Risk prediction method and device, electronic equipment, storage medium and program product

Abstract

The invention discloses a risk prediction method and device, electronic equipment, a storage medium and a program product, and particularly relates to the technical field of computers. According to the specific implementation scheme, the method comprises the steps of obtaining object basic features of a to-be-predicted object and historical resource application features of the to-be-predicted object; combining the object basic features and the historical resource application features to obtain a target vector; searching feature information in the target vector according to a set target; and inputting the feature information into a prediction model to obtain a category probability, the category probability being a predicted probability representing whether the to-be-predicted object has a resource application risk. The resource application risk probability of the to-be-predicted object is obtained by obtaining the object basic characteristics and the historical resource application characteristics of the to-be-predicted object and inputting the object basic characteristics and the historical resource application characteristics into the prediction model, so that future resource application risk identification of the to-be-predicted object is realized, and the resource application of the to-be-predicted object is managed by taking corresponding measures.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a risk prediction method, device, electronic device, storage medium and program product. Background Art

[0002] Online credit business is an important part of financial institutions. With the development of Internet technology, more and more financial institutions provide personal loan services to customers through online channels. Although online credit business is convenient and fast, it also faces higher risks. Therefore, how to effectively manage online credit risks has become one of the focuses of financial institutions.

[0003] Before providing personal loan services to customers, taking appropriate risk management measures is the current issue that needs to be addressed. Summary of the invention

[0004] The present invention provides a risk prediction method, device, electronic device, storage medium and program product to predict the probability of resource application risk existing in a to-be-predicted object.

[0005] According to one aspect of the present invention, there is provided a risk prediction method, comprising:

[0006] Obtaining basic characteristics of the object to be predicted and historical resource application characteristics of the object to be predicted;

[0007] Combining the basic features of the object and the historical resource application features to obtain a target vector;

[0008] Searching for characteristic information in the target vector with a set target;

[0009] The feature information is input into a prediction model to obtain a category probability, where the category probability is a predicted probability that characterizes whether the object to be predicted has a resource application risk.

[0010] According to another aspect of the present invention, there is provided a risk prediction device, comprising:

[0011] An acquisition module, used to acquire basic characteristics of an object to be predicted and historical resource application characteristics of the object to be predicted;

[0012] A merging module, used for merging the basic features of the object and the historical resource application features to obtain a target vector;

[0013] A search module, used to search for characteristic information in the target vector with a set target;

[0014] The input module is used to input the feature information into the prediction model to obtain the category probability, which is the predicted probability that characterizes whether the object to be predicted has a resource application risk.

[0015] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0016] at least one processor; and

[0017] a memory communicatively connected to the at least one processor; wherein,

[0018] 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 risk prediction method described in any embodiment of the present invention.

[0019] 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 risk prediction method described in any embodiment of the present invention when executed.

[0020] According to another aspect of the present invention, a computer program product is provided. The computer program product includes a computer program. When the computer program is executed by a processor, the risk prediction method described in any embodiment of the present invention is implemented.

[0021] The technical solution of the embodiment of the present invention first obtains the basic characteristics of the object to be predicted and the historical resource application characteristics of the object to be predicted, then merges the basic characteristics of the object and the historical resource application characteristics to obtain a target vector, then searches for the characteristic information in the target vector with a set target, and finally inputs the characteristic information into the prediction model to obtain a category probability, which is the predicted probability of whether the object to be predicted has a resource application risk. By obtaining the basic characteristics of the object to be predicted and the historical resource application characteristics of the object to be predicted, and inputting them into the prediction model, the resource application risk probability of the object to be predicted is obtained, and the future resource application risk identification of the object to be predicted is realized, so that corresponding measures can be taken to manage the resource application of the object to be predicted.

[0022] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] 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.

