Financial transaction risk prediction method and device, equipment and storage medium

Abstract

The invention discloses a financial transaction risk prediction method, apparatus and device, and a storage medium. The method comprises the steps of obtaining a transaction list in a target financial software system and feature data of each transaction; determining a risk parameter value corresponding to each transaction according to a pre-constructed transaction risk parameter table and the feature data; the transaction risk parameter table comprises a plurality of risk factors and corresponding score values of each risk factor under different parameters; and inputting the risk parameter value corresponding to each transaction into a pre-trained target logistic regression model, and outputting a risk prediction value corresponding to each transaction through the target logistic regression model. According to the technical scheme provided by the embodiment of the invention, the high-risk transaction list can be scientifically analyzed to provide reference for project test execution, so that the project test quality of a financial software system is improved, and the production quality of a functional module is guaranteed.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method, apparatus, device and storage medium for predicting financial transaction risks. Background Art

[0002] At present, the complexity, production transaction volume and other characteristics of various financial transactions in financial software systems are different. After the functional modules of the software system are put into production, the risk levels of different transactions are also different. During the project development and testing process of such systems, it is necessary to pay special attention to high-risk transactions and carry out sufficient functional testing and performance testing to ensure that the software functional modules can run smoothly after they are put into production.

[0003] In existing technologies, before functional modules in financial software systems are put into production, testers are usually required to select important transactions based on testing experience and other methods. However, there is a lack of technical means to quantify and predict the risk value of financial transactions. Summary of the Invention

[0004] The present invention provides a financial transaction risk prediction method, device, equipment and storage medium, which can scientifically analyze a list of high-risk transactions for reference in project testing execution, thereby helping to improve the project testing quality of financial software systems and ensure the quality of functional modules put into production.

[0005] According to one aspect of the present invention, a method for predicting financial transaction risk is provided, the method comprising:

[0006] Obtaining a transaction list in a target financial software system and characteristic data of each transaction in the transaction list;

[0007] Determine the risk parameter value corresponding to each transaction based on the pre-constructed transaction risk parameter table and the characteristic data;

[0008] The transaction risk parameter table includes multiple risk factors and the corresponding score value of each risk factor under different parameters;

[0009] The risk parameter value corresponding to each transaction is input into a pre-trained target logistic regression model, and the risk prediction value corresponding to each transaction is output through the target logistic regression model.

[0010] Optionally, after outputting the risk prediction value corresponding to each transaction through the target logistic regression model, the method further includes:

[0011] Arrange the risk prediction values corresponding to all transactions from high to low to obtain the transaction arrangement result;

[0012] The transaction arrangement results and the risk prediction value corresponding to each transaction are sent to the target inspection user.

[0013] Optionally, before obtaining the transaction list in the target financial software system, the following steps are also included:

[0014] Pre-configure multiple risk factors associated with financial transactions, determine the weight value corresponding to each risk factor, and the corresponding score value of each risk factor under different parameters;

[0015] The transaction risk parameter table is constructed based on the mapping relationship between each risk factor, the weight value and the score value.

[0016] Optionally, determining a risk parameter value corresponding to each transaction based on a pre-constructed transaction risk parameter table and the characteristic data includes:

[0017] The characteristic data of each transaction is queried in the transaction risk parameter table, and the risk parameter value corresponding to each transaction is determined based on the query result.

[0018] Optionally, before obtaining the transaction list in the target financial software system, the following steps are also included:

[0019] Acquire multiple transaction samples corresponding to the target financial software system, and divide the multiple transaction samples into a training data set and a test data set;

[0020] Using the training data set, iteratively training the original logistic regression model until the loss of the original logistic regression model on the training data set converges;

[0021] Using the test data set, evaluating the effect of the original logistic regression model;

[0022] If the evaluation result of the original logistic regression model meets the preset standard, the original logistic regression model is used as the target logistic regression model for predicting the financial transaction risk value.

[0023] Optionally, the original logistic regression model is iteratively trained using the training dataset, including:

[0024] Using the mean square error as a loss function, using the training data set, and iteratively training the original logistic regression model according to the loss function;

[0025] During the training process of the original logistic regression model, the loss function is optimized using a gradient descent algorithm.

