Joint binning label generation method and apparatus for risk profiling

Abstract

The application provides a joint binning label generation method and device for risk portrait construction, which has the following characteristics: all features are divided into a plurality of sub-feature sets, a plurality of features are selected from all the sub-feature sets according to the importance values of the features to construct an importance representative feature set; step S4: binning calculation is performed on the importance representative feature set to obtain the binning values of each feature corresponding to each target in the importance representative feature set, and a binning feature set is constructed according to all the binning values; step S5: each feature in the binning feature set is combined to obtain a joint binning feature set; and step S6: the woe values of each feature corresponding to each target in the joint binning feature set are calculated. In summary, the method can generate a plurality of labels that improve the risk portrait accuracy and the corresponding label values of each target.

Description

Technical Field

[0001] This invention belongs to the field of risk profiling, specifically relating to a method and apparatus for generating joint bin labels for risk profiling construction. Background Technology

[0002] Risk profiling is used in multiple fields, and the accuracy of risk profiling depends on whether the risk labels can reflect the risk status of the subject in a certain dimension.

[0003] Currently, most entity risk profiling employs rule-driven methods based on expert experience, integrating various characteristics into risk labels to assess entity risk. While this method is highly interpretable and logically clear, its limitations are also significant, as detailed below:

[0004] 1) The curse of dimensionality in high-dimensional features: The data to be analyzed is usually characterized by high dimensionality and diversity, and the relationships between features are complex and not explicit. Rule-based methods struggle to effectively extract key information in high-dimensional feature spaces, often resulting in low-quality label generation due to limited rule coverage or overly simplistic rule design. Furthermore, the computational cost of high-dimensional features also limits the widespread application of rule-based methods.

[0005] 2) Lack of a systematic label generation process: Rule-driven methods typically lack a unified framework for feature selection, feature expansion, and risk label generation, relying instead on customized designs for different scenarios, thus lacking a systematic approach. This lack of a standardized generation process increases the difficulty of implementation and maintenance, while also reducing the interpretability of the model and the reliability of risk assessment.

[0006] 3) Insufficient feature selection and importance assessment: Rule-driven methods rely on the experience and knowledge of domain experts to define feature selection rules, feature combination methods, and risk assessment indicators. This approach may overlook the interactions and potential correlations between different features, leading to the omission of key information and thus reducing the model's predictive performance.

[0007] 4) Limited binning processing methods and lack of interactive analysis capabilities: Current binning technologies mostly use independent single-feature binning, which makes it difficult to reflect the interactive relationships between multiple features. Single-feature binning may lead to insufficient multi-dimensional understanding of risk groups, affecting the accurate characterization of complex risk states. Summary of the Invention

[0008] This invention is made to solve the above-mentioned problems, and aims to provide a method and apparatus for generating joint bin labels for risk profile construction.

[0009] This invention provides a joint binning label generation method for risk profile construction, used to generate risk profile-related label results for each target based on risk-related data. The risk-related data includes the values ​​of multiple different features corresponding to each target, and risk judgment labels corresponding to each target. The method comprises the following steps: Step S1, dividing all features into multiple categories to generate sub-feature sets corresponding to each category, each sub-feature set including at least one feature and all values ​​corresponding to that feature; Step S2, calculating the importance value of each feature in each sub-feature set based on the number of features and the values ​​corresponding to the features; Step S3, selecting multiple features from all sub-feature sets based on their importance values ​​to construct a joint binning label generation method. The importance representative feature set is defined in step S4. Binning calculation is performed on the importance representative feature set to obtain the binning value of each feature corresponding to each target in the importance representative feature set, and a binned feature set is constructed based on all binning values. Step S5. Each feature in the binned feature set is combined to obtain a joint binned feature set. Step S6. Binning calculation is performed on the joint binned feature set to obtain the binning value of each feature corresponding to each target in the joint binned feature set, and the WOE value of each feature corresponding to each target in the joint binned feature set is calculated based on all binning values ​​and risk assessment labels. The label result of the target is each feature of the target in the joint binned feature set and its corresponding WOE value.

[0010] The joint binning label generation method for risk profile construction provided by this invention may also have the following feature: wherein, in step S4, the calculation expression for the binning feature set is: In the formula Let be the binned feature set, and q be the importance representing the total number of features in the feature set. Let be the bins value of feature i corresponding to target k, and n be the total number of targets.