[0024] Figure 1 is a flow chart of a risk prediction method provided according to Embodiment 1 of the present invention;

[0025] Figure 2 is a flowchart of a prediction model iteration method provided according to Embodiment 2 of the present invention;

[0026] Figure 3 is a schematic diagram of the structure of a risk prediction device provided according to Embodiment 3 of the present invention;

[0027] Figure 4 It is a block diagram of an electronic device provided according to a fourth embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme 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 described embodiments 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 creative work should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first", "second", etc. in the specification 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 data 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 that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0031] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0032] As an optional but non-limiting implementation, in response to receiving an active request from the user, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0033] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet the relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0034] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.

[0035] Embodiment 1

[0036] Figure 1 A flowchart of a risk prediction method is provided for the first embodiment of the present invention. This embodiment is applicable to the case of performing risk prediction on a prediction object. The method can be performed by a risk prediction device. The risk prediction device can be implemented in the form of hardware and / or software. The risk prediction device can be configured in an electronic device. The electronic device is a computer device that can implement prediction model training and use. Figure 1 As shown, the method includes:

[0037] S110: Obtain basic characteristics of the object to be predicted and historical resource application characteristics of the object to be predicted.

[0038] In this embodiment, the object to be predicted can be understood as an object that needs to be predicted for resource application risk, which can be a user who needs to be predicted and has the characteristics required for prediction. The basic characteristics of the object can be understood as characteristics related to the characteristic information of the object itself, which can include the age, gender, occupation, etc. of the object. The historical resource application characteristics can be understood as characteristics related to the resource application situation of the object in the historical period.

[0039] Specifically, an object to be predicted that can be predicted is selected from the database. First, multiple features related to the feature information of the object to be predicted are obtained, and cross-statistical information between the multiple features can be extracted, and the results are used as the basic features of the object to be predicted. Similarly, features related to the resource application of the object to be predicted are obtained as the historical resource application features of the object to be predicted.

[0040] For example, multiple features related to the characteristic information of the object to be predicted are obtained, such as the age, gender, occupational category, credit information, etc. of the object to be predicted, and cross-statistical information between multiple features can be extracted through factor decomposition, and the result is used as the basic characteristics of the object to be predicted. Similarly, features related to the resource application of the object to be predicted, such as the time and quantity of resource application, can be obtained as the historical resource application features of the object to be predicted.

[0041] Optionally, the basic characteristics of the object include category characteristics of the object to be predicted, credit metric information of the object to be predicted, and information associated with resource return capability;

[0042] The historical resource application information includes application information and return information of the historically applied resources of the object to be predicted.

[0043] In this embodiment, the category feature can be understood as the basic information of the object to be predicted, including the age, gender, occupational category, etc. of the object to be predicted. The credit measurement information can be understood as the features related to the credit information of the object to be predicted, reflecting the credit level of the object to be predicted. The information associated with the resource return capability can be understood as the dense features that have been through feature engineering, and can include the application resource information of the object to be predicted, etc. The historical resource application information can be understood as the records of resource applications and returned resources in the historical period of the object to be predicted, which can be obtained through feature engineering. The application information of historical application resources can be understood as the information of resource applications in the historical period of the object to be predicted, including statistical information on the number and purpose of the applied resources. Similarly, the return information of historical application resources can be understood as the information of the returned resources in the historical period of the object to be predicted, including statistical information on the number and time of the returned resources.

[0044] S120: Combining the basic features of the object and the historical resource application features to obtain a target vector.

[0045] In this embodiment, the target vector can be understood as a vector obtained by concatenating the basic features of the object and the historical resource application features, and can be used to store feature information.

[0046] Specifically, the basic features of the object to be predicted and the historical resource application features are concatenated to obtain a complete target vector. Feature concatenation can reduce the dimension of the target vector, and the values ​​of the basic features of the object to be predicted and the historical resource application features can be calculated and combined into a new target vector.

[0047] S130: Searching for feature information in the target vector with a set target.

