Polynomial label generation method and device for risk portrait construction

Abstract

The invention provides a polynomial label generation method and device for risk portrait construction, and the method comprises the steps: S1-S3, dividing all features into a plurality of sub-feature sets, and selecting features from each sub-feature set according to an importance value, a correlation value and a feature screening amount to construct a screening feature set; s4, performing polynomial cross feature calculation on features in the screening feature set to obtain a polynomial feature set; s5, calculating an importance value, a correlation value and a feature screening amount of each feature in the polynomial feature set; s6, selecting a plurality of features from the polynomial feature set according to the importance value, the correlation value and the feature screening amount to construct a polynomial screening feature set; and S7, calculating the woe value of each feature corresponding to each target in the polynomial screening feature set. In a word, the method can describe the multi-dimensional risk state of the target in a fine-grained manner.

Description

Technical Field

[0001] The present invention belongs to the field of risk profiling, and specifically relates to a polynomial label generation method and device for risk profiling construction. Background Art

[0002] Risk profiling is used in many fields to characterize the risk status of the subject by analyzing historical data and multi-dimensional features to assist decision-making. Existing risk profiling technology mainly relies on rule-driven methods, that is, building risk assessment logic and generating corresponding risk labels based on domain expert knowledge and existing rules. These methods have certain advantages in practice, such as clear logic and easy explanation, but they also have significant limitations, as shown below:

[0003] 1) Insufficient representation ability of original features: In risk scenarios, original features may not be able to fully describe the complex changes in risk, especially when there are interactive effects or nonlinear relationships between multiple features. Most existing methods are based on single features or simple combinations of features, which cannot accurately capture these complex relationships, resulting in limited representation ability of risk profiles.

[0004] 2) Limitations of feature screening and dimensionality reduction: Traditional methods often use feature screening methods based on statistical indicators or simple algorithms, which may not be able to effectively extract important risk-related features. In addition, the redundancy and noise features in the high-dimensional feature space easily lead to high computational costs and large model complexity, while reducing the efficiency and accuracy of risk label generation.

[0005] 3) Insufficient expression of multi-dimensional feature relationships: When generating feature labels, existing technologies usually only consider single features or simple feature combinations, and fail to fully utilize the interactive relationships between features. For example, linear models often ignore nonlinear feature relationships, and although deep learning models can capture certain nonlinear relationships, they lack targeted optimization, and the model effect depends on large-scale data and complex calculations. Summary of the invention

[0006] The present invention is made to solve the above-mentioned problems, and its purpose is to provide a polynomial label generation method and device for risk profile construction.

[0007] The present invention provides a polynomial label generation method for risk profile construction, which is used to generate label results related to risk profiles corresponding to each target based on risk-related data, wherein the risk-related data includes values ​​of multiple different features corresponding to each target, and a risk judgment label corresponding to each target, and has such characteristics, comprising the following steps: step S1, dividing all features into multiple categories, generating sub-feature sets corresponding to each category, the sub-feature sets including at least one feature and all values ​​corresponding to the feature; step S2, for each sub-feature set, according to the number of features in the sub-feature set and the values ​​corresponding to the features, calculating the importance value and correlation value of each feature and the feature screening amount; step S3, from each sub-feature set, according to the importance value, correlation value and feature screening amount, selecting multiple features to construct a screening feature set; step S4, Perform polynomial cross-feature calculation on the features in the screening feature set to obtain a polynomial feature set; step S5, calculate the importance value and correlation value of each feature and the feature screening amount according to the number of features in the polynomial feature set and the values ​​corresponding to the features; step S6, select multiple features from the polynomial feature set according to the importance value, correlation value and feature screening amount to construct a polynomial screening feature set; step S7, perform binning calculation on the polynomial screening feature set to obtain the binning value of each feature corresponding to each target in the polynomial screening feature set, and calculate the woe value of each feature corresponding to each target in the polynomial screening feature set according to all binning values ​​and risk judgment labels corresponding to the polynomial screening feature set, wherein the label result of the target is each feature of the target in the polynomial screening feature set and its corresponding woe value.

[0008] The polynomial label generation method for risk profile construction provided by the present invention may also have the following features: wherein, in step S4, the calculation expression of the polynomial feature set is: polyfea =ploy(X selected ), x=[χ1,χ2,…,χ n ], where X polyfea is a polynomial feature set, X selected To filter the feature set, χ n is the nth feature in the feature set x.