[0026] Optionally, using the test dataset to evaluate the effectiveness of the original logistic regression model includes:

[0027] The accuracy, confusion matrix, and area under the receiver operating characteristic curve of the original logistic regression model were evaluated using the test data set.

[0028] According to another aspect of the present invention, a financial transaction risk prediction device is provided, the device comprising:

[0029] A data acquisition module, configured to acquire a transaction list in a target financial software system and characteristic data of each transaction in the transaction list;

[0030] A parameter determination module, configured to determine a risk parameter value corresponding to each transaction based on a pre-built transaction risk parameter table and the characteristic data;

[0031] The transaction risk parameter table includes multiple risk factors and the corresponding score value of each risk factor under different parameters;

[0032] The model output module is used to input the risk parameter value corresponding to each transaction into a pre-trained target logistic regression model, and output the risk prediction value corresponding to each transaction through the target logistic regression model.

[0033] According to another aspect of the present invention, an electronic device is provided, comprising:

[0034] at least one processor; and

[0035] a memory communicatively connected to the at least one processor; wherein,

[0036] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the financial transaction risk prediction method described in any embodiment of the present invention.

[0037] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the financial transaction risk prediction method described in any embodiment of the present invention when executed.

[0038] The technical solution provided by the embodiment of the present invention obtains a transaction list in a target financial software system and the characteristic data of each transaction in the transaction list, determines the risk parameter value corresponding to each transaction based on a pre-constructed transaction risk parameter table and the characteristic data, inputs the risk parameter value corresponding to each transaction into a pre-trained target logistic regression model, and outputs the risk prediction value corresponding to each transaction through the target logistic regression model. This technical solution provides a method for quantitatively predicting financial transaction risks without relying on subjective factors such as testing experience. A high-risk transaction list can be analyzed more scientifically for reference in project testing execution, thereby helping to improve the project testing quality of the financial software system and ensure the quality of functional modules put into production.

[0039] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0041] Figure 1 is a flowchart of a financial transaction risk prediction method provided according to an embodiment of the present invention;

[0042] Figure 2 is a flowchart of another financial transaction risk prediction method provided according to an embodiment of the present invention;

[0043] Figure 3 This is a schematic diagram of the structure of a financial transaction risk prediction device provided according to an embodiment of the present invention;

[0044] Figure 4 It is a structural diagram of an electronic device for implementing the financial transaction risk prediction method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0045] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0046] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0047] Figure 1 This is a flowchart of a financial transaction risk prediction method provided by an embodiment of the present invention. This embodiment is applicable to the situation where risk prediction is performed on transactions in a financial software system before the functional modules in the financial software system are put into production. The method can be executed by a financial transaction risk prediction device, which can be implemented in the form of hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method includes:

[0048] Step 110: Obtain a transaction list in the target financial software system and characteristic data of each transaction in the transaction list.

[0049] In this embodiment, optionally, a list of associated transactions can be obtained based on the functional modules to be put into production in the target financial software system. The transaction list can include multiple transactions, and the characteristic data of each transaction can include: whether the transaction involves account movement, the average daily transaction volume of production, the transaction complexity, the number of associated systems that call the transaction, the customer type of the transaction (for example, serving internal customers or external customers), the length of the transaction link, the number of production problems discovered, whether it is a performance measurement transaction, etc.

[0050] Specifically, the link length refers to the tree-like call relationship between methods obtained through dynamic link tracing tools. The interface being called is set to the first level, the first method it calls is the second level, and so on. The maximum number of levels in the system is the link length, and the link length can reflect the complexity of the call.

[0051] Step 120: Determine the risk parameter value corresponding to each transaction based on the pre-constructed transaction risk parameter table and the characteristic data.

[0052] In this embodiment, the transaction risk parameter table includes a plurality of pre-configured risk factors of financial transactions and a score value corresponding to each risk factor under different parameters.

[0053] In this step, specifically, the corresponding risk factor can be obtained from the transaction risk parameter table based on the characteristic data of each transaction, and the score value of the corresponding risk factor under the corresponding parameter can be obtained based on the characteristic value in the characteristic data.

[0054] Step 130: Input the risk parameter value corresponding to each transaction into a pre-trained target logistic regression model, and output the risk prediction value corresponding to each transaction through the target logistic regression model.