[0011] The joint binning label generation method for risk profile construction provided by this invention may also have the following feature: wherein, in step S5, the calculation expression for the joint binning feature set is: UnionBins(x)=[χ1||χ2,χ1||χ3,…,χ n-1 ||χ n ],x=[χ1,χ2,…,χ n ], where X unionbin For the joint binning feature set, χ n Let x be the nth feature in the feature vector set x, and || is the set concatenation symbol.

[0012] The joint binning label generation method for risk profile construction provided by this invention may also have the following features: Binning calculation of the feature set to obtain binning values ​​includes the following steps: Step T1, generating multiple candidate splitting thresholds for the feature set and calculating the splitting value corresponding to each candidate splitting threshold; Step T2, taking the candidate splitting threshold corresponding to the largest splitting value as the optimal splitting point; Step T3, repeating steps T1 to T2 until the number of optimal splitting points reaches a preset value; Step T4, calculating the binning boundary based on all optimal splitting points; Step T5, calculating the bins value and bin0 value of each feature corresponding to each target in the feature set as the binning value based on the binning boundary.

[0013] The joint binning label generation method for risk profile construction provided by this invention may also have the following feature: wherein the calculation expression for the splitting value is: H(D j )=-∑ c∈C p(c)log2p(c), In the formula IG(D j ,θ) is the feature set D j The corresponding splitting value of the candidate splitting threshold θ, where |D| is the number of samples in D. For the feature set D j The value of feature i corresponding to target k, v k For target k, y k Let C be the risk assessment label corresponding to target k, and D be the feature set. j The total number of features in the feature set D, p(c) is the sum of the sum of features c in the feature set D. j The probability of the bin boundary is calculated using the following expression: In the formula for The set of bin boundary values, To sort all optimal split points in ascending order, the expressions for calculating the bins and bin0 values ​​are as follows: In the formula For the feature set D j The value of feature i corresponding to target k. for The left boundary value of the u-th bin interval.

[0014] The joint binning label generation method for risk profile construction provided by this invention may also have the following feature: wherein, in step S2, the corresponding importance value is calculated based on the information gain of the feature at the node of the tree in the LightGBM model, and the expression for calculating the importance value is: In the formula Let be the importance value of feature i in sub-feature set j, p be the total number of features in sub-feature set j, M be the total number of trees in the LightGBM model, and N be the total number of trees in the model. m Let m be the set of nodes of the m-th tree. For the indicator function, ΔL m,n Let i be the information gain of feature i at node n in the m-th tree, when node n uses feature i for splitting. When node n does not use feature i for splitting

[0015] The joint binning label generation method for risk profile construction provided by this invention may also have the following feature: wherein, in step S3, the calculation expression for the importance-representing feature set is: In the formula X lgbm_represent Let X be the set of features representing importance, m be the total number of sub-feature sets, and X be the value of the feature set. j,lgbm_top To filter the feature set corresponding to the importance of the j-th sub-feature set, all features of the sub-feature set j are sorted in descending order of importance value, and a preset number of features are selected from the beginning of the sequence to construct the importance-filtered feature set.

[0016] The joint binning label generation method for risk profile construction provided by this invention may also have the following feature: In step S6, based on the bin0 value of the binning value of the feature corresponding to the target, the values ​​of all target-corresponding features are divided into multiple groups, where the values ​​of all target-corresponding features in each group have the same bin0 value. The risk judgment label is a binary classification label, and the expression for calculating the WOE value is: In the formula Let Woe be the value of feature i corresponding to target k in the joint binning feature set, and N be the value of Woe. bad Let N be the total number of risk judgment labels corresponding to all values ​​of feature i in the joint binning feature set for target k that are classified as bad. good For target k in sub-feature set D j The total number of risk judgment labels corresponding to all values ​​in the group containing the value of feature i, where N is the "good" category. total Let i be the total number of values ​​of feature i corresponding to target k in the joint binning feature set.