[0009] The polynomial label generation method for risk profile construction provided by the present invention may also have the following characteristics: wherein, in step S3, the calculation expression for screening the feature set is: X j,selected =X j,corr ∪X j,lgbm , where X selectedis the screening feature set, m is the total number of sub-feature sets, X j,selected is the filter set corresponding to the sub-feature set j, X j,corr The correlation filter feature set corresponding to the sub-feature set j, X j,lgbm For the importance screening feature set corresponding to the sub-feature set j, all features of the sub-feature set j are sorted from large to small according to the correlation value, and the features of the number of feature screening amounts are selected from the beginning of the sequence to construct the correlation screening feature set. All features of the sub-feature set j are sorted from large to small according to the importance value, and the features of the number of feature screening amounts are selected from the beginning of the sequence to construct the importance screening feature set.

[0010] The polynomial label generation method for risk profile construction provided by the present invention may also have the following characteristics: wherein, in step S2, the calculation expression of the correlation value is: In the formula is the correlation value of feature i in feature set j, is the value of feature i corresponding to the kth target in feature set j, is the mean of feature i in feature set j, y k is the risk judgment label corresponding to the k-th target, is the mean of the risk judgment labels of all targets, and n is the total number of targets.

[0011] In the polynomial label generation method for risk profile construction provided by the present invention, it can also have the following characteristics: wherein, in step S2, according to the information gain of the feature on the node of the tree of the LightGBM model, the corresponding importance value is calculated, and the calculation expression of the importance value is: In the formula is the importance value of feature i in feature set j, p is the total number of features in feature set j, M is the total number of trees in the LightGBM model, and 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 node n does not use feature i for splitting,

[0012] In the polynomial label generation method for risk profile construction provided by the present invention, there may also be such a feature: wherein, in step S2, the calculation expression of the feature screening amount is: Where select_len j is the feature screening amount corresponding to feature set j, p is the total number of features in feature set j, This is a round-down operation.

[0013] In the polynomial label generation method for risk portrait construction provided by the present invention, it can also have the following characteristics: wherein, step S7 includes the following sub-steps: step S7-1, for the polynomial screening feature set, generate multiple candidate splitting thresholds, and calculate the splitting values ​​corresponding to each candidate splitting threshold; step S7-2, take the candidate splitting threshold corresponding to the largest splitting value as the optimal splitting point; step S7-3, repeat step S7-1 to step S7-2 until the number of optimal splitting points reaches a preset value; step S7-4, calculate the bin boundaries based on all optimal splitting points; step S7-5, based on the bin boundaries, calculate the bins value and bin0 value of each feature corresponding to each target in the polynomial screening feature set as the bin value; step S7-6, calculate the woe value of each feature corresponding to each target in the polynomial screening feature set based on all bin values.

[0014] In the polynomial label generation method for risk profile construction provided by the present invention, it can also have the following characteristics: wherein the calculation expression of the split value is: H(D ps )=-∑ c∈C p(c)log2p(c), In the formula, IG(D ps , θ) is the splitting value of the candidate splitting threshold θ corresponding to the polynomial screening feature set, |D| is the number of samples in D, is the value of feature i corresponding to target k in the polynomial screening feature set, v k is the target k, y k is the risk judgment label corresponding to target k, C is the total number of features in the polynomial screening feature set, p(c) is the probability of feature c in the polynomial screening feature set, and the calculation expression of the bin boundary is: In the formula for The set of bin boundary values, To sort all optimal split points in ascending order, the calculation expressions for bins value and bin0 value are: In the formula The value of feature i corresponding to target k in the polynomial screening feature set, for The left boundary value of the u-th binning interval.

[0015] In the polynomial label generation method for risk profile construction provided by the present invention, it can also have the following characteristics: wherein, in step S7-6, according to the bin0 value of the feature corresponding to the target, the values ​​of the features corresponding to all targets are divided into multiple groups, the values ​​of the features corresponding to all targets in the group have the same bin0 value, the risk judgment label is a binary classification label, and the calculation expression of the woe value is: In the formula is the woe value of feature i corresponding to target k in the polynomial screening feature set, N bad N is the total number of risk judgment labels with bad labels corresponding to all values ​​in the group where the value of feature i corresponding to target k in the polynomial screening feature set belongs, good N is the total number of risk judgment labels whose labels are good categories in the group where all values ​​of the feature i corresponding to the target k in the polynomial screening feature set belong, total is the total number of values ​​of feature i corresponding to target k in the polynomial screening feature set.