[0055] The logistic regression model is a generalized linear regression analysis model that can be applied to fields such as data mining and economic forecasting. The logistic regression model can estimate the probability of an event based on a given set of independent variable data. Since the result is a probability, the range of the dependent variable is between 0 and 1.

[0056] Specifically, in this embodiment, before obtaining a transaction list from the target financial software system and the characteristic data for each transaction in the transaction list, a transaction pool comprising multiple transaction samples can be pre-established. To avoid randomness in the model training results, the samples in the transaction pool can be divided into three equal parts, and a three-fold cross-validation method can be used to train a logistic regression model and evaluate the prediction results, thereby obtaining a target logistic regression model for predicting the risk value of financial transactions.

[0057] In the actual model training process, the training results usually fit the training set better than the data outside the training set, so we usually do not use all the data sets for training. The basic idea of cross-validation is to group the original data, one part as the training set and the other as the validation set. First, the classifier is trained with the training set, and then the trained model is tested with the validation set, which is used as a performance indicator for evaluating the classifier. K-fold cross-validation means dividing the initial sample into K sub-samples, a single sub-sample is retained as the data for validating the model, and the other K-1 samples are used for training. Cross-validation is repeated K times, with each sub-sample validated once. The results of K times are averaged or other combined methods are used to finally obtain a single estimate.

[0058] In this step, after the risk parameter value corresponding to each transaction is input into the target logistic regression model, the target logistic regression model can automatically output the risk prediction value corresponding to each transaction based on the pre-trained model parameters.

[0059] The technical solution provided by the embodiment of the present invention obtains a transaction list in a target financial software system and the characteristic data of each transaction in the transaction list, determines the risk parameter value corresponding to each transaction based on a pre-constructed transaction risk parameter table and the characteristic data, inputs the risk parameter value corresponding to each transaction into a pre-trained target logistic regression model, and outputs the risk prediction value corresponding to each transaction through the target logistic regression model. This technical solution provides a method for quantitatively predicting financial transaction risks without relying on subjective factors such as testing experience. A high-risk transaction list can be analyzed more scientifically for reference in project testing execution, thereby helping to improve the project testing quality of the financial software system and ensure the quality of functional modules put into production.

[0060] Figure 2 A flowchart of another financial transaction risk prediction method provided by an embodiment of the present invention is shown in FIG. Figure 2 As shown, the method includes:

[0061] Step 210: Acquire multiple transaction samples corresponding to the target financial software system, and divide the multiple transaction samples into a training data set and a test data set.

[0062] In this embodiment, multiple transaction samples corresponding to the target financial software system can be obtained, and some of these transaction samples can be extracted as a training dataset. The transaction samples in the training dataset are all scored by multiple experts in the field through a back-to-back evaluation method. The resulting scores are continuous values between 0 and 1.

[0063] Step 220: Use the training data set to iteratively train the original logistic regression model until the loss of the original logistic regression model on the training data set converges.

[0064] In one implementation of this embodiment, the original logistic regression model is iteratively trained using the training data set, including: using the mean square error as the loss function, using the training data set, and iteratively training the original logistic regression model according to the loss function; during the training process of the original logistic regression model, the loss function is optimized using a gradient descent algorithm.

[0065] In a specific embodiment, it is assumed that the risk parameter value corresponding to a transaction sample in the training data set is a vector The original logistic regression model can be expressed as:

[0066]

[0067] Where y represents the risk prediction value, represents the model weight, and b represents the model bias. The purpose of model training is to obtain the risk parameter value Accurately predict the risk value y and b.

[0068] In the process of iteratively training the original logistic regression model using the training data set, the mean square error can be used as the loss function, which is expressed as follows:

[0069]

[0070] Among them, n represents the number of samples, y i represents the risk prediction value of the i-th sample, Represents the true risk value of the i-th sample. The original logistic regression model can use the gradient descent algorithm to optimize the loss function, which is expressed as follows:

[0071]

[0072] Where f(θ) is the loss function, the optimization algorithm aims to find the parameters that minimize f(θ), η is the learning rate, and ▽ represents the derivative of f(θ). The parameter θ is gradually optimized through iteration until a satisfactory accuracy or number of iterations is achieved. In this embodiment, an adaptive learning rate can be used for model training. The initial learning rate is set to 0.1. When the loss no longer decreases, the learning rate is reduced to half the current learning rate. When the loss no longer decreases after reducing the learning rate, the model is considered to have reached convergence.

