the optimal solution in terms of improving the accuracy of bond trading risk prediction and reducing learning costs, thereby improving the predictive performance of the method for credit bond investment and trading risks.

[0095] This invention provides a specific implementation of a credit bond investment and trading risk prediction device capable of realizing all the contents of the aforementioned credit bond investment and trading risk prediction method. See [link to relevant documentation]. Figure 6 The credit bond investment and trading risk prediction device specifically includes the following components:

[0096] Data acquisition module 10 is used to collect transaction data during the credit bond investment transaction process. The transaction data includes training set data and prediction set data.

[0097] The training prediction module 20 is used to perform supervised training based on the training set data and the support vector machine algorithm to obtain a credit bond risk prediction model; and to perform risk prediction on the prediction set data based on the credit bond risk prediction model and determine the prediction accuracy of the risk prediction.

[0098] The iterative optimization module 30 is used to use the prediction accuracy as the fitness value of the cuckoo search algorithm, and to perform iterative optimization on the penalty factor and kernel parameters in the credit bond risk prediction model through the cuckoo search algorithm to obtain the risk prediction model.

[0099] The risk prediction module 40 is used to predict the risk of target transaction data in the target credit bond investment transaction process based on the risk prediction model.

[0100] The data acquisition module 10 includes:

[0101] A risk registration unit is used to add a risk registration tag to each piece of data in the transaction data;

[0102] Each risk registration label corresponds to a risk assessment value.

[0103] The iterative optimization module 30 includes:

[0104] An initialization unit is used to initialize the initial parameters of the cuckoo search algorithm. The initial parameters include: the number of nests, the number of iterations, the search range of the penalty factor, and the search range of the kernel parameter.

[0105] An initial bird's nest unit is used to randomly generate the initial bird's nest position; the horizontal axis of the initial bird's nest position is the penalty factor in the credit bond risk prediction model, and the vertical axis is the kernel parameter in the credit bond risk prediction model.

[0106] Update the nest unit, used to update the nest's location via Levi's flight;

[0107] The setting unit is used to use the prediction accuracy as the fitness value corresponding to each bird's nest;

[0108] The first output unit is used to output the penalty factor and kernel parameters of the iterative optimization process after the maximum number of iterations has been reached.

[0109] The iterative optimization module 30 further includes:

[0110] The bird's nest replacement unit is used to compare with the previous generation of bird's nests and replace bird's nests with low prediction accuracy;

[0111] The judgment unit is used to determine whether the generated random number is greater than the host discovery probability; if so, the nest location is randomly changed and the discovered nest is replaced; the fitness value of each nest is calculated and the current optimal nest and the optimal risk prediction accuracy are determined; if not, the fitness value of each nest is calculated and the current optimal nest and the optimal risk prediction accuracy are determined.

[0112] In one embodiment of the present invention, see Figure 7 The credit bond investment and trading risk prediction device further includes:

[0113] The normalization module 50 is used to normalize the training set data and the prediction set data.

[0114] The embodiments of the credit bond investment and trading risk prediction device provided by the present invention can be used to execute the processing flow of the embodiments of the credit bond investment and trading risk prediction method in the above embodiments. Its functions will not be repeated here, but can be referred to the detailed description of the above method embodiments.

[0115] As described above, the credit bond investment transaction risk prediction device provided in this embodiment of the invention collects transaction data during the credit bond investment transaction process. This transaction data includes training set data and prediction set data. Supervised training is performed using the training set data and a support vector machine algorithm to obtain a credit bond risk prediction model. Based on the credit bond risk prediction model, risk prediction is performed on the prediction set data, and the prediction accuracy is determined. The prediction accuracy is used as the fitness value of a cuckoo search algorithm. The cuckoo search algorithm iteratively optimizes the penalty factor and kernel parameters in the credit bond risk prediction model to obtain the risk prediction model. Based on the risk prediction model, risk prediction is performed on target transaction data during the target credit bond investment transaction process. This improves the prediction accuracy of the risk prediction model and reduces learning costs, thereby enhancing the accuracy of credit bond investment transaction risk prediction.

[0116] This application provides an embodiment of an electronic device for implementing all or part of the credit bond investment transaction risk prediction method. The electronic device specifically includes the following components:

[0117] The device comprises a processor, memory, a communications interface, and a bus; wherein the processor, memory, and communications interface communicate with each other via the bus; the communications interface is used to realize information transmission between related devices; the electronic device can be a desktop computer, tablet computer, or mobile terminal, etc., and this embodiment is not limited to these. In this embodiment, the electronic device can be implemented with reference to the embodiments for implementing the credit bond investment transaction risk prediction method and the embodiments for implementing the credit bond investment transaction risk prediction device, the content of which is incorporated herein, and repeated details will not be described again.

