Multi-view label generation method and device for risk portrait construction

Abstract

The invention provides a multi-view label generation method and device for risk portrait construction, and the method is characterized in that the method comprises the steps: S1-S2, constructing a sub-feature set, and calculating the importance value, the correlation value and the feature screening amount of each feature; s3, constructing a screening feature set; s4, calculating and constructing a positive correlation feature set and a negative correlation feature set according to correlation values of all features in the screening feature set; s5, constructing a discrete feature set and a continuous feature set according to the number of unique values corresponding to each feature in the screening feature set; s6, obtaining a multi-view model feature set according to the positive correlation feature set, the negative correlation feature set, the discrete feature set and the continuous feature set; and S7, calculating the woe value of each feature corresponding to each target in the multi-view model feature set. In a word, the method can generate the tag with better risk expression ability.

Description

Technical Field

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

[0002] Risk profiling is used in many fields, and building accurate risk profiling is crucial to identifying, assessing, and predicting risks. Traditional risk profiling methods usually rely on rule-driven methods or machine learning models to extract the characteristics of the subject through historical data, and then generate risk labels based on these characteristics to assess the risk status of the subject. However, with the rapid growth of data volume and data types, traditional methods have exposed some significant deficiencies in feature extraction and risk assessment:

[0003] 1) Feature interference problem: In the subject-related data, there are complex correlations between different features, including positive correlation, negative correlation and even nonlinear correlation. Traditional machine learning models often encounter the problem of gradient offset when dealing with positive and negative correlation features, which makes it difficult for the model to effectively focus on key risk factors during the learning process, reducing the model's prediction accuracy. In addition, feature interference can also cause model training instability, which will have an adverse impact on the final risk profile construction.

[0004] 2) Learning bias of feature types: In risk profiling, feature types are diverse, such as the coexistence of discrete and continuous features, and their distribution is complex. Existing deep learning models usually learn discrete or continuous column features based on the value or distribution characteristics of the features, which easily leads to bias in the learning effect of the model for different feature types and makes it difficult to capture the correlation between discrete and continuous features. This limitation affects the effectiveness of the model in building a global risk profile.

[0005] 3) Lack of multi-view feature representation: Current risk profiling technology rarely considers multi-view feature representation, that is, it lacks the ability to generate a comprehensive feature space from different angles, such as feature correlation, distribution discreteness, etc. Existing methods usually extract features based on a single perspective, which is difficult to reflect the complex risk characteristics of the subject. This results in the dimensions of risk profiling being not comprehensive enough and difficult to meet the risk assessment needs in complex scenarios. Summary of the invention

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

[0007] The present invention provides a multi-view 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, including 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 corresponding importance value, correlation value and feature screening amount, selecting multiple features to construct a screening feature set; step S4, according to the features in the screening feature set, calculating the importance value and correlation value of each feature and the feature screening amount. The number of features and the value corresponding to each feature are used to calculate the correlation value of each feature, and a positively correlated feature set and a negatively correlated feature set are constructed according to the correlation value; step S5, according to the number of unique values ​​corresponding to each feature in the screening feature set, a discrete feature set and a continuous feature set are constructed; step S6, according to the positively correlated feature set, the negatively correlated feature set, the discrete feature set and the continuous feature set, combined with the machine learning model, a multi-view model feature set is obtained; step S7, the multi-view model feature set is binned, and the bin value of each feature corresponding to each target in the multi-view model feature set is calculated, and the woe value of each feature corresponding to each target in the multi-view model feature set is calculated according to all the bin values ​​and risk judgment labels corresponding to the multi-view model feature set, wherein the label result of the target is each feature of the target in the multi-view model feature set and its corresponding woe value.

[0008] In the multi-view label generation method for risk profile construction provided by the present invention, there may also be such a feature: wherein the calculation expressions of the positive correlation feature set and the negative correlation feature set are: Where X p is a set of positively correlated features, To filter the correlation value of feature i in the feature set, X n is a set of negatively correlated features.