[0017] This invention also provides a joint binning label generation device for risk profile construction, used to generate risk profile-related label results for each target based on risk-related data. The risk-related data includes the values ​​of multiple different features corresponding to each target, and risk judgment labels corresponding to each target. The device comprises: a subset partitioning module, which divides all features into multiple categories and generates sub-feature sets corresponding to each category, each sub-feature set including at least one feature and all values ​​corresponding to that feature; an importance value calculation module, which calculates the importance value of each feature in each sub-feature set based on the number of features in the sub-feature set and the values ​​corresponding to the features; and an importance representative feature set generation module, which selects multiple features from all sub-feature sets based on their importance values ​​to construct an important feature set. The system comprises: a representative feature set; a binning feature set generation module, which performs binning calculations on the representative feature set to obtain the binning values ​​of each feature corresponding to each target in the representative feature set, and constructs a binning feature set based on all binning values; a joint binning feature set generation module, which combines the features in the binning feature set to obtain a joint binning feature set; and a risk assessment (WOE) calculation module, which performs binning calculations on the joint binning feature set to obtain the binning values ​​of each feature corresponding to each target in the joint binning feature set, and calculates the WEE values ​​of each feature corresponding to each target in the joint binning feature set based on all binning values ​​and risk assessment labels. The label result for a target is the target's features in the joint binning feature set and its corresponding WEE value.

[0018] The role and effect of invention

[0019] According to the method and apparatus for generating joint binning labels for risk profiling based on the present invention, the method generates multiple labels and corresponding label values ​​for each target by dividing features into sub-feature sets, calculating and filtering multiple features from each sub-feature set according to their corresponding importance values, constructing a representative feature set of importance, binning and combining these representative feature sets to obtain a joint binning feature set, and finally calculating the WOE value of each target in the joint binning feature set to obtain the label result. Therefore, the method and apparatus for generating joint binning labels for risk profiling based on the present invention can generate multiple labels that improve the accuracy of risk profiling and corresponding label values ​​for each target. Attached Figure Description

[0020] Figure 1 This is a block diagram of a joint bin label generation device for risk profile construction in an embodiment of the present invention;

[0021] Figure 2 This is a schematic diagram of the process for calculating the binning value in an embodiment of the present invention;

[0022] Figure 3 This is a flowchart illustrating the joint binning label generation method for risk profiling in an embodiment of the present invention;

[0023] Figure 4 This is a radar diagram illustrating a high-risk user profile in an embodiment of the present invention;

[0024] Figure 5 This is a radar schematic diagram of a low-resolution user profile in an embodiment of the present invention;

[0025] Figure 6 This is a schematic diagram of the scorecard visualization in an embodiment of the present invention. Detailed Implementation

[0026] To make the technical means, creative features, objectives and effects of the present invention easy to understand, the following embodiments, in conjunction with the accompanying drawings, specifically illustrate the method and apparatus for generating joint sub-labels for risk profiling.

[0027] This embodiment provides a joint binning label generation device for risk profile construction, used to generate label results related to the risk profile for each target based on risk-related data. The risk-related data includes the values ​​of multiple different features corresponding to each target, and risk assessment labels for each target. The risk assessment labels are binary classification labels.

[0028] In this embodiment, the joint binning label generation device for risk profiling is applied in the financial field, and the risk-related data is financial transaction data D = [VXY]. Where V = {v1,...,v...} n} represents a set of trading accounts, where each trading account is the target. For each v i Each ∈V has a binary label indicating whether it is illegal, i.e., a separator label y. i ∈Y, where n is the number of trading accounts, and the feature space constructed from the perspectives of statistical calculation, complex rules, expert knowledge, and intelligent algorithms is X, where X={X1,X2,…,X…} d}, X i ={χ i,k |k=1,2,…,n}, representing the feature χ i The feature set, where χ i,k χ represents the feature corresponding to the k-th transaction account. i The value of . In other embodiments, the joint box label generation device for risk profile construction can be applied to other fields, such as food safety, where the target is a specific food and the risk-related data is production data related to the specific food, such as the manufacturer.

[0029] Figure 1This is a block diagram of a joint bin label generation device for risk profiling in an embodiment of the present invention.

[0030] like Figure 1 As shown, the joint binning label generation device 100 for risk profile construction includes a subset partitioning module 11, an importance value calculation module 12, an importance representative feature set generation module 13, a binning feature set generation module 14, a joint binning feature set generation module 15, a WOE calculation module 16, and a control module 17 that controls the operation of the above modules.

[0031] The subset partitioning module 11 is used to divide all features into multiple categories and generate a subset of features corresponding to each category. The subset of features includes at least one feature and all values ​​corresponding to that feature.