[0073] Step 230: Use the test data set to evaluate the effectiveness of the original logistic regression model. If the evaluation result of the original logistic regression model meets the preset standard, the original logistic regression model is used as the target logistic regression model for predicting the financial transaction risk value.

[0074] In one implementation of this embodiment, the test data set is used to evaluate the effectiveness of the original logistic regression model, including: using the test data set to evaluate the accuracy, confusion matrix, and area under the receiver operating characteristic curve (ROC) (Area Under the Curve, AUC) of the original logistic regression model.

[0075] Specifically, when the original logistic regression model reaches convergence on the training dataset, training is stopped and the model's performance is evaluated. For each evaluation metric, a reference value can be pre-set as a passing criterion. If the model performs better than the reference value, it is considered to have passed the evaluation and can be put into use.

[0076] The confusion matrix, also known as the error matrix, is a standard format for representing accuracy assessments, expressed as an n-row, n-column matrix. Each column in the confusion matrix represents the predicted category, and the total number in each column represents the number of data instances predicted to be of that category. Each row represents the true category of the data, and the total number of data instances in each row represents the number of data instances of that category. From the confusion matrix, more advanced classification metrics can be derived: accuracy, correctness, recall, specificity, and sensitivity.

[0077] The ROC curve is a graph plotted against a series of different binary classification methods (cutoff values or decision thresholds), with the true positive rate (sensitivity) as the vertical axis and the false positive rate (1-specificity) as the horizontal axis. The AUC value is defined as the area under the ROC curve. It is used as a model evaluation metric because the ROC curve often does not clearly indicate which classifier performs better. As a numerical value, the classifier with a larger AUC is more effective.

[0078] Step 240: Obtain a transaction list in the target financial software system and characteristic data of each transaction in the transaction list.

[0079] Step 250: Determine the risk parameter value corresponding to each transaction based on the pre-constructed transaction risk parameter table and the characteristic data.

[0080] In one implementation of this embodiment, before obtaining the transaction list in the target financial software system, it also includes: pre-configuring multiple risk factors associated with financial transactions, and determining the weight value corresponding to each risk factor, as well as the score value corresponding to each risk factor under different parameters; constructing the transaction risk parameter table based on the mapping relationship between each risk factor and the weight value and the score value.

[0081] In a specific embodiment, eight risk factors associated with financial transactions may be pre-configured, and a transaction risk parameter table as shown in Table 1 may be constructed:

[0082] Table 1

[0083]

[0084]

[0085] As shown in Table 1, the transaction risk parameter table records the weight value corresponding to each risk factor, as well as the score value of each risk factor under different parameters (such as Option 1, Option 2, Option 3, etc.).

[0086] In this step, the risk parameter value corresponding to each transaction is determined based on the pre-constructed transaction risk parameter table and the characteristic data, including: querying the characteristic data of each transaction in the transaction risk parameter table, and determining the risk parameter value corresponding to each transaction based on the query result.

[0087] Specifically, if a transaction's feature data involves account turnover, the corresponding score for the risk factor "Whether Account Loans Are Involved" is F1S1; if it does not involve account turnover, the corresponding score for the risk factor "Whether Account Loans Are Involved" is F1S2. If a transaction's feature data ranks in the top 1-10 by average daily trading volume, the corresponding score for the risk factor "Ranking of Average Daily Trading Volume" is F2S1. If it ranks in the top 11-20, the corresponding score is F2S2. If it ranks below the top 20, the corresponding score is F2S3.

[0088] Step 260: Input the risk parameter value corresponding to each transaction into a pre-trained target logistic regression model, and output the risk prediction value corresponding to each transaction through the target logistic regression model.

[0089] In this step, for the transaction A to be evaluated in the transaction list, its risk parameter value can be obtained according to Table 1 above And input this risk parameter value into the target logistic regression model to obtain the predicted risk value y a .

[0090] Step 270: Arrange the risk prediction values corresponding to all transactions in descending order to obtain a transaction arrangement result, and send the transaction arrangement result and the risk prediction value corresponding to each transaction to the target inspection user.

[0091] In this embodiment, the target inspection user may be a project tester or test equipment corresponding to the target financial software system, etc., for reference in project test execution, and this embodiment does not limit this.