[0009] In the multi-view label generation method for risk profile construction provided by the present invention, there may also be such a feature: wherein the calculation expressions of the discrete feature set and the continuous feature set are: Where X d is a discrete feature set, X c is a continuous feature set, is the number of unique values ​​of feature i in the filtered feature set, and p is the total number of features in the filtered feature set.

[0010] In the multi-view 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 multi-view model feature set is: X p_d =X p ∩X d , X p_c =X p ∩X c , X n_d =X n ∩X d , X n_c =X n ∩X c , where X multi_view is the multi-view model feature set, || is the set concatenation symbol, The machine learning model is based on the input feature set X p_d The generated sample prediction value, The machine learning model is based on the input feature set X p_c The generated sample prediction value, The machine learning model is based on the input feature set X n_d The generated sample prediction value, The machine learning model is based on the input feature set X n_c The generated sample predictions.

[0011] In the multi-view 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 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.

[0012] In the multi-view 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 sub-feature set j, p is the total number of features in 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 node n does not use feature i for splitting, In step S2, the calculation expression of the feature screening amount is: Where select_len j is the feature screening amount corresponding to sub-feature set j, p is the total number of features in sub-feature set j, This is a round-down operation.

[0013] In the multi-view label generation method for risk profile construction provided by the present invention, the following features may also be provided: wherein, in step S3, the calculation expression for screening the feature set is: X j,selected =X j,corr ∪X j,lgbm , Where 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, X selected is the screening feature set, m is the total number of sub-feature sets, all 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 features of sub-feature set j are sorted from large to small according to the importance value, 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.

[0014] In the multi-view label generation method for risk profile 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 multi-view model 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 steps S6-1 to S6-2 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 multi-view model feature set as the bin value; step S7-6, calculate the woe value of each feature corresponding to each target in the multi-view model feature set based on all bin values.

[0015] In the multi-view 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 mv )=-∑ c∈C p(c)log2p(c), In the formula, IG(D mv , θ) is the splitting value of the candidate splitting threshold θ corresponding to the multi-view model feature set, |D| is the number of samples in D, is the value of feature i corresponding to target k in the multi-view model 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 multi-view model feature set, p(c) is the probability of feature c in the multi-view model 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 is the value of feature i corresponding to target k in the multi-view model feature set, for The left boundary value of the u-th binning interval. 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. The calculation expression of the woe value is: In the formula is the woe value of feature i corresponding to target k in the multi-view model feature set, N bad 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 multi-view model feature set belongs, N good is the total number of risk judgment labels whose labels are good categories in the group where all values ​​of feature i corresponding to target k in the multi-view model feature set belong, N total is the total number of values ​​of feature i corresponding to target k in the multi-view model feature set.

[0016] The present invention also provides a multi-view label generation device 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 the values ​​of multiple different features corresponding to each target, and the risk judgment label corresponding to each target, and 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 sub-feature set and the values ​​corresponding to the features; a screening set generation module, which selects multiple features from each sub-feature set according to the corresponding importance value, correlation value and feature screening amount to construct a screening feature set; a positive and negative correlation feature set generation module, which selects multiple features from each sub-feature set according to the corresponding importance value, correlation value and feature screening amount to construct a screening feature set according to the number of features in the screening feature set and The values ​​corresponding to each feature are used to calculate the correlation values ​​of each feature, and a positively correlated feature set and a negatively correlated feature set are constructed based on the correlation values; a discrete-continuous feature set generation module is used to construct a discrete feature set and a continuous feature set based on the number of unique values ​​corresponding to each feature in the screening feature set; a multi-view model feature set generation module is used to obtain a multi-view model feature set based on the positively correlated feature set, the negatively correlated feature set, the discrete feature set and the continuous feature set in combination with the machine learning model; a woe calculation module is used to bin the multi-view model feature set, calculate the bin values ​​of each feature corresponding to each target in the multi-view model feature set, and calculate the woe values ​​of each feature corresponding to each target in the multi-view model feature set based on all the bin values ​​and risk judgment labels corresponding to the multi-view model feature set, where the label result of the target is each feature of the target in the multi-view model feature set and its corresponding woe value.