[0032] In this embodiment, the subset partitioning module 11 divides information into m categories, thus obtaining the sub-feature set X. 1 ,X 2 ,…,X m And satisfy

[0033] The importance value calculation module 12 is used to calculate the importance value of each feature for each sub-feature set based on the number of features in the sub-feature set and the corresponding values ​​of the features.

[0034] The importance value calculation module 12 includes a LightGBM model. Based on the information gain of features at nodes in the LightGBM model's tree, the corresponding importance value is calculated. The expression for calculating the importance value is as follows:

[0035]

[0036] In the formula Let be the importance value of feature i in sub-feature set j, p be the total number of features in sub-feature set j, M be the total number of trees in the LightGBM model, and N be the total number of trees in the model. m Let m be the set of nodes of the m-th tree. For the indicator function, ΔL m,n Feature i is used as the loss reduction, or information gain, for splitting at node n in the m-th tree. When node n splits using feature i, When node n does not use feature i for splitting

[0037] In this embodiment, the loss function corresponding to the LightGBM model is the binary cross-entropy loss L, and its calculation expression is as follows:

[0038]

[0039] In the formula, N is the total number of samples, and y i Let i be the risk assessment label for the i-th sample. Let be the predicted probability of the LightGBM model for the i-th sample.

[0040] The importance representative feature set generation module 13 is used to select multiple features from all sub-feature sets according to their importance values ​​to construct an importance representative feature set.

[0041] The expression for calculating importance, representing the feature set, is as follows:

[0042]

[0043] In the formula X lgbm_reporesent Let X be the set of features representing importance, m be the total number of sub-feature sets, and X be the value of the feature set. j,lgbm_top To select a feature set based on the importance corresponding to the j-th sub-feature set.

[0044] Sort all features in sub-feature set j according to their importance value from largest to smallest. Select a predetermined number of features from the beginning of this sequence to construct the importance-filtered feature set. The calculation expression for the importance-filtered feature set is:

[0045] X j,lgbm_top =argsort(|lgbm_importance j |)[:1],

[0046]

[0047] In the formula, argsort(|lgbm_importance) j |) is to sort the sub-feature set j in descending order of importance values ​​by absolute value. That is, in this embodiment, the sorting is based on the size of the absolute value of the importance value. [:1] is the preset number.

[0048] The binning feature set generation module 14 is used to perform binning calculation on the importance representative feature set, obtain the binning value of each feature corresponding to each target in the importance representative feature set, and construct the binning feature set based on all binning values.

[0049] Figure 2 This is a schematic diagram of the process for calculating the binning value in an embodiment of the present invention.

[0050] like Figure 2 As shown, binning the feature set to obtain bin values ​​includes the following steps:

[0051] Step T1: For the feature set, generate multiple candidate split thresholds and calculate the split value corresponding to each candidate split threshold.

[0052] The expression for calculating the splitting value is as follows:

[0053]

[0054] H(D j )=-∑ c∈C p(c)log2p(c),

[0055]

[0056] In the formula IG(D j θ) is the sub-feature set D j The corresponding candidate splitting threshold θ represents the splitting value, where |D| is the number of samples in D. A sample includes the values ​​of all features corresponding to a target in set D. For the sub-feature set D j The value of feature i corresponding to target k, v k For target k, y k Let C be the risk assessment label corresponding to target k, and D be the sub-feature set. j The total number of features in the subset D, p(c) is the sum of the values ​​of feature c in the subset D. j The probability of.

[0057] Step T2: Select the candidate split threshold corresponding to the largest split value as the optimal split point.

[0058] Step T3: Repeat steps T1 to T2 until the number of optimal split points reaches a preset value. In this embodiment, at most four optimal split points are generated through two iterations.

[0059] Step T4: Calculate the bin boundaries based on all optimal split points.

[0060] The calculation expression for the bin boundary is as follows:

[0061]

[0062] In the formula for The set of bin boundary values, To sort all optimal split points in ascending order, negative infinity (-∞) and positive infinity (∞) are used in this embodiment to ensure that the final bin boundaries cover all values.

[0063] Step T5: Based on the binning boundaries, calculate the bins and bin0 values ​​of each feature corresponding to each target in the feature set as binning values.

[0064] The expressions for calculating the bins and bin0 values ​​are as follows:

[0065]

[0066] In the formula For the sub-feature set D j The value of feature i corresponding to target k. for The left boundary value of the u-th bin interval.