[0016] The present invention also provides a polynomial label generation device for risk portrait construction, which is used to generate label results related to risk portraits corresponding to each target based on risk-related data, and the risk-related data includes the values ​​of multiple different features corresponding to each target, and the risk judgment label corresponding to each target, which has the following characteristics, including: a subset division module, which divides all features into multiple categories, and generates sub-feature sets corresponding to each category, and the sub-feature sets include at least one feature and all values ​​corresponding to the feature; a screening module, which calculates the importance value and correlation value of each feature and the feature screening amount according to the number of features in the input feature set and the values ​​corresponding to the features; a screening set generation module, which selects from each sub-feature set according to the importance value, correlation value and feature screening amount corresponding to the sub-feature set. Take multiple features to construct a screening feature set; a polynomial cross module performs polynomial cross feature calculation on the features in the screening feature set to obtain a polynomial feature set; a polynomial screening set generation module selects multiple features from the polynomial feature set according to the corresponding importance value, correlation value and feature screening amount to construct a polynomial screening feature set; a woe calculation module performs binning calculation on the polynomial screening feature set to obtain the bin value of each feature corresponding to each target in the polynomial screening feature set, and calculates the woe value of each feature corresponding to each target in the polynomial screening feature set based on all the bin values ​​and risk judgment labels corresponding to the polynomial screening feature set, where the label result of the target is the various features of the target in the polynomial screening feature set and its corresponding woe value.

[0017] Functions and Effects of the Invention

[0018] According to the polynomial label generation method and device for risk profile construction involved in the present invention, by dividing the features into sub-feature sets, and calculating the corresponding importance values ​​and correlation values ​​and feature screening amounts, multiple features are screened from each sub-feature set to construct a screening feature set, and then polynomial cross-feature calculations are performed on the features in the screening feature set to obtain a polynomial feature set, and then the corresponding importance values ​​and correlation values ​​and feature screening amounts are calculated for the polynomial feature set to screen the features to construct a polynomial screening feature set, and finally the woe value of each target is calculated for the features in the polynomial screening feature set to obtain the label result. Therefore, the polynomial label generation method and device for risk profile construction of the present invention can describe the multidimensional risk status of the target in a fine-grained manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is a block diagram of a polynomial label generation device for risk profile construction in an embodiment of the present invention;

[0020] Figure 2 It is a schematic diagram of a process of generating a woe value by a woe calculation module in an embodiment of the present invention;

[0021] Figure 3 is a flow chart of a polynomial label generation method for risk profile construction in an embodiment of the present invention;

[0022] Figure 4 is a radar schematic diagram of a high-risk user portrait in an embodiment of the present invention;

[0023] Figure 5 is a radar schematic diagram of a low-risk user portrait in an embodiment of the present invention;

[0024] Figure 6 Schematic diagram of visualizing a scorecard in an embodiment of the present invention. DETAILED DESCRIPTION

[0025] In order to make the technical means, creative features, objectives and effects achieved by the present invention easy to understand, the following embodiments and the accompanying drawings specifically illustrate the polynomial label generation method and device for risk profile construction of the present invention.

[0026] This embodiment provides a polynomial label generation device for risk profile construction, which is used to generate label results related to risk profiles for each target according to risk-related data. The risk-related data includes the values ​​of multiple different features corresponding to each target, and the risk judgment label corresponding to each target. The risk judgment label is a binary classification label.

[0027] In this embodiment, the polynomial label generation device for risk profile construction is applied to 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, each trading account is a target, for each v i ∈V has a binary label whether it is illegal, that is, the line judgment label y i ∈Y, 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 ={ i,k |k=1,2,…,n}, represents the feature χ i The feature set of i,k Indicates the feature χ corresponding to the kth trading account i In other embodiments, the polynomial label generation device for risk profile construction can be applied to other fields, such as food safety, where the target is a specified food, and the risk-related data is production data related to the specified food, such as the manufacturer.