[0092] The technical solution provided by an embodiment of the present invention obtains multiple transaction samples corresponding to a target financial software system, divides the multiple transaction samples into a training data set and a test data set, iteratively trains an original logistic regression model using the training data set, and evaluates the effectiveness of the original logistic regression model using the test data set. If the evaluation result meets a preset standard, the original logistic regression model is used as the target logistic regression model. A transaction list and characteristic data of each transaction in the target financial software system are obtained, and a risk parameter value corresponding to each transaction is determined based on a pre-constructed transaction risk parameter table and characteristic data. The risk parameter value corresponding to each transaction is input into the target logistic regression model to obtain a risk prediction value. The risk prediction values corresponding to all transactions are arranged in descending order, and the transaction arrangement results and the risk prediction value corresponding to each transaction are sent to the target inspection user. This technical solution provides a method for quantitatively predicting financial transaction risks without relying on subjective factors such as testing experience. A high-risk transaction list can be more scientifically analyzed for reference in project testing execution, thereby helping to improve the project testing quality of the financial software system and ensure the production quality of functional modules.

[0093] Figure 3 This is a schematic diagram of the structure of a financial transaction risk prediction device provided by an embodiment of the present invention, wherein the device is applied to an electronic device, such as Figure 3 As shown, the device includes: a data acquisition module 310, a parameter determination module 320 and a model output module 330.

[0094] The data acquisition module 310 is used to obtain a transaction list in the target financial software system and characteristic data of each transaction in the transaction list;

[0095] Parameter determination module 320, for determining the risk parameter value corresponding to each transaction based on the pre-built transaction risk parameter table and the characteristic data;

[0096] The transaction risk parameter table includes multiple risk factors and the corresponding score value of each risk factor under different parameters;

[0097] The model output module 330 is used to input the risk parameter value corresponding to each transaction into a pre-trained target logistic regression model, and output the risk prediction value corresponding to each transaction through the target logistic regression model.

[0098] The technical solution provided by the embodiment of the present invention obtains a transaction list in a target financial software system and the characteristic data of each transaction in the transaction list, determines the risk parameter value corresponding to each transaction based on a pre-constructed transaction risk parameter table and the characteristic data, inputs the risk parameter value corresponding to each transaction into a pre-trained target logistic regression model, and outputs the risk prediction value corresponding to each transaction through the target logistic regression model. This technical solution provides a method for quantitatively predicting financial transaction risks without relying on subjective factors such as testing experience. A high-risk transaction list can be analyzed more scientifically for reference in project testing execution, thereby helping to improve the project testing quality of the financial software system and ensure the quality of functional modules put into production.

[0099] Based on the above embodiment, the device further includes:

[0100] A transaction ranking module is used to sort the risk prediction values corresponding to all transactions in descending order to obtain a transaction ranking result; and send the transaction ranking result and the risk prediction value corresponding to each transaction to the target inspection user;

[0101] A risk factor configuration module is used to pre-configure multiple risk factors associated with financial transactions, determine the weight value corresponding to each risk factor, and the score value corresponding to each risk factor under different parameters; and construct the transaction risk parameter table based on the mapping relationship between each risk factor, the weight value, and the score value;

[0102] A data set partitioning module is used to obtain multiple transaction samples corresponding to the target financial software system and divide the multiple transaction samples into a training data set and a test data set;

[0103] A model training module is used to iteratively train the original logistic regression model using the training data set until the loss of the original logistic regression model on the training data set converges;

[0104] The model evaluation module is used to evaluate the effectiveness of the original logistic regression model using the test data set; if the evaluation result of the original logistic regression model meets the preset standard, the original logistic regression model is used as the target logistic regression model for predicting the risk value of financial transactions.

[0105] The model training module includes:

[0106] The iterative training unit is used to use the mean square error as a loss function, use the training data set, and iteratively train the original logistic regression model according to the loss function; during the training process of the original logistic regression model, the gradient descent algorithm is used to optimize the loss function.

[0107] The model evaluation module includes:

[0108] An indicator evaluation unit is used to evaluate the accuracy, confusion matrix, and area under the receiver operating characteristic curve of the original logistic regression model using the test data set.

[0109] The parameter determination module 320 includes:

[0110] The parameter table query unit is used to query the characteristic data of each transaction in the transaction risk parameter table and determine the risk parameter value corresponding to each transaction based on the query result.