[0048] In this embodiment, the set target can be understood as a feature related to the resource application of the object to be predicted.

[0049] Specifically, a target that meets the set conditions among the targets related to the resource application of the object to be predicted is determined as the set target. The set target is searched in the target vector obtained by splicing the basic features of the object and the historical resource application features, and the feature information related to the resource application of the object to be predicted in the target vector is searched.

[0050] Exemplarily, when searching with a set target, a particle swarm optimization algorithm based on linear decreasing weights may be used to search for characteristic information related to the resource application of the object to be predicted in the target vector.

[0051] S140: Input the feature information into a prediction model to obtain a category probability, where the category probability is a predicted probability that characterizes whether the object to be predicted has a resource application risk.

[0052] In this embodiment, the prediction model can be understood as a model for predicting the resource application risk of the object to be predicted, and the model can output the probability of the resource application risk of the object to be predicted. The category probability can be understood as the probability obtained by the prediction model based on the basic characteristics of the object to be predicted and the historical resource application characteristics, which can characterize the size of the resource application risk of the object to be predicted. The resource application risk can be understood as the impact or uncertainty on the resource application caused by the behavior of the object to be predicted.

[0053] Specifically, the feature information searched from the target vector is input into the prediction model to obtain the category probability that characterizes the resource application risk of the object to be predicted. After obtaining the category probability, the category probability can also be optimized through an optimization algorithm to obtain a more accurate probability that characterizes the resource application risk of the object to be predicted.

[0054] Exemplarily, the prediction model can be a lightweight gradient boosting machine model that has been iteratively trained. It is a tree-based ensemble learning method that uses gradient boosting technology to combine multiple decision trees into a large model. The category probability that characterizes the resource application risk of the object to be predicted is obtained by inputting feature information into the prediction model. After obtaining the category probability, the category probability can also be corrected and optimized by an indicator optimization algorithm based on a particle swarm to obtain a more accurate probability that characterizes the resource application risk of the object to be predicted.

[0055] The technical solution of the embodiment of the present invention first obtains the basic characteristics of the object to be predicted and the historical resource application characteristics of the object to be predicted, then merges the basic characteristics of the object and the historical resource application characteristics to obtain a target vector, then searches for the characteristic information in the target vector with a set target, and finally inputs the characteristic information into the prediction model to obtain a category probability, which is the predicted probability of whether the object to be predicted has a resource application risk. By obtaining the basic characteristics of the object to be predicted and the historical resource application characteristics of the object to be predicted, and inputting them into the prediction model, the resource application risk probability of the object to be predicted is obtained, and the future resource application risk identification of the object to be predicted is realized, so that corresponding measures can be taken to manage the resource application of the object to be predicted.

[0056] Based on the above embodiment, a variant embodiment of the above embodiment is proposed. It should be noted that in order to make the description concise, only the differences from the above embodiment are described in the variant embodiment.

[0057] In one embodiment, searching the characteristic information in the target vector with a set target includes:

[0058] The first evaluation index satisfies the set condition as the set goal, the feature selection method is used as a particle, and the feature information in the target vector is searched by updating the position and speed of the particle.

[0059] In this embodiment, the first evaluation index can be understood as being set according to the basic characteristics of the object to be predicted and the historical resource application characteristics, and is used to select feature information related to resource application in the target vector of the object to be predicted. The setting condition can be understood as a condition for selecting a set target related to resource application of the object to be predicted. The feature selection method can be understood as a method for selecting the most relevant features from the original data, and each feature selection method can be used as a feature selection scheme. In the particle swarm optimization algorithm, each feature selection method can be used as a particle as a potential solution of the particle swarm optimization algorithm.

[0060] Specifically, the first evaluation index in the target vector satisfies the set condition as the set target. The first evaluation index can be an index about feature information gain or accuracy. Using the particle swarm optimization algorithm, each feature selection algorithm is used as a particle, and the process of searching for feature information in the target vector is completed by updating the position and speed of the particle.