[0028] Figure 1 It is a block diagram of a polynomial label generation device for risk profile construction in an embodiment of the present invention.

[0029] like Figure 1 As shown, the polynomial label generation device 100 for risk profile construction includes a subset partitioning module 11, a screening module 12, a screening set generation module 13, a polynomial intersection module 14, a polynomial screening set generation module 15, a woe calculation module 16 and a control module 17 for controlling the operation of the above modules.

[0030] The subset division module 11 divides all features into multiple categories and generates a sub-feature set corresponding to each category. The sub-feature set includes at least one feature and all values ​​corresponding to the feature.

[0031] In this embodiment, the subset division module 11 divides the information into m categories, that is, obtains the sub-feature set X 1 ,X 2 ,…,X m , and satisfies

[0032] The screening module 12 calculates the importance value and the correlation value of each feature and the feature screening amount according to the number of features in the input feature set and the values ​​corresponding to the features.

[0033] Among them, the screening module 12 includes a LightGBM model. The screening module 12 calculates the corresponding importance value 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:

[0034]

[0035] In the formula is the importance value of feature i in feature set j, p is the total number of features in feature set j, M is the total number of trees in the LightGBM model, and 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 node n does not use feature i for splitting,

[0036] The loss function corresponding to the LightGBM model in this embodiment is the binary cross entropy loss L, and its calculation expression is:

[0037]

[0038] Where N is the total number of samples, y i is the risk judgment label of the i-th sample, is the predicted probability of the LightGBM model for the i-th sample.

[0039] The calculation expression of the correlation value is:

[0040]

[0041] In the formula is the correlation value of feature i in feature set j, is the value of feature i corresponding to the kth target in feature set j, is the mean of feature i in feature set j, y k is the risk judgment label corresponding to the k-th target, is the mean of the risk judgment labels of all targets, and n is the total number of targets.

[0042] The calculation expression of the feature screening amount is:

[0043]

[0044] Where select_len j is the feature screening amount corresponding to feature set j, p is the total number of features in feature set j, This is a round-down operation.

[0045] The screening set generation module 13 selects multiple features from each sub-feature set according to the importance value, correlation value and feature screening amount corresponding to the sub-feature set to construct a screening feature set.

[0046] Among them, the calculation expression for filtering feature sets is:

[0047]

[0048] X j,selected =X j,corr ∪X j,lgbm ,

[0049] Where X selected is the screening feature set, m is the total number of sub-feature sets, X j,selected is the filter set corresponding to the sub-feature set j, X j,corr The correlation filter feature set corresponding to the sub-feature set j, X j,lgbm Filter the feature set corresponding to the importance of sub-feature set j.

[0050] Sort all the features of sub-feature set j from large to small according to the correlation value, select the number of features of feature screening from the beginning of the sequence, and construct a correlation screening feature set. Correlation screening feature set X j,corr The calculation expression is:

[0051] X j,corr =argsort(|correlations j |)[:select_len j ],

[0052]

[0053] In the formula, argsort(|correlations j |) is to sort the correlation values ​​of the sub-feature set j in descending order according to the absolute value, that is, in this embodiment, the correlation values ​​are sorted according to their absolute values, [:select_len j ] is the feature screening amount corresponding to the sub-feature set j.

[0054] Sort all the features of sub-feature set j from large to small according to their importance values, select the number of features of feature screening quantity from the beginning of the sequence, and construct an importance screening feature set. Importance screening feature set X j,lgbm The calculation expression is:

[0055] X j,lgbm =argsort(|lgbm_importance j|)[:select_len j ],

[0056]

[0057] In the formula, argsort(|lgbm_importance j |) is to sort the importance values ​​of sub-feature set j in descending order according to their absolute values.

[0058] The polynomial crossover module 14 performs polynomial crossover feature calculation on the features in the screening feature set to obtain a polynomial feature set.

[0059] Among them, the calculation expression of the polynomial feature set is:

[0060] X polyfea =poly(X selected ),

[0061]

[0062] x=[χ1,χ2,…,χ n ],

[0063] Where X polyfea is a polynomial feature set, X selected To filter the feature set, χ n is the nth feature in the feature set x.