[0111] The above device can execute the methods provided by all the above embodiments of the present invention, and has the corresponding functional modules and beneficial effects of executing the above methods. For technical details not fully described in the embodiments of the present invention, please refer to the methods provided by all the above embodiments of the present invention.

[0112] Figure 4 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0113] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0114] Multiple 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, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a 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.

[0115] Processor 11 can be any general-purpose and / or specialized processing component with 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, digital signal processors (DSPs), and any other suitable processor, controller, microcontroller, etc. Processor 11 executes the various methods and processes described above, such as the financial transaction risk prediction method.

[0116] In some embodiments, the financial transaction 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 on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the financial transaction risk prediction method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to execute the financial transaction risk prediction method in any other suitable manner (e.g., via firmware).

[0117] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0118] Computer programs 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, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0119] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0120] To provide interaction with a user, the systems and techniques described herein 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 the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the 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 can be received in any form (including acoustic input, voice input, or tactile input).

[0121] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, 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: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0122] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0123] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0124] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A financial transaction risk prediction method, characterized in that: The method comprises: Obtaining a transaction list in a target financial software system and characteristic data of each transaction in the transaction list; Determine the risk parameter value corresponding to each transaction based on the pre-constructed transaction risk parameter table and the characteristic data; The transaction risk parameter table includes multiple risk factors and the corresponding score value of each risk factor under different parameters; The risk parameter value corresponding to each transaction is input into a pre-trained target logistic regression model, and the risk prediction value corresponding to each transaction is output through the target logistic regression model.

2. The method according to claim 1, characterized in that After outputting the risk prediction value corresponding to each transaction through the target logistic regression model, the method further includes: Arrange the risk prediction values corresponding to all transactions from high to low to obtain the transaction arrangement result; The transaction arrangement results and the risk prediction value corresponding to each transaction are sent to the target inspection user.

3. The method according to claim 1, characterized in that Before obtaining the transaction list in the target financial software system, it also includes: Pre-configure multiple risk factors associated with financial transactions, determine the weight value corresponding to each risk factor, and the corresponding score value of each risk factor under different parameters; The transaction risk parameter table is constructed based on the mapping relationship between each risk factor, the weight value and the score value.

4. The method according to claim 1, wherein Determine the risk parameter value corresponding to each transaction based on the pre-built transaction risk parameter table and the characteristic data, including: The characteristic data of each transaction is queried in the transaction risk parameter table, and the risk parameter value corresponding to each transaction is determined based on the query result.

5. The method according to claim 1, wherein Before obtaining the transaction list in the target financial software system, it also includes: Acquire multiple transaction samples corresponding to the target financial software system, and divide the multiple transaction samples into a training data set and a test data set; Using the training data set, iteratively training the original logistic regression model until the loss of the original logistic regression model on the training data set converges; Using the test data set, evaluating the effect of the original logistic regression model; If the evaluation result of the original logistic regression model meets the preset standard, the original logistic regression model is used as the target logistic regression model for predicting the financial transaction risk value.

6. The method according to claim 5, characterized in that Using the training dataset, the original logistic regression model is iteratively trained, including: Using the mean square error as a loss function, using the training data set, and iteratively training the original logistic regression model according to the loss function; During the training process of the original logistic regression model, the loss function is optimized using a gradient descent algorithm.

7. The method according to claim 5, characterized in that Using the test data set, the effect of the original logistic regression model is evaluated, including: The accuracy, confusion matrix, and area under the receiver operating characteristic curve of the original logistic regression model were evaluated using the test data set.

8. A financial transaction risk prediction device, characterized in that: The device comprises: A data acquisition module, configured to acquire a transaction list in a target financial software system and characteristic data of each transaction in the transaction list; A parameter determination module, configured to determine a risk parameter value corresponding to each transaction based on a pre-built transaction risk parameter table and the characteristic data; The transaction risk parameter table includes multiple risk factors and the corresponding score value of each risk factor under different parameters; The model output module is used to input the risk parameter value corresponding to each transaction into a pre-trained target logistic regression model, and output the risk prediction value corresponding to each transaction through the target logistic regression model.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the financial transaction risk prediction method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the financial transaction risk prediction method according to any one of claims 1 to 7 when executed.

Images