Default risk judgment model training method and default risk judgment method

Abstract

The application discloses a training method of a default risk judgment model and a default risk judgment method, and relates to the technical fields of artificial intelligence and financial technology. The main method comprises the following steps: performing missing degree analysis on desensitized credit data to obtain high-value features in the desensitized credit data; performing coarse classification on the desensitized credit data based on the high-value features through a non-neural network model to obtain training samples for weak supervision learning; and performing weak supervision training on a neural network model according to the training samples to obtain a default risk prediction model. The embodiment of the application can improve the availability of the desensitized credit data.

Description

Technical Field

[0001] The present invention relates to the fields of artificial intelligence and financial technology, and in particular to a training method for a default risk judgment model and a method for judging default risk. Background Art

[0002] For many banks, loan revenue accounts for the vast majority of their total revenue, making it crucial to their economic performance. However, lending also carries certain risks, the most significant of which is credit risk—the risk that customers will not repay their loans on time. Therefore, banks need to conduct risk assessments when granting loans to mitigate the risk of loan defaults. Many banks are using machine learning technology to strengthen loan risk management, which can be applied across multiple aspects of loan risk management, including customer credit assessment, fraud prevention, and risk management.

[0003] Machine learning is highly data-dependent. When the data is rational (large, clean, and low-bias), machine learning can quickly and easily enable the model to adaptively learn the data features, thereby predicting the corresponding risks. However, due to practical reasons (computing power limitations and the cost of data acquisition) (data requires manual labeling, which can still have accuracy issues and privacy concerns), the data obtained often contains missing values ​​and noise.

[0004] This problem is particularly acute in loan risk management scenarios. Personal information collected for loan defaults involves multiple dimensions and a wide range of content, often raising privacy concerns. Consequently, the collected data may contain significant gaps. Furthermore, much of the data must be desensitized upon collection, making it difficult to determine the specific meaning of each feature in the data during machine learning. This further reduces data usability and hinders subsequent machine learning and risk prediction. Summary of the Invention

[0005] The present invention provides a training method for a default risk judgment model and a default risk judgment method to improve the availability of desensitized credit data.

[0006] According to one aspect of the present invention, a method for training a default risk prediction model is provided, comprising:

[0007] Perform a missing degree analysis on the desensitized credit data to obtain high-value features in the desensitized credit data:

[0008] Based on the high-value features, the desensitized credit data is roughly classified using a non-neural network model to obtain training samples for weakly supervised learning;

[0009] The neural network model is weakly supervised trained according to the training samples to obtain a default risk prediction model.

[0010] According to another aspect of the present invention, a method for predicting default risk is provided, comprising:

[0011] Preprocess the credit data of the user to be predicted to obtain the data to be predicted;

[0012] Based on the data to be predicted, obtaining a default risk prediction result of the user to be predicted according to the default risk prediction model;

[0013] The default risk prediction model is obtained by training the default risk prediction model according to any embodiment of the present invention.

[0014] According to another aspect of the present invention, a training device for a default risk prediction model is provided, comprising:

[0015] The analysis module is used to analyze the degree of missingness of the desensitized credit data and obtain high-value features in the desensitized credit data:

[0016] A classification module, configured to perform coarse classification of the desensitized credit data using a non-neural network model based on the high-value features to obtain training samples for weakly supervised learning;

[0017] The training module is used to perform weak supervision training on the neural network model according to the training samples to obtain a default risk prediction model.

[0018] According to another aspect of the present invention, there is provided a device for predicting default risk, comprising:

[0019] A preprocessing module, used to preprocess the credit data of the user to be predicted to obtain the data to be predicted;

[0020] A prediction module, configured to obtain a default risk prediction result of the user to be predicted based on the data to be predicted and according to the default risk prediction model;

[0021] The default risk prediction model is obtained by training using the default risk prediction model training device described in any embodiment of the present invention.

[0022] According to another aspect of the present invention, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the method for training a default risk judgment model or the method for predicting default risk according to any embodiment of the present invention.

[0023] According to another aspect of the present invention, an electronic device is provided, comprising: 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 method for training a default risk judgment model or the method for predicting default risk as described in any embodiment of the present invention.

[0024] 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 training method of the default risk judgment model or the default risk prediction method described in any embodiment of the present invention when executed.

[0025] The embodiment of the present invention successfully converts desensitized credit data into training samples for weakly supervised training through feature screening and multi-model fusion, thereby improving the availability of desensitized credit data and reducing the impact of the low quality of desensitized credit data on subsequent machine learning.