[0064] The polynomial screening set generation module 15 selects multiple features from the polynomial feature set according to the corresponding importance value, correlation value and feature screening amount to construct a polynomial screening feature set. The specific processing process of the polynomial screening set generation module 15 generating the polynomial screening feature set according to the polynomial feature set in this embodiment is the same as the processing process of the screening set generation module 13 generating the corresponding screening set according to the sub-feature set, which will not be repeated here.

[0065] The woe calculation module 16 performs bin calculation on the polynomial screening feature set to obtain the bin values ​​of each feature corresponding to each target in the polynomial screening feature set, and calculates the woe value of each feature corresponding to each target in the polynomial screening feature set based on all the bin values ​​and risk judgment labels corresponding to the polynomial screening feature set. Among them, the label result of the target is the various features of the target in the polynomial screening feature set and its corresponding woe value.

[0066] Figure 2 It is a schematic diagram of the process of generating a woe value by a woe calculation module in an embodiment of the present invention.

[0067] like Figure 2As shown, the process of generating the woe value by the woe calculation module 16 includes the following steps:

[0068] Step S7-1, a polynomial screening feature set is used to generate multiple candidate split thresholds, and the split value corresponding to each candidate split threshold is calculated. In this embodiment, the candidate split threshold is obtained by the average value of the sorted adjacent samples.

[0069] The calculation expression of the split value is:

[0070]

[0071] H(D ps )=-∑ c∈C p(c)log2p(c),

[0072]

[0073] In the formula, IG(D ps , θ) is the splitting value of the candidate splitting threshold θ corresponding to the polynomial screening feature set, |D| is the number of samples in D, and a sample includes the values ​​of all features corresponding to a target in the set D. is the value of feature i corresponding to target k in the polynomial screening feature set, v k is the target k, y k is the risk judgment label corresponding to target k, C is the total number of features in the polynomial screening feature set, and p(c) is the probability of feature c in the polynomial screening feature set.

[0074] Step S7-2: taking the candidate splitting threshold corresponding to the maximum splitting value as the optimal splitting point.

[0075] Step S7-3, repeating steps S7-1 to S7-2 until the number of optimal splitting points reaches a preset value. In this embodiment, iterating two layers generates at most four optimal splitting points.

[0076] Step S7-4, calculating the bin boundaries based on all the optimal splitting points.

[0077] The calculation expression of the bin boundary is:

[0078]

[0079] In the formula for The set of bin boundary values, To sort all the optimal splitting points in ascending order. In this embodiment, negative infinity -∞ and positive infinity ∞ are used to ensure that the final binning boundary allows all values ​​to be covered.

[0080] Step S7-5, according to the binning boundaries, calculate the bins value and bin0 value of each feature corresponding to each target in the polynomial screening feature set as the binning value.

[0081] Among them, the calculation expressions of bins value and bin0 value are:

[0082]

[0083]

[0084] In the formula The value of feature i corresponding to target k in the polynomial screening feature set, for The left boundary value of the u-th binning interval.

[0085] Step S7-6, based on all bin values, calculate the woe value of each feature corresponding to each target in the polynomial screening feature set.

[0086] Among them, the woe calculation module 16 divides the values ​​of the features corresponding to all targets into multiple groups according to the bin0 value of the feature corresponding to the target The values ​​of the features corresponding to all targets in the group have the same bin0 value, that is, if The target corresponding feature

[0087] The calculation expression of woe value is:

[0088]

[0089] In the formula is the woe value of feature i corresponding to target k in the polynomial screening feature set, N bad N is the total number of risk judgment labels with bad labels corresponding to all values ​​in the group where the value of feature i corresponding to target k in the polynomial screening feature set belongs, good N is the total number of risk judgment labels whose labels are good categories in the group where all values ​​of the feature i corresponding to the target k in the polynomial screening feature set belong, total is the total number of values ​​of feature i corresponding to target k in the polynomial screening feature set. In this embodiment, the risk judgment label is 0 or 1, 0 represents a good category, and 1 represents a bad category. In other embodiments, other forms can be used to replace 0 and 1 to distinguish between good and bad categories.

[0090] The control module 17 stores a control program for controlling the operation of each module.