[0118] Figure 8 This is a schematic block diagram illustrating the system configuration of the electronic device 9600 according to an embodiment of this application. Figure 8 As shown, the electronic device 9600 may include a central processing unit 9100 and a memory 9140; the memory 9140 is coupled to the central processing unit 9100. It is worth noting that... Figure 8 This is an example; other types of structures can also be used to supplement or replace this structure to achieve telecommunications functions or other functions.

[0119] In one embodiment, the credit bond investment and trading risk prediction function can be integrated into the central processing unit 9100. The central processing unit 9100 can be configured to perform the following controls:

[0120] The process involves collecting transaction data during credit bond investment transactions, including training set data and prediction set data. Supervised training is performed using the training set data and a support vector machine algorithm to obtain a credit bond risk prediction model. Risk prediction is then performed on the prediction set data based on the credit bond risk prediction model, and the prediction accuracy is determined. This prediction accuracy is used as the fitness value of a cuckoo search algorithm. The cuckoo search algorithm iteratively optimizes the penalty factor and kernel parameters in the credit bond risk prediction model to obtain the risk prediction model itself. Finally, risk prediction is performed on target transaction data during the target credit bond investment transaction process based on the risk prediction model.

[0121] As described above, the electronic device provided in the embodiments of this application collects transaction data during the credit bond investment transaction process. This transaction data includes training set data and prediction set data. Supervised training is performed using the training set data and a support vector machine algorithm to obtain a credit bond risk prediction model. Based on the credit bond risk prediction model, risk prediction is performed on the prediction set data, and the prediction accuracy is determined. The prediction accuracy is used as the fitness value of a cuckoo search algorithm. The cuckoo search algorithm iteratively optimizes the penalty factor and kernel parameters in the credit bond risk prediction model to obtain a risk prediction model. Based on the risk prediction model, risk prediction is performed on target transaction data during the target credit bond investment transaction process. This improves the prediction accuracy of the risk prediction model and reduces learning costs, thereby enhancing the accuracy of credit bond investment transaction risk prediction.

[0122] In another embodiment, the credit bond investment and trading risk prediction device can be configured separately from the central processing unit 9100. For example, the credit bond investment and trading risk prediction device can be configured as a chip connected to the central processing unit 9100, and the credit bond investment and trading risk prediction function can be realized through the control of the central processing unit.

[0123] like Figure 8 As shown, the electronic device 9600 may further include: a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It is worth noting that the electronic device 9600 does not necessarily need to include these components. Figure 8 All components shown; in addition, the electronic device 9600 may also include Figure 8 For components not shown, please refer to existing technologies.

[0124] like Figure 8 As shown, the central processing unit 9100, sometimes also referred to as a controller or operating control, may include a microprocessor or other processor device and / or logic device, which receives inputs and controls the operation of various components of the electronic device 9600.

[0125] The memory 9140 may be, for example, one or more of a cache, flash memory, hard drive, removable media, volatile memory, non-volatile memory, or other suitable devices. It may store the aforementioned failure-related information, and also store a program for executing that information. The central processing unit 9100 may execute the program stored in the memory 9140 to perform information storage or processing, etc.

[0126] Input unit 9120 provides input to central processing unit 9100. Input unit 9120 may be, for example, a keypad or touch input device. Power supply 9170 provides power to electronic device 9600. Display 9160 displays images and text. Display may be, for example, an LCD display, but is not limited thereto.

[0127] The memory 9140 can be a solid-state memory, such as a read-only memory (ROM), random access memory (RAM), a SIM card, etc. It can also be a memory that retains information even when power is off, can be selectively erased, and contains more data; examples of this type of memory are sometimes referred to as EPROMs. The memory 9140 can also be some other type of device. The memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 may include an application / function storage unit 9142 for storing application programs and function programs or processes for executing the operation of the electronic device 9600 via the central processing unit 9100.

[0128] The memory 9140 may also include a data storage unit 9143 for storing data, such as contacts, digital data, pictures, sounds, and / or any other data used by the electronic device. The driver storage unit 9144 of the memory 9140 may include various drivers for the electronic device's communication functions and / or for performing other functions of the electronic device (such as messaging applications, address book applications, etc.).