[0017] Functions and Effects of the Invention

[0018] According to the multi-view label generation method and device for risk profile construction involved in the present invention, by calculating the correlation value and the number of unique values ​​of the features in the screening set, constructing a positive correlation feature set, a negative correlation feature set, a discrete feature set and a continuous feature set, and then generating a multi-view model feature set, and then binning and woe value calculation are performed on the multi-view model feature set to obtain the label result. Therefore, the multi-view label generation method and device for risk profile construction of the present invention can generate labels with better risk expression capabilities and improve the comprehensiveness and accuracy of risk profiles. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is a block diagram of a multi-view 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 multi-view 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 multi-view label generation method and device for risk profiling construction of the present invention.

[0026] This embodiment provides a multi-view 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 multi-view label generation device for risk profiling 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 vi ∈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 x corresponding to the kth trading account i In other embodiments, the multi-view 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 multi-view label generation device for risk profile construction in an embodiment of the present invention.

[0029] like Figure 1 As shown, the multi-view label generation device 100 for risk portrait construction includes a subset division module 11, a screening module 12, a screening set generation module 13, a positive and negative correlation feature set generation module 14, a discrete continuous feature set generation module 15, a multi-view model feature set generation module 16, a woe calculation module 17 and a control module 18 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 for each sub-feature set according to the number of features in the sub-feature set and the values ​​corresponding to the features.

[0033] 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 sub-feature set j, p is the total number of features in 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 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 sub-feature set j, p is the total number of features in sub-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 corresponding importance value, correlation value and feature screening amount to construct a screening feature set.

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

[0047] X j,selected =X j,corr ∪X j,lgbm ,

[0048]

[0049] Where 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, X selected is the filter feature set, and m is the total number of sub-feature sets.

[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 positive and negative correlation feature set generation module 14 calculates the correlation value of each feature according to the number of features in the screening feature set and the value corresponding to each feature, and constructs a positive correlation feature set and a negative correlation feature set according to the correlation value.

[0059] Among them, the calculation expressions of positive correlation feature set and negative correlation feature set are:

[0060]

[0061] Where X p is a set of positively correlated features, To filter the correlation value of feature i in the feature set, X n is a set of negatively correlated features.

[0062] The discrete-continuous feature set generation module 15 constructs a discrete feature set and a continuous feature set according to the number of unique values ​​corresponding to each feature in the screening feature set.

[0063] Among them, the calculation expressions of discrete feature sets and continuous feature sets are:

[0064]

[0065] Where X d is a discrete feature set, X c is a continuous feature set, is the number of unique values ​​of feature i in the filtered feature set, and p is the total number of features in the filtered feature set.

[0066] The multi-view model feature set generation module 16 obtains a multi-view model feature set according to the positive correlation feature set, the negative correlation feature set, the discrete feature set and the continuous feature set in combination with a machine learning model.

[0067] Among them, the calculation expression of the multi-view model feature set is:

[0068]

[0069] X p_d =X p ∩X d ,

[0070] X p_c =X p ∩X c ,

[0071] Xn_d =X n ∩X d ,

[0072] X n_c =X n ∩X c ,

[0073] Where X multi_view is the multi-view model feature set, || is the set concatenation symbol, The machine learning model is based on the input feature set X p_d The generated sample prediction value, The machine learning model is based on the input feature set X p_c The generated sample prediction value, The machine learning model is based on the input feature set X n_d The generated sample prediction value, The machine learning model is based on the input feature set X n_c Generated sample prediction value. In this embodiment, the machine learning model is a LightGBM model, which generates a sample prediction value corresponding to a target for the values ​​of all features corresponding to a target in the input feature set.

[0074] The woe calculation module 17 bins the multi-view model feature set, calculates the bin values ​​of each feature corresponding to each target in the multi-view model feature set, and calculates the woe value of each feature corresponding to each target in the multi-view model feature set based on all the bin values ​​and risk judgment labels corresponding to the multi-view model feature set. Among them, the label result of the target is the various features of the target in the multi-view model feature set and their corresponding woe values.

[0075] 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.