[0091] The following describes the process of using the polynomial label generation device 100 for risk profile construction to perform a polynomial label generation method for risk profile construction in conjunction with the accompanying drawings.

[0092] Figure 3 It is a flowchart of a polynomial label generation method for risk profile construction in an embodiment of the present invention.

[0093] like Figure 3 As shown, the polynomial label generation method for risk profile construction includes the following steps:

[0094] Step S1: using the subset division module 11 to divide all features into multiple categories, generating a sub-feature set corresponding to each category, wherein the sub-feature set includes at least one feature and all values ​​corresponding to the feature.

[0095] Step S2: Using the screening module 12 to calculate the importance value and correlation value of each feature and the feature screening amount for each sub-feature set according to the number of features in the sub-feature set and the values ​​corresponding to the features.

[0096] Step S3, using the screening set generation module 13 to select multiple features from each sub-feature set according to the importance value, the relevance value and the feature screening amount to construct a screening feature set.

[0097] Step S4: Use the polynomial crossover module 14 to perform polynomial crossover feature calculation on the features in the screening feature set to obtain a polynomial feature set.

[0098] Step S5, using the screening module 12 to calculate the importance value and correlation value of each feature and the feature screening amount according to the number of features and the values ​​corresponding to the features in the polynomial feature set.

[0099] Step S6, using the polynomial screening set generation module 15, multiple features are selected from the polynomial feature set according to the importance value, the correlation value and the feature screening amount to construct a polynomial screening feature set.

[0100] Step S7, use the Woe calculation module 16 to perform bin calculation on the polynomial screening feature set, obtain the bin value of each feature corresponding to each target in the polynomial screening feature set, and calculate the Woe value of each feature corresponding to each target in the polynomial screening feature set based on all the bin values ​​and risk judgment labels corresponding to the polynomial screening feature set.

[0101] In this embodiment, a radar chart of the user portrait of the target can be constructed based on the label results of the target.

[0102] Figure 4 It is a radar schematic diagram of a high-risk user portrait in an embodiment of the present invention.

[0103] Figure 5 It is a radar schematic diagram of a low-risk user portrait in an embodiment of the present invention.

[0104] like Figure 4 and Figure 5 As shown in the figure, the label result includes 8 features, i.e., polynomial labels and their corresponding values, i.e., ploy_fea_1, ploy_fea_2, ploy_fea_3, ploy_fea_4, ploy_fea_5, ploy_fea_6, ploy_fea_7, and ploy_fea_8. It can be seen that the area occupied by abnormal subjects, i.e., high-risk users, is large, while the area occupied by normal subjects, i.e., low-risk users, is small, which can intuitively show that the label result effectively depicts the multi-dimensional risk level of the subject risk.

[0105] In this embodiment, based on the existing scoring model, the characteristic coefficient and intercept are extracted, the benchmark score and the score PDO for each doubling of the odds are set, and the factor weights and offsets are calculated at the same time to create a score card containing the characteristics, coefficients, sample scores and predicted probabilities. The scores are divided into several equidistant scoring intervals, and the number and proportion of positive and negative samples in each scoring interval are calculated to intuitively reflect the distribution of positive and negative samples in each scoring interval.

[0106] Figure 6 Schematic diagram of visualizing a scorecard in an embodiment of the present invention.

[0107] like Figure 6 As shown in the figure, the horizontal axis is the sample score interval value score_bins, the vertical axis of the histogram is the number of samples in the score interval Count, and the vertical axis of the line graph is the bad sample ratio Bad Rate in the score interval. It can be seen that the score card based on the label result intuitively shows the distinction between positive and abnormal in each module, and realizes a strong association between abnormal subjects and risk scores.

[0108] In this embodiment, some key model labels are selected, grouped using bin values, and the number and proportion of bad samples are calculated within the group. The results are shown in the following table:

[0109]

[0110] The first column in the table above is the different polynomial labels χ polyfea1 , χ polyfea2 and χ polyfea3, the second to sixth columns are woe value, bins range, number of samples in bad category, total number of samples and proportion of samples in bad category. It can be seen that in the given example key polynomial label grouping, the proportion of bad samples with the best label reaches 98.43%, showing the accurate expression of bad samples by polynomial labels in specific dimensions.