[0067] The expression for calculating the binning feature set is as follows:

[0068]

[0069] In the formula Let be the binned feature set, and q be the importance representing the total number of features in the feature set. Let be the bins value of feature i corresponding to target k, and n be the total number of targets.

[0070] In this embodiment, the binning feature set generation module 14 uses the importance representative feature set as the feature set to calculate the corresponding binning value.

[0071] The joint binning feature set generation module 15 is used to combine the features in the binning feature set to obtain the joint binning feature set.

[0072] In step S5, the calculation expression for the joint binning feature set is:

[0073]

[0074] UnionBins(x)=[χ1||χ2,χ1||χ3,…,χ n-1 ||χ n ],

[0075] x=[χ1,χ2,…,χ n ],

[0076] In the formula X unionbin For the joint binning feature set, χ n Let x be the nth feature in the feature vector set x, and || is the set concatenation symbol.

[0077] The WOE calculation module 16 is used to perform binning calculations on the joint binning feature set, obtain the binning value of each feature corresponding to each target in the joint binning feature set, and calculate the WOE value of each feature corresponding to each target in the joint binning feature set based on all binning values ​​and risk assessment labels. The label result for a target is its features in the joint binning feature set and its corresponding WOE value.

[0078] In this embodiment, the WOE calculation module 16 uses the joint binning feature set as the feature set to calculate the corresponding binning value.

[0079] Specifically, the woe calculation module 16 divides the values ​​of all target-corresponding features into multiple groups based on the bin0 value of the feature corresponding to the target. The feature values ​​corresponding to all targets in the group have the same bin0 value, that is, if The features corresponding to the target

[0080] The expression for calculating the woe value is:

[0081]

[0082] In the formula For target k in sub-feature set D j The WOE value of the corresponding feature i in N bad For target k in sub-feature set D j The total number of risk judgment labels corresponding to all values ​​in the group containing the value of feature i that are classified as bad, N. good For target k in sub-feature set D j The total number of risk judgment labels corresponding to all values ​​in the group containing the value of feature i, where N is the "good" category. total For target k in sub-feature set D j The total number of values ​​corresponding to feature i. In this embodiment, the risk judgment label is 0 or 1, where 0 represents the good category and 1 represents the bad category. In other embodiments, other forms can be used to replace 0 and 1 to distinguish between good and bad categories.

[0083] Control module 17 stores the control program that controls the operation of each module.

[0084] The following description, in conjunction with the accompanying drawings, illustrates the process of generating joint sub-labels for risk profiling using the joint sub-label generation device 100.

[0085] Figure 3 This is a flowchart illustrating the joint binning label generation method for risk profiling in an embodiment of the present invention.

[0086] like Figure 3 As shown, the joint binning label generation method for risk profile construction includes the following steps:

[0087] Step S1: Use the subset partitioning module 11 to divide all features into multiple categories and generate a sub-feature set corresponding to each category. The sub-feature set includes at least one feature and all values ​​corresponding to that feature.

[0088] Step S2: The importance value calculation module 12 calculates the importance value of each feature for each sub-feature set based on the number of features in the sub-feature set and the corresponding values ​​of the features.

[0089] Step S3: The importance representative feature set generation module 13 selects multiple features from all sub-feature sets according to their importance values ​​to construct the importance representative feature set.

[0090] Step S4: The binning feature set generation module 14 is used to perform binning calculation on the importance representative feature set to obtain the binning value of each feature corresponding to each target in the importance representative feature set, and a binning feature set is constructed based on all binning values.

[0091] Step S5: The joint binning feature set generation module 15 is used to combine the features in the binning feature set to obtain the joint binning feature set.

[0092] Step S6: The WoE calculation module 16 is used to perform binning calculation on the joint binning feature set to obtain the binning value of each feature corresponding to each target in the joint binning feature set. Based on all the binning values ​​and risk judgment labels corresponding to the joint binning feature set, the WoE value of each feature corresponding to each target in the joint binning feature set is calculated.

[0093] In this embodiment, a radar map of the user profile of the target can be constructed based on the target's tag results.

[0094] Figure 4 This is a radar diagram illustrating a high-risk user profile in an embodiment of the present invention.

[0095] Figure 5 This is a radar diagram illustrating a low-risk user profile in an embodiment of the present invention.