[0076] like Figure 2 As shown, the process of generating the woe value by the woe calculation module 16 includes the following steps:

[0077] Step S7-1: Generate multiple candidate splitting thresholds for the multi-view model feature set, and calculate the splitting value corresponding to each candidate splitting threshold. In this embodiment, the candidate splitting threshold is obtained by the average value of the sorted adjacent samples.

[0078] The calculation expression of the split value is:

[0079]

[0080] H(D mv )=-∑c∈C p(c)log2p(c),

[0081]

[0082] In the formula, IG(D mv , θ) is the splitting value of the candidate splitting threshold θ corresponding to the multi-view model 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 multi-view model 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 multi-view model feature set, and p(c) is the probability of feature c in the multi-view model feature set.

[0083] Step S7-2: taking the candidate splitting threshold corresponding to the maximum splitting value as the optimal splitting point.

[0084] Step S7-3, repeating steps S6-1 to S6-2 until the number of optimal splitting points reaches a preset value. In this embodiment, iterating two layers generates at most four optimal splitting points.

[0085] Step S7-4, calculating the bin boundaries based on all the optimal splitting points.

[0086] The calculation expression of the bin boundary is:

[0087]

[0088] 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.

[0089] Step S7-5: According to the binning boundaries, the bins value and bin0 value of each feature corresponding to each target in the multi-view model feature set are calculated as the binning value.

[0090] Among them, the calculation expressions of bins value and bin0 value are:

[0091]

[0092] In the formula is the value of feature i corresponding to target k in the multi-view model feature set, for The left boundary value of the u-th binning interval.

[0093] Step S7-6, based on all the bin values, calculate the woe value of each feature corresponding to each target in the multi-view model feature set.

[0094] Among them, 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, that is, if The target corresponding feature

[0095] The calculation expression of woe value is:

[0096]

[0097] In the formula is the woe value of feature i corresponding to target k in the multi-view model feature set, N bad 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 multi-view model feature set belongs, N good is the total number of risk judgment labels whose labels are good categories in the group where all values ​​of feature i corresponding to target k in the multi-view model feature set belong, N total is the total number of values ​​of feature i corresponding to target k in the multi-view model 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.

[0098] The control module 18 stores a control program for controlling the operation of each module.

[0099] The following describes the process of using the multi-view label generation device 100 for risk profile construction to perform a multi-view label generation method for risk profile construction in conjunction with the accompanying drawings.

[0100] Figure 3 It is a flowchart of a multi-view label generation method for risk profile construction in an embodiment of the present invention.

[0101] like Figure 3 As shown, the multi-view label generation method for risk profile construction includes the following steps:

[0102] 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.

[0103] 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.

[0104] Step S3, using the screening set generation module 13 to select multiple features from each sub-feature set according to the corresponding importance value, correlation value and feature screening amount to construct a screening feature set.

[0105] Step S4, using the positive and negative correlation feature set generation module 14 to calculate the correlation value of each feature according to the number of features in the screening feature set and the value corresponding to each feature, and construct a positive correlation feature set and a negative correlation feature set according to the correlation value.

[0106] Step S5: using the discrete-continuous feature set generation module 15 to construct a discrete feature set and a continuous feature set according to the number of unique values ​​corresponding to each feature in the screening feature set.

[0107] Step S6, using the multi-view model feature set generation module 16 to obtain a multi-view model feature set based on the positive correlation feature set, the negative correlation feature set, the discrete feature set and the continuous feature set in combination with the machine learning model.

[0108] Step S7, use the Woe calculation module 17 to bin the multi-view model feature set, calculate the bin value of each feature corresponding to each target in the multi-view model feature set, and calculate the Woe value of each feature corresponding to each target in the multi-view model feature set based on all the bin values ​​and risk judgment labels corresponding to the multi-view model feature set.

[0109] In this embodiment, a radar chart of the user portrait of the target can be constructed based on the label results of the target.

[0110] Figure 4 It is a radar schematic diagram of a high-risk user portrait in an embodiment of the present invention.

[0111] Figure 5 It is a radar schematic diagram of a low-risk user portrait in an embodiment of the present invention.