[0111] Functions and Effects of the Embodiments

[0112] According to the polynomial label generation method and device for risk profiling involved in this embodiment, by dividing the features into sub-feature sets, and calculating the corresponding importance values ​​and correlation values ​​and feature screening amounts, multiple features are screened from each sub-feature set to construct a screening feature set, and then polynomial cross-feature calculations are performed on the features in the screening feature set to obtain a polynomial feature set, and then the corresponding importance values ​​and correlation values ​​and feature screening amounts are calculated for the polynomial feature set to screen the features to construct a polynomial screening feature set, and finally the woe value of each target is calculated for the features in the polynomial screening feature set to obtain a label result. In short, this method generates a polynomial screening feature set through polynomial cross-calculation and screening, which enhances the capture of nonlinear relationships and the characterization of feature interaction relationships, retains key information related to risks while effectively reducing the dimension, and describes the multidimensional risk status of the target in a fine-grained manner.

[0113] Those skilled in the art should understand that the present invention is not limited to the above embodiments, and the above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may be subject to various changes and improvements, which are within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A polynomial label generation method for risk profile construction, used to generate label results related to risk profiles corresponding to each target based on risk-related data, wherein the risk-related data includes values ​​of multiple different features corresponding to each target and risk judgment labels corresponding to each target, characterized in that: The following steps are involved: Step S1, dividing all the features into multiple categories, generating a sub-feature set corresponding to each category, wherein the sub-feature set includes at least one feature and all the values ​​corresponding to the feature; Step S2, for each of the sub-feature sets, according to the number of the features in the sub-feature set and the values ​​corresponding to the features, calculate the importance value and the correlation value of each of the features and the feature screening amount; Step S3, from each of the sub-feature sets, according to the importance value, the relevance value and the feature screening amount, selecting a plurality of the features to construct a screening feature set; Step S4, performing polynomial cross feature calculation on the features in the screening feature set to obtain a polynomial feature set; Step S5, calculating the importance value and the correlation value of each feature and the feature screening amount according to the number of features in the polynomial feature set and the values ​​corresponding to the features; Step S6, selecting a plurality of the features from the polynomial feature set according to the importance value, the relevance value and the feature screening amount to construct a polynomial screening feature set; Step S7, performing bin calculation on the polynomial screening feature set to obtain the bin values ​​of each feature corresponding to each target in the polynomial screening feature set, and calculating the woe value of each feature corresponding to each target in the polynomial screening feature set according to all the bin values ​​corresponding to the polynomial screening feature set and the risk judgment label, Among them, the label result of the target is each of the features of the target in the polynomial screening feature set and its corresponding woe value.

2. The polynomial label generation method for risk profile construction according to claim 1, characterized in that: in, In step S4, the calculation expression of the polynomial feature set is: X polyfea =poly(X selected ), x=[x1,x2,…,x n ], Where X polyfea is a polynomial feature set, X selected To filter the feature set, X n is the nth feature in the feature set X.

3. The polynomial label generation method for risk profile construction according to claim 1, characterized in that: in, In step S3, the calculation expression of the screening feature set is: X j,selected =X j,corr ∪X j,lgbm , Where X selected is the screening feature set, m is the total number of sub-feature sets, X j,selected is the filter set corresponding to the sub-feature set j, X j,corr The correlation filter feature set corresponding to the sub-feature set j, X j,lgbm Filter the feature set corresponding to the importance of sub-feature set j, All the features of sub-feature set j are sorted from large to small according to the correlation value, and the features of the number of feature screening quantities are selected from the beginning of the sequence to construct the correlation screening feature set, All the features of sub-feature set j are sorted from large to small according to the importance values, and the features of the number of feature screening quantities are selected from the beginning of the sequence to construct the importance screening feature set.

4. The polynomial label generation method for risk profile construction according to claim 1, characterized in that: in, In step S2, the calculation expression of the correlation value is: In the formula is the correlation value of feature i in feature set j, is the value of feature i corresponding to the kth target in feature set j, is the mean of feature i in feature set j, y k is the risk judgment label corresponding to the k-th target, is the mean of the risk judgment labels of all targets, and n is the total number of targets.