[0061] In one embodiment, the operation of iteratively updating the weights of samples in the training phase of the prediction model includes:

[0062] With the goal of maximizing the second evaluation index, the particle swarm optimization algorithm based on linearly decreasing weight values ​​searches for weights.

[0063] In this embodiment, the second evaluation index can be understood as an index that characterizes the performance of the prediction model, and can be determined based on the target of the prediction model and its corresponding weight.

[0064] Specifically, when updating the weight of a sample, the second evaluation index is first determined according to the target value and the weight. The second evaluation index is maximized as the goal, and the particle swarm optimization algorithm based on the linearly decreasing weight value is used to search for the optimal weight to update the weight of the sample.

[0065] For example, in a particle swarm optimization algorithm based on linear decreasing weight values, the weight of each sample is first taken as a particle, an initial position and an initial velocity are assigned to each particle, and the fitness of each particle and its optimal position are calculated. The particle with the best fitness is found among all particles as the global extreme value. Then, the position of each particle is updated according to the velocity, current position, global extreme value, etc. of each particle, and the global extreme value is updated to obtain the optimal weight, thus completing the update of the sample weight.

[0066] In one embodiment, the second evaluation index is a value determined based on a target value and a weight, and the target value includes a value measuring the comprehensive performance of precision and recall.

[0067] In this embodiment, the target value is an indicator that measures the average between precision and recall, and is used to strike a balance between precision and recall. A larger target value indicates better model performance. Precision refers to the proportion of samples predicted as positive by the prediction model that are actually positive, and is used to measure the accuracy of the prediction model in predicting positive samples. Recall refers to the proportion of all samples predicted as positive by the prediction model that are actually positive, and is used to measure how many of all positive samples are correctly predicted.

[0068] Embodiment 2

[0069] Figure 2This is a flowchart of a prediction model iteration method provided in the second embodiment of the present invention. This embodiment is similar to one of the iteration processes in the training phase of the prediction model in the above embodiment. Figure 2 As shown, the method includes:

[0070] S210: Filter the sample set for this round of iteration from the training samples according to the gradient size of the training samples.

[0071] In this embodiment, the training sample can be understood as being composed of feature information searched from the target vector of the object to be predicted. The sample set can be understood as a set of samples selected from the training sample according to the sample gradient, which is used in the process of training the prediction model.

[0072] Specifically, the target vector is obtained based on the basic features of the object to be predicted and the historical resource application features, and the feature information is searched from the target vector and used as a training sample. The gradient of the training sample is determined, and the characteristic that samples with large gradients have a greater impact on the information gain calculation is used. In this round of iteration, a small number of training samples with large gradients are retained, and training samples with small gradients are randomly sampled, and the selected training samples are put into the sample set for this round of iteration.

[0073] S220: Determine whether to perform feature dimensionality reduction processing based on the distribution information of the features in the sample set.

[0074] In this embodiment, the distribution information of the feature can be understood as the distribution of the training sample features in the sample set, including the sparsity, mutual exclusivity and computational complexity of the feature distribution. Feature dimensionality reduction can be understood as an operation that reduces the number of features in the sample set while retaining important feature information, and can remove noise and irrelevant features.

[0075] Specifically, according to the distribution information of the features in the sample set, if most of the features in the sample set are sparse and there are a large number of mutually exclusive features in the sample set, it is possible to consider reducing the dimension of the features in the sample set to reduce the computational complexity. If the features in the sample set do not meet the sparseness and mutual exclusivity, it is not necessary to perform feature dimensionality reduction on the features.

[0076] For example, if the distribution information of the features in the sample set shows that most of the features are sparse and there are a large number of mutually exclusive features in the sample set, that is, many features in the sample set are zero values ​​in most samples, and many sparse features will not be non-zero values ​​at the same time, then you can consider reducing the dimensionality of the features in the sample set.