[0112] like Figure 4 and Figure 5 As shown in the figure, the label result includes 4 features, namely multi-view labels and their corresponding values, namely multi_view_1, multi_view_2, multi_view_3 and multi_view_4. It can be seen that the area occupied by abnormal subjects, namely high-risk users, is large, while the area occupied by normal subjects, namely low-risk users, is small, which can intuitively show that the multi-view labels accurately depict the multi-dimensional risk level of the subject risk.

[0113] In this embodiment, the label result generated by the multi-view label generation method for risk profile construction is the model label X multi_view , with general statistics optimization label X anno Conduct a comparative experiment on the scorecard model. The general statistical optimization label X anno For a financial institution, the internal expert rule-driven label is constructed to build a scoring model SCM based on logistic regression using the model label X multi_view and general statistics optimization tag X anno The training data set is used for training, and the trained models are used for binary classification prediction. The specific indicator results are shown in the following table:

[0114] KS AUC <![CDATA[f10]]> <![CDATA[Recall1]]> <![CDATA[f11]]> <![CDATA[SCM+X anno ]]> 0.7454 0.9533 0.9657 0.5707 0.6782 <![CDATA[SCM+X multi_view ]]> 0.7937 0.9616 0.9702 0.6244 0.7268

[0115] The first column in the table above shows the models trained with different training sets, and the second to sixth columns show the KS index, AUC index, f10 index, Recall1 index, and f11 index of the models. For example, the cell in the second row and second column indicates that the general statistical optimization label X anno The KS index of the scoring model SCM trained by the constructed training set is 0.7454. It can be seen that in the model label X multi_view The classification ability of the scoring model SCM is further improved under the data representation of multi_view The anomaly detection effect of the scoring model SCM is enhanced.

[0116] In this embodiment, based on the scoring model SCM, the characteristic coefficients and intercepts 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, and 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.

[0117] Figure 6 Schematic diagram of visualizing a scorecard in an embodiment of the present invention.

[0118] 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. multi_view The scorecard intuitively shows how each module distinguishes between positive and abnormal entities, achieving a strong correlation between abnormal entities and risk scores.

[0119] 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:

[0120]

[0121] The first column in the table above is the different model labels x m_woe1 、x lm_woe2 and x m_woe3 , 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 model label grouping, the proportion of bad samples is more than 85%, showing the accurate expression of bad samples by multi-view labels in specific dimensions.

[0122] Functions and Effects of the Embodiments

[0123] According to the multi-view label generation method and device for risk profile construction involved in this embodiment, by calculating the correlation value and the number of unique values ​​of the features in the screening set, a positive correlation feature set, a negative correlation feature set, a discrete feature set and a continuous feature set are constructed, and then a multi-view model feature set is generated, and then the multi-view model feature set is binned and the woe value is calculated to obtain the label result. In short, this method can generate labels with better risk expression capabilities and improve the comprehensiveness and accuracy of risk profiles.

[0124] 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 have various changes and improvements, and these changes and improvements fall 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 multi-view label generation method for risk profile construction, which is used to generate label results related to risk profiles corresponding to each target according to 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 corresponding importance value, the relevance value and the feature screening amount, selecting a plurality of the features to construct a screening feature set; Step S4, calculating the correlation value of each feature according to the number of features in the screening feature set and the value corresponding to each feature, and constructing a positive correlation feature set and a negative correlation feature set according to the correlation value; Step S5, constructing a discrete feature set and a continuous feature set according to the number of unique values ​​corresponding to each feature in the screening feature set; Step S6, obtaining a multi-view model feature set according to the positive correlation feature set, the negative correlation feature set, the discrete feature set and the continuous feature set in combination with a machine learning model; Step S7, binning the multi-view model feature set, calculating the bin value of each feature corresponding to each target in the multi-view model feature set, and calculating the woe value of each feature corresponding to each target in the multi-view model feature set according to all the bin values ​​corresponding to the multi-view model 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 multi-view model feature set and its corresponding woe value.

2. The multi-view label generation method for risk profile construction according to claim 1, characterized in that: in, The calculation expressions of the positive correlation feature set and the negative correlation feature set are: Where X p is a set of positively correlated features, To filter the correlation value of feature i in the feature set, X n is a set of negatively correlated features.