[0096] like Figure 4 and Figure 5 As shown, the labeling results include eight features—union_bin_1, union_bin_2, union_bin_3, union_bin_4, union_bin_5, union_bin_6, union_bin_7, and union_bin_8—that are the joint binning labels and their corresponding values. It is evident that abnormal subjects, i.e., high-risk users, occupy a larger area, while normal subjects, i.e., low-risk users, occupy a smaller area. This clearly demonstrates how the joint binning labels accurately portray the multi-dimensional risk levels of the subjects.

[0097] This embodiment, based on existing scoring models, extracts feature coefficients and intercepts, sets a baseline score and a score PDO for each doubling of odds, and calculates factor weights and offsets to create a scorecard containing features, coefficients, sample scores, and predicted probabilities. Furthermore, the scores are divided into several equidistant scoring intervals, and the number and proportion of positive and negative samples within each interval are calculated, visually reflecting the distribution of positive and negative samples across each interval.

[0098] Figure 6 This is a schematic diagram of the scorecard visualization in an embodiment of the present invention.

[0099] like Figure 6 As shown, the horizontal axis represents the sample score interval values ​​(score_bins), the vertical axis of the histogram represents the number of samples (Count) within that score interval, and the vertical axis of the line graph represents the bad rate within that score interval. Therefore, the scorecard based on the model labels, i.e., the target result of this embodiment, intuitively demonstrates how each module distinguishes between positive and abnormal samples, achieving a strong correlation between the abnormal subject and the risk score.

[0100] The role and effect of the embodiments

[0101] According to the joint binning label generation method and apparatus for risk profile construction involved in this embodiment, features are divided into sub-feature sets, and multiple features are selected from each sub-feature set according to their corresponding importance values ​​to construct an important representative feature set. Then, binning calculation and joint analysis are performed on this important representative feature set to obtain a joint binning feature set. Finally, the WOE value of each target in the joint binning feature set is calculated to obtain the label result. In summary, this method, on the one hand, reduces irrelevant or redundant features and lowers feature complexity by constructing an important representative feature set, thus mitigating the curse of dimensionality problem. On the other hand, through binning statistics and feature cross-combination, it generates label results that reflect multi-dimensional feature interaction relationships, enhancing feature interaction analysis capabilities and improving the model's ability to learn complex data patterns.

[0102] Those skilled in the art should understand that this invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to this invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the invention as claimed. The scope of protection of this invention is defined by the appended claims and their equivalents.

Claims

1. A joint binning label generation method for risk profile construction, configured to generate a label result related to a risk profile corresponding to each target according to risk-related data, wherein the risk-related data comprises values of a plurality of different features corresponding to each target, and a risk judgment label corresponding to each target, and the method is characterized in that, The method comprises the following steps: Step S1, dividing all the features into multiple categories, generating a sub-feature set corresponding to each category, the sub-feature set comprising at least one feature and all the values corresponding to the feature; Step S2, for each sub-feature set, calculating the importance value of each feature according to the number of features in the sub-feature set and the values corresponding to the features; Step S3, selecting multiple features from all the sub-feature sets according to the importance values to construct an importance representative feature set; Step S4, performing binning calculation on the importance representative feature set to obtain the binning value of each feature corresponding to each target in the importance representative feature set, and constructing a binning feature set according to all the binning values; Step S5, combining each feature in the binning feature set to obtain a joint binning feature set; Step S6, performing the binning calculation on the joint binning feature set to obtain the binning value of each feature corresponding to each target in the joint binning feature set, and calculating the woe value of each feature corresponding to each target in the joint binning feature set according to all the binning values corresponding to the joint binning feature set and the risk judgment label, wherein the label result of the target is the value of each feature in the joint binning feature set and the corresponding woe value.

2. The joint binning label generation method for risk portrait construction according to claim 1, wherein: wherein, in the step S4, the calculation expression of the binning feature set is: wherein is the set of binned features, q is the total number of features in the set of importance representing features, is the value of bin in the binned values of feature i corresponding to target k, and n is the total number of targets.

3. The joint binning label generation method for risk portrait construction according to claim 1, wherein: wherein, in the step S5, the calculation expression of the joint binning feature set is: UnionBins(x) = [x1||x2, x1||x3,..., x n-1 ||x n ], x = [x1, x2,..., x n ], where X unionbin is the union of the binned feature sets, x n is the nth feature in the feature vector set x, and || is the set concatenation symbol.