[0077] S230: If yes, bundle the mutually exclusive features in the sample set to obtain bundled features.

[0078] Specifically, when the features in the sample set need to be reduced in dimension, this can be achieved through the mutually exclusive feature bundling algorithm. That is, firstly, mutually exclusive features with good fusion effect are selected through the greedy bundling algorithm, and then they are merged into new features using the merge mutually exclusive feature algorithm to complete the feature dimensionality reduction.

[0079] For example, among all the features in a sample set, there are mutually exclusive features, that is, they will not be non-zero values ​​at the same time, and these mutually exclusive features can be bundled into one feature through the mutually exclusive feature bundling algorithm. For example, the mutually exclusive feature bundling algorithm first finds all the mutually exclusive features in the sample set, and then bundles the found mutually exclusive features together to form a new feature, and the value of the new feature can be the sum of the original feature values.

[0080] S240, constructing a histogram-based decision tree based on the bundled features.

[0081] In this embodiment, the decision tree is a tree structure consisting of nodes and edges, which can be used to infer target variables from features.

[0082] Specifically, the bundled features are used as input features. First, the continuous input features are discretized into a finite number of intervals, and a histogram is constructed. When traversing the input features, the statistics are accumulated in the histogram based on the discretized values ​​as indexes. After traversing the data once, the histogram accumulates the required statistics, and then the optimal split point is traversed based on the discrete values ​​of the histogram. Then, the root node, child nodes and decision rules of the decision tree are determined based on the optimal split point, and the decision tree construction based on the histogram is completed.

[0083] For example, for a feature with a value range of [0,100], if it is discretized into 10 intervals [0,10), [10,20), ..., [90,100], then only the statistical information of these 10 intervals needs to be calculated, which simplifies the calculation process.

[0084] S250: Training the prediction model based on the decision tree.

[0085] Specifically, the prediction model is trained by a histogram-based decision tree. First, the sample set for this round of iteration is selected from the training samples using the gradient sampling method. Then, the training samples that need to be reduced in dimension are reduced in dimension using the mutually exclusive feature bundling algorithm to obtain the bundled features. Finally, the bundled features are used to construct a histogram-based decision tree and train the prediction model. The above is a single-iteration training process. By selecting different sample sets through different training samples, multiple iterations of the training model can be achieved, and finally a prediction model that can be used for the object to be predicted is obtained.

[0086] The technical solution of the embodiment of the present invention first selects the sample set of this round of iteration from the training samples according to the gradient size of the training samples, and determines whether to perform feature dimensionality reduction processing based on the distribution information of the features in the sample set. If so, the mutually exclusive features in the sample set are bundled to obtain bundled features. Finally, a histogram-based decision tree is constructed based on the bundled features, and the prediction model is trained based on the decision tree. Each iterative process of the training stage of the prediction model is described in detail. Through feature dimensionality reduction and feature bundling, the computational difficulty of model training is reduced, the speed of model training is increased, and the performance of the prediction model is optimized.

[0087] Embodiment 3

[0088] Figure 3 This is a schematic diagram of the structure of a risk prediction device provided by Embodiment 3 of the present invention. Figure 3 As shown, the device comprises:

[0089] An acquisition module 310 is used to acquire basic characteristics of an object to be predicted and historical resource application characteristics of the object to be predicted;

[0090] A merging module 320, configured to merge the basic features of the object and the historical resource application features to obtain a target vector;

[0091] A search module 330, configured to search for feature information in the target vector with a set target;

[0092] The input module 340 is used to input the feature information into the prediction model to obtain a category probability, where the category probability is a predicted probability that characterizes whether the object to be predicted has a resource application risk.