[0026] 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

[0027] 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.

[0028] Figure 1 is a flowchart of a method for training a default risk prediction model according to one embodiment of the present invention;

[0029] Figure 2A is a flowchart of a method for training a default risk prediction model according to another embodiment of the present invention;

[0030] Figure 2B is a statistical diagram of missing ratios provided according to another embodiment of the present invention;

[0031] Figure 3 is a flow chart of a method for predicting default risk according to one embodiment of the present invention;

[0032] Figure 42 is a schematic structural diagram of a training device for a default risk prediction model provided according to another embodiment of the present invention;

[0033] Figure 5 is a schematic structural diagram of a default risk prediction device provided according to another embodiment of the present invention;

[0034] Figure 6 It is a schematic structural diagram of an electronic device implementing an embodiment of the present invention. DETAILED DESCRIPTION

[0035] 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.

[0036] It should be noted that the terms "first," "second," and the like in the present invention are used to distinguish similar objects and are not necessarily used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable 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," "having," and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to these processes, methods, products, or apparatuses.

[0037] Figure 1 This is a flowchart of a method for training a default risk prediction model provided by one embodiment of the present invention. This embodiment is applicable to the collection of industry-disclosed and desensitized credit data and the use of machine learning based on this data. The method can be executed by a training device for a default risk prediction model, which can be implemented in the form of hardware and / or software and can be configured in an electronic device with corresponding data processing capabilities. Figure 1 As shown, the method includes:

[0038] S110: Analyze the degree of missingness of the desensitized credit data to obtain high-value features in the desensitized credit data.

[0039] S120. Based on the high-value features, the desensitized credit data is roughly classified using a non-neural network model to obtain training samples for weakly supervised learning.

[0040] S130. Perform weak supervision training on the neural network model according to the training samples to obtain a default risk prediction model.

[0041] Weakly supervised learning is a machine learning method that uses partially or incompletely labeled data to train models, addressing the problem of insufficient labeled data. Unlike traditional supervised learning, weakly supervised learning does not require all data to be labeled. Instead, it can learn useful patterns and knowledge from partially labeled data. In weakly supervised learning, only a portion of the sample data is labeled, leaving some data unlabeled (incomplete supervision); sample data is given only coarse-grained labels (inexact supervision); and labels are not always correct (imprecise supervision). A neural network can be viewed as a complex nonlinear function fitting model. It learns the relationship between input and output, fitting a function that enables the neural network to predict the corresponding output for a given input. Each layer of a neural network can be viewed as a complex nonlinear function. By combining multiple layers of neurons, a neural network can fit very complex functional relationships. It learns to analyze and process input data by mimicking the neural network of the human brain to solve complex problems. Neural networks typically consist of multiple layers of neurons, each connected by weights. Training is performed using the backpropagation algorithm to minimize a loss function, enabling the neural network to predict the output. Neural networks can perform weakly supervised learning because the trained models are all high-dimensional vectors. Prediction errors occur because the vectors are biased. However, since the training and test data are independent and identically distributed, we can modify the direction of the output vectors in the test set based on the training data.

[0042] Specifically, we obtain credit data whose key information disclosed by the credit platform has been desensitized. These desensitized credit data usually contain multiple features (such as work, bank statements, identity, age, income, address, etc.), but because they have been desensitized, testers can no longer know the actual meaning of each feature. We analyze the features of the desensitized credit data one by one to determine the missing ratio of each feature. For features with a large proportion of missing data, these features will cause certain interference to the subsequent coarse classification. Therefore, we choose to eliminate these features and no longer use them in the coarse classification. The remaining features are used as high-value features, and only the high-value features of the desensitized credit data are used in the coarse classification.

[0043] A non-neural coarse classification model is selected, and high-value features in the desensitized credit data are used as input features for the coarse classification model. Each sample in the desensitized credit data is classified using the coarse classification model, obtaining a coarse classification label for each sample in the desensitized credit data. These coarse classification labels are then attached to the corresponding samples to obtain training samples for weakly supervised learning.

[0044] Select a suitable network knot as the underlying structure of the neural network model, train the rough classification label through the training sample with the rough classification label, and test and verify the neural network using the test set and the verification set. After passing the test and verification, the neural network is determined as the default risk prediction model.