[0129] The communication module 9110 is a transmitter / receiver 9110 that transmits and receives signals via the antenna 9111. The communication module (transmitter / receiver) 9110 is coupled to the central processing unit 9100 to provide input signals and receive output signals, which can be the same as in a conventional mobile communication terminal.

[0130] Based on different communication technologies, multiple communication modules 9110 can be configured in the same electronic device, such as cellular network modules, Bluetooth modules, and / or wireless LAN modules. The communication module (transmitter / receiver) 9110 is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130 to provide audio output via the speaker 9131 and receive audio input from the microphone 9132, thereby realizing typical telecommunications functions. The audio processor 9130 may include any suitable buffer, decoder, amplifier, etc. Additionally, the audio processor 9130 is coupled to a central processing unit 9100, enabling on-device recording via the microphone 9132 and on-device playback of stored sound via the speaker 9131.

[0131] Embodiments of the present invention also provide a computer-readable storage medium capable of implementing all steps of the credit bond investment and transaction risk prediction method in the above embodiments. The computer-readable storage medium stores a computer program that, when executed by a processor, implements all steps of the credit bond investment and transaction risk prediction method in the above embodiments. For example, when the processor executes the computer program, it implements the following steps:

[0132] The process involves collecting transaction data during credit bond investment transactions, including training set data and prediction set data. Supervised training is performed using the training set data and a support vector machine algorithm to obtain a credit bond risk prediction model. Risk prediction is then performed on the prediction set data based on the credit bond risk prediction model, and the prediction accuracy is determined. This prediction accuracy is used as the fitness value of a cuckoo search algorithm. The cuckoo search algorithm iteratively optimizes the penalty factor and kernel parameters in the credit bond risk prediction model to obtain the risk prediction model itself. Finally, risk prediction is performed on target transaction data during the target credit bond investment transaction process based on the risk prediction model.

[0133] As described above, the computer-readable storage medium provided in this embodiment of the invention collects transaction data during the credit bond investment transaction process. This transaction data includes training set data and prediction set data. Supervised training is performed using the training set data and a support vector machine algorithm to obtain a credit bond risk prediction model. Based on the credit bond risk prediction model, risk prediction is performed on the prediction set data, and the prediction accuracy is determined. The prediction accuracy is used as the fitness value of a cuckoo search algorithm. The cuckoo search algorithm iteratively optimizes the penalty factor and kernel parameters in the credit bond risk prediction model to obtain a risk prediction model. Based on the risk prediction model, risk prediction is performed on target transaction data during the target credit bond investment transaction process. This improves the prediction accuracy of the risk prediction model and reduces learning costs, thereby enhancing the accuracy of credit bond investment transaction risk prediction.

[0134] While this invention provides the method operation steps as described in the embodiments or flowcharts, more or fewer operation steps may be included based on conventional or non-inventive labor. The order of steps listed in the embodiments is merely one possible execution order among many and does not represent the only possible execution order. In actual device or client product execution, the methods shown in the embodiments or drawings can be executed sequentially or in parallel (e.g., in a parallel processor or multi-threaded processing environment).

[0135] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, apparatus (systems), or computer program products. Therefore, the embodiments of this specification can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, the invention can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0136] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0137] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0138] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0139] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on its differences from other embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other. This invention is not limited to any single aspect, nor to any single embodiment, nor to any combination and / or substitution of these aspects and / or embodiments. Furthermore, each aspect and / or embodiment of this invention can be used alone or in combination with one or more other aspects and / or embodiments thereof.

[0140] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered within the scope of the claims and specification of the present invention.