[0093] The risk prediction device provided by the embodiment of the present invention first obtains the basic characteristics of the object to be predicted and the historical resource application characteristics of the object to be predicted through the acquisition module, then merges the basic characteristics of the object and the historical resource application characteristics through the merging module to obtain the target vector, and then searches the characteristic information in the target vector by setting the target through the search module, and finally inputs the characteristic information into the prediction model through the input module to obtain the category probability, which is the predicted probability of whether the object to be predicted has a resource application risk. Through the mutual cooperation between the modules, the basic characteristics of the object to be predicted and the historical resource application characteristics of the object to be predicted are obtained and input into the prediction model to obtain the resource application risk probability of the object to be predicted, thereby realizing the identification of the future resource application risk of the object to be predicted, so as to take corresponding measures to manage the resource application of the object to be predicted.

[0094] In one embodiment, the search module 330 is specifically configured to:

[0095] The first evaluation index satisfies the set condition as the set goal, the feature selection method is used as a particle, and the feature information in the target vector is searched by updating the position and speed of the particle.

[0096] In one embodiment, the input module 340 includes: each iteration process of the training phase of the prediction model is specifically used to:

[0097] According to the gradient size of the training samples, the sample set for this round of iteration is selected from the training samples;

[0098] Determining whether to perform feature dimensionality reduction processing based on distribution information of features in the sample set;

[0099] If so, the mutually exclusive features in the sample set are bundled to obtain bundled features;

[0100] Construct a histogram-based decision tree based on the bundled features;

[0101] The prediction model is trained based on the decision tree.

[0102] In one embodiment, the input module 340 includes: an operation of iteratively updating the weights of samples in the training phase of the prediction model, specifically for:

[0103] With the goal of maximizing the second evaluation index, the particle swarm optimization algorithm based on linearly decreasing weight values ​​searches for weights.

[0104] In one embodiment, the second evaluation index is a value determined based on a target value and a weight, and the target value includes a value measuring the comprehensive performance of precision and recall.

[0105] In one embodiment, the basic characteristics of the object include the category characteristics of the object to be predicted, the credit measurement information of the object to be predicted and the information associated with the resource return capability; the historical resource application information includes the application information and return information of the historical resource application of the object to be predicted.

[0106] The data center submission device provided in the embodiment of the present invention can execute the risk prediction method provided in any embodiment of the present invention, completes the submission of the data center through the mutual cooperation and collaboration between the modules, and has the functional modules and beneficial effects corresponding to the execution method.

[0107] Embodiment 4

[0108] According to an embodiment of the present invention, the present invention also provides an electronic device, a computer-readable storage medium and a computer program product.

[0109] Figure 4It is a block diagram of an electronic device provided according to Embodiment 4 of the present invention, and the electronic device can implement the risk prediction method described in the embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, 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 required herein.

[0110] like Figure 4 As shown, the electronic device 410 includes at least one processor 411, and a memory connected to the at least one processor 411 in communication, such as a read-only memory (ROM) 412, a random access memory (RAM) 413, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 411 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 412 or the computer program loaded from the storage unit 418 to the random access memory (RAM) 413. In the RAM 413, various programs and data required for the operation of the electronic device 410 can also be stored. The processor 411, the ROM 412, and the RAM 413 are connected to each other via a bus 414. An input / output (I / O) interface 415 is also connected to the bus 414.

[0111] A number of components in the electronic device are connected to the I / O interface 415, including: an input unit 416, such as a keyboard, a mouse, etc.; an output unit 417, such as various types of displays, speakers, etc.; a storage unit 418, such as a disk, an optical disk, etc.; and a communication unit 419, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 419 allows the electronic device to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0112] Processor 411 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of processor 411 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. Processor 411 performs the various methods and processes described above, such as risk prediction methods.

[0113] In some embodiments, the risk prediction method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 418. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 410 via the ROM 412 and / or the communication unit 419. When the computer program is loaded into the RAM 413 and executed by the processor 411, one or more steps of the risk prediction method described above may be performed. Alternatively, in other embodiments, the processor 411 may be configured to perform the risk prediction method in any other appropriate manner (e.g., by means of firmware).