[0045] The embodiment of the application converts the desensitized credit data into weakly supervised training samples through feature screening and multi-model fusion, improves the availability of the desensitized credit data, and reduces the influence of low desensitized credit data quality on subsequent machine learning.

[0046] Figure 2A A flowchart of a training method of a default risk prediction model is provided for another embodiment of the application. The embodiment is optimized and improved on the basis of the above-mentioned embodiment. As shown in the figure, Figure 2A The method comprises the following steps:

[0047] S210, distribution statistics is performed on each feature in the desensitized credit data to obtain missing features with missing values and missing proportions of the missing features.

[0048] S220, low-value features in the missing features are determined according to the missing proportions, and other features except the low-value features are determined as high-value features.

[0049] Specifically, distribution feature statistics is performed on each feature in the desensitized credit data to check whether the bias of a feature is particularly large. It can be seen that the distribution of the loan data is still seriously left-biased. It can be concluded that the source of the left bias is that most of the customers have consistent conditions, such as low professional titles, low annual income, and no or few unsettled credit limits in the credit archives of most customers. These are the user portraits that are more consistent with the general routine of ordinary customers, so the model needs to focus on these customers to obtain a classification result as accurately as possible. According to the bias result, missing features with missing values are further determined, and missing proportions of the missing features are calculated. The higher the missing proportion, the greater the negative impact of the feature on subsequent rough classification. A missing proportion threshold can be set to determine low-value features with a missing proportion lower than the threshold. The missing features can also be sorted in descending order of the missing proportions, and the missing features at the front of the sorted list are determined as low-value features. After determining the low-value features, the remaining features are high-value features. By screening the features according to the quantitative missing proportions, the screening accuracy of the high and low values of the features is improved.

[0050] Optionally, the determination of the low-value features in the missing features according to the missing proportions comprises:

[0051] Draw a statistical diagram of the missing proportion according to the missing proportion;

[0052] The missing ratio statistical diagram is pushed to the tester, and the low-value features determined by the tester are obtained.

[0053] Specifically, such as Figure 2B As shown, a missing ratio statistical diagram can be drawn based on the missing ratio of each missing feature. The diagram shows the features with missing values ​​and the corresponding missing ratio. Testers can manually select some features as low-value features based on actual conditions. By manually participating in the screening of low-value features, the accuracy of low-value feature screening can be further improved.

[0054] S230: Using the high-value features as extraction features for the desensitized credit data, and fine-tuning the non-neural network model using the desensitized credit data to obtain a coarse classification model.

[0055] S240. Determine a coarse classification label for each sample in the desensitized credit data according to the coarse classification model; and construct a weakly supervised training sample according to the coarse classification label for each sample in the desensitized credit data.

[0056] Specifically, a pre-built non-neural network model is selected as the base model. By fine-tuning the non-neural network model using desensitized credit data, a coarse classification model can be obtained. This eliminates the need to train the coarse classification model from scratch, greatly improving the efficiency of coarse classification.

[0057] Optionally, the number of the coarse classification models is at least two, and determining the coarse classification label of each sample in the desensitized credit data according to the coarse classification model includes:

[0058] For each sample in the desensitized credit data, obtaining the classification results of each coarse classification model for the sample; the classification results include the probability that the sample belongs to each category;

[0059] The classification results are fused to obtain a rough classification label of the sample.

[0060] Specifically, non-neural network models with different structures are fine-tuned to generate multiple coarse classification models. Each sample in the desensitized credit data is fed into different coarse classification models to obtain multiple classification results. These classification results are then fused using methods such as voting, averaging, and weighted averaging to obtain the final coarse classification label for the sample. By designing and using multiple coarse classification models, overfitting can be reduced, generalization capability can be improved, and classification stability can be enhanced.

[0061] For example, the Extreme Gradient Boosting (XGboost) decision tree model and the Support Vector Machine (SVM) model can be used as non-neural network models in the coarse classification, and greedy parameter adjustment can be used before the coarse classification to iteratively fine-tune both as much as possible to achieve the best model effect.

[0062] Greedy parameter tuning is an iterative parameter optimization method that adjusts only one parameter at a time while keeping other parameters unchanged to observe the impact of that parameter on model performance. The specific steps are as follows:

[0063] 1. Initialization parameters: First, set an initial value for each parameter.

[0064] 2. Single parameter tuning: Select a parameter and adjust its value while keeping other parameters constant to observe the changes in model performance. Typically, we will try multiple parameters within the range of possible values ​​to select the parameter value that optimizes model performance.