Claims

1. A method for predicting investment and trading risks in credit bonds, characterized in that, include: The process of collecting transaction data during the investment and trading of credit bonds includes training set data and prediction set data. The process of collecting transaction data during the investment and trading of credit bonds includes adding a risk registration label to each piece of data in the transaction data. Each risk registration label corresponds to a risk assessment value. Supervised training is performed using the training set data and the support vector machine algorithm to obtain a credit bond risk prediction model; risk prediction is then performed on the prediction set data based on the credit bond risk prediction model, and the prediction accuracy of the risk prediction is determined. The prediction accuracy is used as the fitness value of the Cuckoo Search algorithm. The Cuckoo Search algorithm is used to iteratively optimize the penalty factor and kernel parameters in the credit bond risk prediction model to obtain the risk prediction model. Based on the aforementioned risk prediction model, risk prediction is performed on the target transaction data during the target credit bond investment transaction process; The prediction accuracy is used as the fitness value of the Cuckoo Search algorithm. The Cuckoo Search algorithm is then used to iteratively optimize the penalty factor and kernel parameters in the credit bond risk prediction model to obtain the risk prediction model, which includes: Initialize the initial parameters of the cuckoo search algorithm, including: the number of nests, the number of iterations, the search range of the penalty factor, and the search range of the kernel parameter; The initial bird's nest location is randomly generated; the x-axis of the initial bird's nest location is the penalty factor in the credit bond risk prediction model, and the y-axis is the kernel parameter in the credit bond risk prediction model. The bird updates its nest position by flying through Levi. During the flight, high-frequency short-distance walking with small strides and occasional long-distance walking with large strides alternate, forming a phenomenon in which the clusters caused by multiple short-distance walking are separated by occasional long-distance hopping walking. The prediction accuracy is used as the fitness value for each bird's nest. After reaching the maximum number of iterations, output the penalty factor and kernel parameters of the iterative optimization process; After using the prediction accuracy as the fitness value for each nest, the method further includes: Compared to the previous generation of Bird's Nest, this replaces the Bird's Nest with low prediction accuracy; Determine if the generated random number is greater than the host discovery probability; if so, randomly change the nest location and replace the discovered nest; calculate the fitness value of each nest and determine the current optimal nest and the optimal risk prediction accuracy; if not, calculate the fitness value of each nest and determine the current optimal nest and the optimal risk prediction accuracy. After the optimal risk prediction accuracy is greater than the preset required accuracy, the penalty factor and kernel parameters of the iterative optimization process are output. The initial parameters also include: host discovery probability.

2. The method for predicting the investment and trading risks of credit bonds according to claim 1, characterized in that, Following the transaction data in the aforementioned credit bond investment transaction process, the following is also included: The training set data and the prediction set data are normalized.

3. A risk prediction device for credit bond investment and trading, characterized in that, include: The data acquisition module is used to collect transaction data during the credit bond investment transaction process. The transaction data includes training set data and prediction set data. The data acquisition module includes a risk registration unit, which is used to add a risk registration tag to each piece of data in the transaction data. Each risk registration tag corresponds to a risk assessment value. The training and prediction module is used to perform supervised training based on the training set data and the support vector machine algorithm to obtain a credit bond risk prediction model; and to perform risk prediction on the prediction set data based on the credit bond risk prediction model and determine the prediction accuracy of the risk prediction. The iterative optimization module is used to use the prediction accuracy as the fitness value of the cuckoo search algorithm, and to perform iterative optimization on the penalty factor and kernel parameters in the credit bond risk prediction model through the cuckoo search algorithm to obtain the risk prediction model. The risk prediction module is used to predict the risk of target transaction data in the target credit bond investment transaction process based on the risk prediction model. The iterative optimization module includes: An initialization unit is used to initialize the initial parameters of the cuckoo search algorithm. The initial parameters include: the number of nests, the number of iterations, the search range of the penalty factor, and the search range of the kernel parameter. An initial bird's nest unit is used to randomly generate the initial bird's nest position; the horizontal axis of the initial bird's nest position is the penalty factor in the credit bond risk prediction model, and the vertical axis is the kernel parameter in the credit bond risk prediction model. The nest unit is updated by updating the nest position through Levi's flight. During the flight, high-frequency short-distance walking with small strides and occasional long-distance walking with large strides alternate, forming a phenomenon where the clusters caused by multiple short-distance walks are separated by occasional long-distance hopping walks. The setting unit is used to use the prediction accuracy as the fitness value corresponding to each bird's nest; The first output unit is used to output the penalty factor and kernel parameters of the iterative optimization process after the maximum number of iterations has been reached; The iterative optimization module further includes: The bird's nest replacement unit is used to compare with the previous generation of bird's nests and replace bird's nests with low prediction accuracy; The judgment unit is used to determine whether the generated random number is greater than the host discovery probability; if so, the nest location is randomly changed and the discovered nest is replaced; the fitness value of each nest is calculated and the current optimal nest and the optimal risk prediction accuracy are determined; if not, the fitness value of each nest is calculated and the current optimal nest and the optimal risk prediction accuracy are determined. The second output unit is used to output the penalty factor and kernel parameters of the iterative optimization process after the optimal risk prediction accuracy is greater than the preset required accuracy. The initial parameters also include: host discovery probability.

4. The credit bond investment and trading risk prediction device according to claim 3, characterized in that, Also includes: The normalization module is used to normalize the training set data and the prediction set data.

5. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the credit bond investment transaction risk prediction method as described in claim 1 or 2.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the credit bond investment transaction risk prediction method as described in claim 1 or 2.

Images