4. The joint binned label generation method for risk profiling according to claim 1, characterized in that: wherein, the binning calculation on the feature set to obtain the binning value comprises the following steps: Step T1, generating multiple candidate split thresholds for the feature set and calculating the split value corresponding to each candidate split threshold; Step T2, taking the candidate split threshold corresponding to the maximum split value as the optimal split point; Step T3, repeating steps T1 to T2 until the number of optimal split points reaches a preset value; Step T4, calculating the binning boundary according to all the optimal split points; Step T5, calculating the bins value and bin0 value of each feature corresponding to each target in the feature set as the binning value according to the binning boundary.

5. The joint binning label generation method for risk portrait construction according to claim 4, wherein: wherein the calculation expression of the split value is: H(D j ) = -∑ c∈C p(c) log2 p(c), where IG(D j , θ) is the information gain of the feature set D j with respect to the candidate split threshold θ, |D| is the number of samples in D, is the value of feature i corresponding to target k in the feature set D j , v k is the value of feature i corresponding to target k in the feature set D k , y j is the risk judgment label corresponding to target k, C is the total number of features in the feature set D j , and p(c) is the probability of feature c in the feature set D the calculation expression of the binning boundary is: wherein is a set of bin boundary values, is an ascending sort of all optimal split points, the calculation expression of the bins value and the bin0 value is: In the formula is a feature set D j the value of the feature i corresponding to the target k in the middle, is the left boundary value of the u-th bin interval.

6. The joint binning label generation method for risk portrait construction according to claim 1, wherein: wherein, In the step S2, the importance value is calculated according to the information gain of the feature on the node of the tree of the LightGBM model, The calculation expression of the importance value is: wherein is the importance value of feature i in the sub-feature set j, p is the total number of features in the sub-feature set j, M is the total number of trees in the LightGBM model, N m is the set of nodes of the mth tree, is the indicator function, ΔL m,n is the information gain of feature i on node n of the mth tree, when node n is split using feature i, when the node n does not split using the feature i, 7. The joint binning label generation method for risk portrait construction according to claim 1, characterized in that: wherein In the step S3, the calculation expression of the importance representative feature set is: where X lgbm_represent is a set of importance representative features, m is the total number of sub-feature sets, X j,lgbm_top is a set of importance filtered features from the jthsub-feature set All the features in the sub-feature set j are sorted according to the importance value from large to small, and a preset number of features are selected from the beginning of the sequence to construct the importance screening feature set.

8. The joint binning label generation method for risk portrait construction according to claim 1, characterized in that: wherein In the step S6, according to the bin0 value in the binning value of the feature corresponding to the target, the values of the features corresponding to all the targets are divided into multiple groups, All the values of the features corresponding to the targets in the group have the same bin0 value, The risk judgment label is a binary classification label, The calculation expression of the woe value is: wherein is the total number of values of feature i corresponding to target k in the joint binned feature set, N bad is the total number of values of feature i corresponding to target k in the joint binned feature set, N good is the total number of values of feature i corresponding to target k in the joint binned feature set, N j is the total number of values of feature i corresponding to target k in the joint binned feature set, N total is the total number of values of feature i corresponding to target k in the joint binned feature set, N 9.A joint binning label generation device for risk profile construction, configured to generate a label result associated with a risk profile of each target according to risk-related data, wherein the risk-related data comprises values of a plurality of different features corresponding to each target, and a risk judgment label corresponding to each target, and the joint binning label generation device is characterized in that, Comprise: A sub-set division module divides all the features into multiple categories, generates a sub-feature set corresponding to each category, and the sub-feature set includes at least one feature and all the values corresponding to the feature; An importance value calculation module calculates the importance value of each feature according to the number of features in each sub-feature set and the values corresponding to the features; An importance representative feature set generation module selects multiple features from all the sub-feature sets according to the importance value to construct an importance representative feature set; A binning feature set generation module performs binning calculation on the importance representative feature set to obtain the binning value of each feature corresponding to each target in the importance representative feature set, and constructs a binning feature set according to all the binning values; A joint binning feature set generation module performs joint calculation on each feature in the binning feature set to obtain a joint binning feature set; A woe calculation module performs the binning calculation on the joint binning feature set to obtain the binning value of each feature corresponding to each target in the joint binning feature set, and calculates the woe value of each feature corresponding to each target in the joint binning feature set according to all the binning values corresponding to the joint binning feature set and the risk judgment label, Wherein, the label result of the target is the features in the joint binning feature set and the woe values corresponding thereto.

Images