[0065] 3. Iterative Tuning: Repeat step 2 until all parameters have been tuned once. Then, start tuning again from scratch until the model performance no longer improves significantly.

[0066] The formula for greedy parameter adjustment can be expressed as:

[0067]

[0068] XGBoost, or eXtreme Gradient Boosting, is a highly efficient gradient boosting decision tree algorithm. The training process of the boosting method is step-by-step: base models are trained one by one, the training set of the base models is transformed according to a specific strategy, and then the predictions of all the base models are linearly combined to produce the final prediction.

[0069] XGBoost is an additive model composed of k base models. Assume that the tree model to be trained in the tth iteration is f t (x), then:

[0070]

[0071] in, is the prediction result of sample i after the tth iteration, is the prediction result of the first t-1 trees, f t (x i ) is the model (function) of the t-th tree. The loss function of XGboost can be obtained by the predicted value and the true value yi To express:

[0072]

[0073] Here, n is the number of samples.

[0074] We know that the prediction accuracy of a model is determined by both its bias and variance. The loss function represents the model's bias. To minimize the variance, a regularization term needs to be added to the objective function to prevent overfitting. Therefore, the objective function consists of the model's loss function L and the regularization term Ω, which suppresses model complexity. The objective function is defined as follows:

[0075]

[0076] Here, n is the number of samples.

[0077] Among them, Ω(f i ) is to sum the complexity of all t trees and add it to the objective function as a regularization term to prevent the model from overfitting.

[0078] Support Vector Machine (SVM) is a supervised learning model widely used in classification and regression tasks. In the classification problem, SVM tries to find a hyperplane that maximizes the gap between two classes. This hyperplane is called the maximum margin hyperplane. For our final binary classification problem, where each sample x i There is a label y i ∈-1,1, linearly separable SVM tries to find a hyperplane ω T x + b = 0, so that the predicted values ​​of all positive samples are greater than 1 and the predicted values ​​of all negative samples are less than -1. In other words, SVM tries to maximize the following interval:

[0079]

[0080] To find this maximum margin hyperplane, SVM needs to minimize the following loss function:

[0081]

[0082] The following constraints must also be met:

[0083]

[0084] Here ||ω|| 2 is the L2 norm of the weight vector ω, which is used to control the complexity of the model and prevent overfitting. iis to deal with the slack variables introduced by linear inseparability, and C is the penalty parameter used to control the balance between model complexity and classification error.

[0085] S250. Perform weak supervision training on the neural network model according to the training samples to obtain a default risk prediction model.

[0086] The embodiment of the present invention selects an already constructed non-neural network model as a basic model, eliminating the need to train a coarse classification model from scratch, thereby greatly improving the efficiency of coarse classification.

[0087] Figure 3 This is a flow chart of a method for predicting default risk provided by one embodiment of the present invention. This embodiment is applicable to situations where a bank predicts a user's default risk in advance before lending to the user. This method can be executed by a default risk prediction device, which can be implemented in the form of hardware and / or software and can be configured in an electronic device with corresponding data processing capabilities. Figure 3 As shown, the method includes:

[0088] S310: Preprocess the credit data of the user to be predicted to obtain data to be predicted.

[0089] S320: Based on the data to be predicted, obtain a default risk prediction result of the user to be predicted according to the default risk prediction model.

[0090] Wherein, the default risk prediction model is obtained by training the default risk prediction model according to any embodiment of the present invention.

[0091] Specifically, the credit data of the user to be predicted is obtained from various sources (such as bank records, credit reporting agencies, etc.), and the credit data is preprocessed as necessary (such as feature selection and standardization). The preprocessed user data to be predicted is input into the trained default risk prediction model to obtain the default risk prediction result. The prediction result may be the probability of default or a direct binary classification result (default / non-default). If the prediction result is the probability of default, a threshold can be set based on business rules to determine the final prediction category. In addition, the performance of the model must be evaluated regularly, and the model parameters must be adjusted or the model must be retrained in a timely manner as market conditions and individual behavior patterns change.

[0092] The embodiment of the present invention uses a pre-trained default risk prediction model to predict the user's default risk before lending, thereby achieving efficient and accurate screening of loan-eligible users and improving the economic benefits of lending.