3. The multi-view label generation method for risk profile construction according to claim 1, characterized in that: in, The calculation expressions of the discrete feature set and the continuous feature set are: Where X d is a discrete feature set, X c is a continuous feature set, is the number of unique values ​​of feature i in the filtered feature set, and p is the total number of features in the filtered feature set.

4. The multi-view label generation method for risk profile construction according to claim 1, characterized in that: in, The calculation expression of the multi-view model feature set is: X p_d =X p ∩X d , X p_c =X p ∩X c , X n_d =X n ∩X d , X n_c =X n ∩X c , Where X multi_view is the multi-view model feature set, || is the set concatenation symbol, The machine learning model is based on the input feature set X p_d The generated sample prediction value, The machine learning model is based on the input feature set X p_c The generated sample prediction value, The machine learning model is based on the input feature set X n_d The generated sample prediction value, The machine learning model is based on the input feature set X n_c The generated sample predictions.

5. The multi-view label generation method for risk profile construction according to claim 1, characterized in that: in, 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.

6. The multi-view 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 sub-feature set j, p is the total number of features in 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 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, In step S2, the calculation expression of the characteristic screening amount is: Where select_len j is the feature screening amount corresponding to sub-feature set j, p is the total number of features in sub-feature set j, This is a round-down operation.

7. The multi-view 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 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, X selected is the filter feature set, m is the total number of sub-feature sets, 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.

8. The multi-view label generation method for risk profile construction according to claim 1, Features: Wherein, the step S7 includes the following sub-steps: Step S7-1, generating a plurality of candidate splitting thresholds for the multi-view model feature set, and calculating a 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 S6-1 to S6-2 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, calculating, according to the binning boundaries, the bins value and bin0 value of each of the features corresponding to each of the targets in the multi-view model feature set as the binning value; Step S7-6: Calculate the woe value of each feature corresponding to each target in the multi-view model feature set according to all the binning values.

9. The multi-view label generation method for risk profile construction according to claim 8, characterized in that: in, The calculation expression of the split value is: H(D mv )=-∑ c∈C p(c)log2p(c), In the formula, IG(D mv , θ) is the splitting value of the candidate splitting threshold θ corresponding to the multi-view model feature set, |D| is the number of samples in D, is the value of feature i corresponding to target k in the multi-view model 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 multi-view model feature set, p(c) is the probability of feature c in the multi-view model 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 is the value of feature i corresponding to target k in the multi-view model feature set, for The left boundary value of the u-th bin interval, 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 multi-view model feature set, N bad 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 multi-view model feature set belongs, N good is the total number of risk judgment labels whose labels are good categories in the group where all values ​​of feature i corresponding to target k in the multi-view model feature set belong, N total is the total number of values ​​of feature i corresponding to target k in the multi-view model feature set.

10. A multi-view 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, for each of the sub-feature sets, calculates the importance value and the relevance value of each of the features and the feature screening amount according to the number of the features in the sub-feature set and the values ​​corresponding to the features; A screening set generation module, which selects a plurality of features from each of the sub-feature sets according to the corresponding importance value, the relevance value and the feature screening amount to construct a screening feature set; A positive and negative correlation feature set generation module, which calculates the correlation value of each feature according to the number of features in the screening feature set and the value corresponding to each feature, and constructs a positive correlation feature set and a negative correlation feature set according to the correlation value; A discrete-continuous feature set generation module, which constructs a discrete feature set and a continuous feature set according to the number of unique values ​​corresponding to each of the features in the screening feature set; A multi-view model feature set generation module, which obtains a multi-view model feature set according to the positive correlation feature set, the negative correlation feature set, the discrete feature set and the continuous feature set in combination with a machine learning model; a woe calculation module, which bins the multi-view model feature set, calculates the bin values ​​of each feature corresponding to each target in the multi-view model feature set, and calculates the woe value of each feature corresponding to each target in the multi-view model feature set according to all the bin values ​​and the risk judgment label corresponding to the multi-view model feature set, Among them, the label result of the target is each of the features of the target in the multi-view model feature set and its corresponding woe value.

Images