[0114] Various implementations of the systems and techniques described above 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), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including 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.

[0115] 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, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0116] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0117] To provide interaction with a user, the systems and techniques described herein may 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 a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0118] The systems and techniques described herein may be implemented in a computing system that includes backend 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 frontend components (e.g., a user computer with a graphical user interface or a 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 backend components, middleware components, or frontend components. The components of the system may 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.

[0119] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0120] In some embodiments, the computer program product includes a computer program, and when the computer program is executed by a processor, it implements the risk prediction method provided by the embodiment of the present invention.

[0121] The technical solution of the embodiment of the present invention, through a risk prediction method, device, electronic device, storage medium and program product, first obtains the basic characteristics of the object to be predicted and the historical resource application characteristics of the object to be predicted, then merges the basic characteristics of the object and the historical resource application characteristics to obtain a target vector, then searches for the characteristic information in the target vector with a set target, and finally inputs the characteristic information into the prediction model to obtain a category probability, which is the predicted probability of whether the object to be predicted has a resource application risk. The present invention obtains the basic characteristics of the object to be predicted and the historical resource application characteristics of the object to be predicted, inputs them into the prediction model, obtains the resource application risk probability of the object to be predicted, and realizes the identification of the future resource application risk of the object to be predicted, so as to take corresponding measures to manage the resource application of the object to be predicted.

[0122] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0123] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A risk prediction method, characterized in that: include: Obtaining basic characteristics of the object to be predicted and historical resource application characteristics of the object to be predicted; Combining the basic features of the object and the historical resource application features to obtain a target vector; Searching for characteristic information in the target vector with a set target; The feature information is input into a prediction model to obtain a category probability, where the category probability is a predicted probability that characterizes whether the object to be predicted has a resource application risk.

2. The method according to claim 1, characterized in that The step of searching the characteristic information in the target vector with a set target includes: The first evaluation index satisfies the set condition as the set goal, the feature selection method is used as a particle, and the feature information in the target vector is searched by updating the position and speed of the particle.

3. The method according to claim 1, characterized in that Each iteration process of the training phase of the prediction model includes: According to the gradient size of the training samples, the sample set for this round of iteration is selected from the training samples; Determining whether to perform feature dimensionality reduction processing based on distribution information of features in the sample set; If so, the mutually exclusive features in the sample set are bundled to obtain bundled features; Construct a histogram-based decision tree based on the bundled features; The prediction model is trained based on the decision tree.

4. The method according to claim 1, characterized in that: The operation of iteratively updating the weights of samples in the training phase of the prediction model includes: With the goal of maximizing the second evaluation index, the particle swarm optimization algorithm based on linearly decreasing weight values ​​searches for weights.

5. The method according to claim 4, characterized in that The second evaluation index is a value determined based on a target value and a weight, and the target value includes a value for measuring the comprehensive performance of precision and recall.

6. The method according to claim 1, characterized in that The basic characteristics of the object include the category characteristics of the object to be predicted, the credit metric information of the object to be predicted and the information associated with the resource return capability; The historical resource application information includes application information and return information of the historically applied resources of the object to be predicted.

7. A risk prediction device, characterized in that: include: An acquisition module, used to acquire basic characteristics of an object to be predicted and historical resource application characteristics of the object to be predicted; A merging module, used for merging the basic features of the object and the historical resource application features to obtain a target vector; A search module, used to search for characteristic information in the target vector with a set target; The input module is used to input the feature information into the prediction model to obtain the category probability, which is the predicted probability that characterizes whether the object to be predicted has a resource application risk.

8. 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 risk prediction method according to any one of claims 1 to 6.

9. 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 risk prediction method according to any one of claims 1 to 6 when executed.

10. A computer program product, characterized in that The computer program product comprises a computer program, which, when executed by a processor, implements the risk prediction method according to any one of claims 1 to 6.

Images