[0093] Based on the above embodiment, optionally, obtaining the default risk prediction result of the user to be predicted based on the data to be predicted and according to the default risk prediction model includes:

[0094] Obtaining preliminary classification results of the data to be predicted through a coarse classification model;

[0095] The data to be predicted and the preliminary classification results are input into a default risk prediction model to obtain a default risk prediction result of the user to be predicted.

[0096] Specifically, model cascading refers to connecting multiple models in series, with the output of the previous model serving as the input of the next model, forming a multi-stage processing flow. If computing resources and hardware equipment permit, the coarse classification model used in the training process can also be deployed and cascaded with the default risk prediction model. Before the data to be predicted is input into the default risk prediction model, it is first input into the coarse classification model to obtain the preliminary classification results of the coarse classification model. The preliminary classification results are then input into the default risk prediction model together with the data to be predicted. By cascading the coarse classification model and the default risk prediction model, the default risk prediction model's ability to predict default risk is improved.

[0097] Figure 4 This is a structural diagram of a training device for a default risk prediction model provided by another embodiment of the present invention. Figure 3 As shown, the device includes:

[0098] The analysis module 410 is used to analyze the degree of missingness of the desensitized credit data and obtain high-value features in the desensitized credit data:

[0099] A classification module 420 is configured to perform a rough classification of the desensitized credit data using a non-neural network model based on the high-value features to obtain training samples for weakly supervised learning;

[0100] The training module 430 is used to perform weak supervision training on the neural network model according to the training samples to obtain a default risk prediction model.

[0101] The training device for the default risk prediction model provided by the embodiment of the present invention can execute the training method for the default risk prediction model provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0102] Optionally, the analysis module 410 includes:

[0103] The statistical unit is used to perform distribution statistics on each feature in the desensitized credit data to obtain missing features with missing values ​​and the missing ratio of each missing feature;

[0104] A determining unit is configured to determine low-value features among the missing features according to the missing ratio, and determine other features other than the low-value features as high-value features.

[0105] Optionally, the statistical unit is specifically used to: draw a missing ratio statistical diagram according to the missing ratio; push the missing ratio statistical diagram to the tester, and obtain the low-value features determined by the tester

[0106] Optionally, the classification module 420 includes:

[0107] a fine-tuning unit, configured to use the high-value features as extracted features of the desensitized credit data, and fine-tune the non-neural network model using the desensitized credit data to obtain a coarse classification model;

[0108] a classification unit, configured to determine a coarse classification label for each sample in the desensitized credit data according to the coarse classification model;

[0109] A construction unit is used to construct a weakly supervised training sample based on the coarse classification label of each sample in the desensitized credit data.

[0110] Optionally, the number of the coarse classification models is at least two, and the classification unit is specifically used to: for each sample in the desensitized credit data, obtain the classification results of each coarse classification model for the sample; the classification results include the probability that the sample belongs to each type; and fuse the classification results to obtain the coarse classification label of the sample.

[0111] The training device for the default risk prediction model further described can also execute the training method for the default risk prediction model provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0112] Figure 5 This is a schematic diagram of the structure of a default risk prediction device provided by another embodiment of the present invention. Figure 5 As shown, the device includes:

[0113] A preprocessing module 510 is used to preprocess the credit data of the user to be predicted to obtain the data to be predicted;

[0114] A prediction module 520 is configured to obtain a default risk prediction result of the user to be predicted based on the data to be predicted and according to the default risk prediction model;

[0115] Wherein, the default risk prediction model is obtained by training using the default risk prediction model training device described in any embodiment of the present invention.

[0116] The default risk prediction device provided by the embodiment of the present invention can execute the default risk prediction method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0117] Optionally, the prediction module 520 includes:

[0118] A preliminary classification unit, configured to obtain preliminary classification results of the data to be predicted through a coarse classification model;

[0119] The prediction unit is used to input the data to be predicted and the preliminary classification result into the default risk prediction model to obtain the default risk prediction result of the user to be predicted.

[0120] The default risk prediction device further described can also execute the default risk prediction method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0121] Figure 6 A schematic diagram of the structure of an electronic device 60 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 assistants, 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.

[0122] like Figure 6 As shown, the electronic device 60 includes at least one processor 61 and a memory, such as a read-only memory (ROM) 62, a random access memory (RAM) 63, etc., which is communicatively connected to the at least one processor 61. The memory stores a computer program that can be executed by the at least one processor. The processor 61 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 62 or the computer program loaded from the storage unit 68 into the random access memory (RAM) 63. Various programs and data required for the operation of the electronic device 60 can also be stored in the RAM 63. The processor 61, ROM 62, and RAM 63 are connected to each other via a bus 64. An input / output (I / O) interface 65 is also connected to the bus 66.