5. The polynomial label generation method for risk profile construction according to claim 1, characterized in that: in, In step S2, the corresponding 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: In the formula is the importance value of feature i in feature set j, p is the total number of features in 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 at node n of the mth tree, When node n is split using feature i, When node n does not use feature i for splitting, 6. The polynomial label generation method for risk profile construction according to claim 1, characterized in that: in, In step S2, the calculation expression of the characteristic screening amount is: Where select_len j is the feature screening amount corresponding to feature set j, p is the total number of features in feature set j, This is a round-down operation.

7. The polynomial label generation method for risk profile construction according to claim 1, Features: Wherein, the step S7 includes the following sub-steps: Step S7-1, screening the polynomial feature set to generate multiple candidate splitting thresholds, and calculating the splitting value corresponding to each of the candidate splitting thresholds; Step S7-2, taking the candidate splitting threshold corresponding to the maximum splitting value as the optimal splitting point; Step S7-3, repeatedly executing steps S7-1 to S7-2 until the number of the optimal splitting points reaches a preset value; Step S7-4, calculating the bin boundaries according to all the optimal splitting points; Step S7-5, according to the binning boundaries, calculating the bins value and bin0 value of each of the features corresponding to each of the targets in the polynomial screening feature set as the binning value; Step S7-6, based on all the bin values, calculate the woe value of each feature corresponding to each target in the polynomial screening feature set.

8. The polynomial label generation method for risk profile construction according to claim 7, characterized in that: in, The calculation expression of the split value is: H(D ps )=-∑ c∈C p(c)log2p(c), In the formula, IG(D ps , θ) is the splitting value of the candidate splitting threshold θ corresponding to the polynomial screening feature set, |D| is the number of samples in D, is the value of feature i corresponding to target k in the polynomial screening feature set, v k is the target k, y k is the risk judgment label corresponding to target k, C is the total number of features in the polynomial screening feature set, p(c) is the probability of feature c in the polynomial screening feature set, The calculation expression of the bin boundary is: In the formula for The set of bin boundary values, To sort all optimal splitting points in ascending order, The calculation expressions of the bins value and the bin0 value are: In the formula The value of feature i corresponding to target k in the polynomial screening feature set, for The left boundary value of the u-th binning interval.

9. The polynomial label generation method for risk profile construction according to claim 7, characterized in that: in, In step S7-6, according to the bin0 value of the feature corresponding to the target, the values ​​of the feature corresponding to all the targets are divided into multiple groups, The values ​​of the features corresponding to all 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: In the formula is the woe value of feature i corresponding to target k in the polynomial screening feature set, N bad N is the total number of risk judgment labels with bad labels corresponding to all values ​​in the group where the value of feature i corresponding to target k in the polynomial screening feature set belongs, good N is the total number of risk judgment labels whose labels are good categories in the group where all values ​​of the feature i corresponding to the target k in the polynomial screening feature set belong, total is the total number of values ​​of feature i corresponding to target k in the polynomial screening feature set.

10. A polynomial label generation device for risk profile construction, used to generate label results related to risk profiles corresponding to each target based on risk-related data, wherein the risk-related data includes values ​​of multiple different features corresponding to each target and risk judgment labels corresponding to each target, characterized in that: include: A subset division module divides all the features into multiple categories and generates a sub-feature set corresponding to each category, wherein the sub-feature set includes at least one feature and all the values ​​corresponding to the feature; A screening module calculates the importance value and relevance value of each feature and the feature screening amount according to the number of features in the input feature set and the values ​​corresponding to the features; A screening set generating module, which selects a plurality of features from each of the sub-feature sets according to the importance value, the relevance value and the feature screening amount corresponding to the sub-feature set to construct a screening feature set; A polynomial crossover module performs polynomial crossover feature calculation on the features in the screening feature set to obtain a polynomial feature set; A polynomial screening set generation module selects a plurality of features from the polynomial feature set according to the corresponding importance value, the correlation value and the feature screening amount to construct a polynomial screening feature set; The woe calculation module performs bin calculation on the polynomial screening feature set to obtain the bin values ​​of each feature corresponding to each target in the polynomial screening feature set, and calculates the woe value of each feature corresponding to each target in the polynomial screening feature set according to all the bin values ​​and the risk judgment label corresponding to the polynomial screening feature set. Among them, the label result of the target is each of the features of the target in the polynomial screening feature set and its corresponding woe value.

Images