[0123] Multiple components in the electronic device 60 are connected to the I / O interface 65, including an input unit 66, such as a keyboard, a mouse, etc.; an output unit 67, such as various types of displays, speakers, etc.; a storage unit 68, such as a magnetic disk, an optical disk, etc.; and a communication unit 69, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 69 allows the electronic device 60 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0124] Processor 61 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Examples of processor 61 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 that run machine learning model algorithms, digital signal processors (DSPs), and any other suitable processors, controllers, microcontrollers, and the like. Processor 61 executes the various methods and processes described above, such as the method for training a default risk determination model or the method for predicting default risk.

[0125] In some embodiments, the training method of the default risk judgment model or the method for predicting the default risk can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as the storage unit 68. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 60 via the ROM 62 and / or the communication unit 69. When the computer program is loaded into the RAM 63 and executed by the processor 61, one or more steps of the training method of the default risk judgment model or the method for predicting the default risk described above can be performed. Alternatively, in other embodiments, the processor 61 can be configured to execute the training method of the default risk judgment model or the method for predicting the default risk by any other appropriate means (for example, by means of firmware).

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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).

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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 training method for a default risk prediction model, characterized in that: The method comprises: Perform distribution statistics on each feature in the desensitized credit data to obtain missing features with missing values ​​and the missing ratio of each missing feature; Determine low-value features among the missing features according to the missing ratio, and determine other features other than the low-value features as high-value features; Based on the high-value features, the desensitized credit data is roughly classified using a non-neural network model to obtain training samples for weakly supervised learning, which includes: using the high-value features as extracted features of the desensitized credit data, and fine-tuning the non-neural network model using the desensitized credit data to obtain a rough classification model; The number of the coarse classification models is at least two; for each sample in the desensitized credit data, a classification result of the sample by each coarse classification model is obtained; the classification result includes the probability that the sample belongs to each category; the classification results are integrated to obtain a coarse classification label for the sample; Constructing a weakly supervised training sample based on the coarse classification label of each sample in the desensitized credit data; The neural network model is weakly supervised trained according to the training samples to obtain a default risk prediction model.

2. The method according to claim 1, characterized in that Determining the low-value features among the missing features according to the missing ratio includes: Draw a statistical diagram of the missing proportion according to the missing proportion; The missing ratio statistical diagram is pushed to the tester, and the low-value features determined by the tester are obtained.

3. A method for predicting default risk, characterized in that: The method comprises: Preprocess the credit data of the user to be predicted to obtain the data to be predicted; Based on the data to be predicted, obtaining a default risk prediction result of the user to be predicted according to the default risk prediction model; Wherein, the default risk prediction model is obtained by training through the method described in any one of claims 1-2.

4. The method according to claim 3, characterized in that Obtaining a default risk prediction result of the user to be predicted based on the data to be predicted and according to the default risk prediction model includes: Obtaining preliminary classification results of the data to be predicted through a coarse classification model; The data to be predicted and the preliminary classification results are input into a default risk prediction model to obtain a default risk prediction result of the user to be predicted.

5. A training device for a default risk prediction model, used to execute the training method for a default risk prediction model according to any one of claims 1 to 2, characterized in that: The device comprises: An analysis module, configured to analyze the degree of missingness of the desensitized credit data and obtain high-value features in the desensitized credit data; A classification module, configured to perform coarse classification of the desensitized credit data using a non-neural network model based on the high-value features to obtain training samples for weakly supervised learning; The training module is used to perform weak supervision training on the neural network model according to the training samples to obtain a default risk prediction model.

6. A default risk prediction device, used to execute the default risk prediction method according to any one of claims 3 to 4, characterized in that: The device comprises: A preprocessing module, used to preprocess the credit data of the user to be predicted to obtain the data to be predicted; A prediction module, configured to obtain a default risk prediction result of the user to be predicted based on the data to be predicted and according to the default risk prediction model; Wherein, the default risk prediction model is obtained by training the device described in claim 5.

7. 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 that can be executed 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 training method of the default risk judgment model described in any one of claims 1-2 or the default risk prediction method described in any one of claims 3-4.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, which are used to enable a processor to implement the training method of the default risk judgment model described in any one of claims 1-2 or the default risk prediction method described in any one of claims 3-4 when executed.

Images