Risk control model building method and device for marketing scene
Through the combination of the unsupervised algorithm model and the DeepFM algorithm, the problem of high cost of identifying new risk behaviors and sample labeling of existing risk control models is solved, and the automatic discovery and update of new risk behaviors is realized, and the identification of models is improved. Accuracy and expression ability solve the accuracy and accuracy problems of traditional risk control models.
Patent Information
- Application Number
- CN202411495060.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-24
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2044-10-24
Smart Images

Figure CN119026060A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of information security and risk control technology, and in particular to a method and device for building a risk control model for marketing scenarios. Background Art
[0002] In the current marketing environment, risks such as fraud and false transactions are becoming increasingly serious, severely impacting businesses' economic benefits and user experience. Traditional risk control models often rely on supervised learning methods, which require large amounts of labeled data for training.
[0003] In existing technical solutions, the key implementation steps for building risk control models primarily include sample construction, feature engineering, and algorithm model training and tuning. The current mainstream solution primarily trains classification and recognition models on previously identified abnormal samples to uncover underlying behavioral patterns, then applies these models to new traffic to identify abnormal users with similar behaviors. In this approach, sample construction is primarily based on the accumulation of risky behaviors intercepted by the rule engine and expert-labeled data. Feature engineering involves operations such as feature calculation, data cleaning, standardization, and feature selection. These are then fed into supervised classification algorithms such as logistic regression and random forests for model training and tuning.
[0004] The advantage of this solution is that it can use supervised classification algorithms to identify segment header problems and accuracy problems in the rule engine. However, this solution also has the disadvantages of being unable to automatically discover new risk behaviors and the high cost of sample compliance. Summary of the Invention
[0005] The present invention aims to provide a method, device, equipment and storage medium for building a risk control model for marketing scenarios to address the deficiencies in the prior art. The technical problems to be solved by the present invention are achieved through the following technical solutions.
[0006] In a first aspect, a method for building a risk control model for a marketing scenario is provided, the method comprising: Step 1: Build an unsupervised algorithm model: constructing a list of characteristics based on perceptions of risky behavior; According to the relative entropy algorithm, risky behaviors are identified by identifying distribution differences; According to the isolation forest algorithm, risky behaviors are identified by identifying outliers; Step 2: updating the risk sample library based on the recognition results of the unsupervised algorithm model; Step 3: Build a supervised algorithm model: Behaviors existing in the risk sample library are considered positive samples, and behaviors with business conversion effects are considered negative samples; Constructing a classification and recognition model according to the DeepFM algorithm as a supervised algorithm model; splitting the positive samples and negative samples into a training set and a validation set, and evaluating and iteratively tuning the classification and recognition model; The traffic to be evaluated is input into a supervised classification recognition model, a risk score is output, and whether to execute the risk control strategy is determined based on the risk score.
[0007] In some implementations, identifying risky behaviors by identifying distribution differences based on the relative entropy algorithm specifically includes: Compile statistics on the baseline distribution of each dimension and feature; and compile statistics on the distribution of the dimension corresponding to the traffic to be evaluated across all features; Perform relative entropy analysis on the baseline distribution of each dimension and each feature and the distribution corresponding to the traffic to be evaluated to obtain an anomaly score of the traffic to be evaluated in each feature; The anomaly scores of all features under the same dimension in the traffic to be evaluated are accumulated as an anomaly score; the anomaly scores of all features under all dimensions in the traffic to be evaluated are accumulated as a total anomaly score; According to the total anomaly score and the distribution interval of its characteristic values, it is determined whether the traffic to be evaluated triggers a risk strategy.
[0008] In some implementations, identifying risky behaviors by identifying outliers based on the isolation forest algorithm specifically includes: Based on the understanding of historical risk behaviors, a feature list is constructed to capture risk behaviors; According to the features, the categorical features are preprocessed and converted into numerical features by performing LabelEncoder as sample data; Based on the sample data, multiple isolated trees are constructed by random subsampling to form an isolation forest model; According to the sample data corresponding to the traffic to be evaluated, the anomaly score is analyzed by calling the isolation forest model, and the risk control strategy is executed when the anomaly score is higher than the set threshold.
[0009] In some implementations, the anomaly score s(x, n) is calculated as shown in formula (1): ; Wherein, E(h(x)) is the average path length of the sample point x in all trees, n is the sample size of the training data, c(n) is the average path length of the tree, and the anomaly interval is [0,1].
[0010] In some implementations, the classification and recognition model specifically includes a neural network part and a factor decomposition machine part; the neural network part and the factor decomposition machine part respectively extract low-order features and high-order features.
[0011] In a second aspect, an embodiment of the present invention provides a device for building a risk control model for a marketing scenario, the device comprising: Unsupervised algorithm model building modules, including: The first building block is used to construct a list of characteristics based on the perception of risky behavior; Anomaly identification unit, used to identify risky behaviors by identifying distribution differences based on the relative entropy algorithm; The risk judgment unit is used to identify risky behaviors by identifying outliers based on the isolation forest algorithm; An updating module, configured to update the risk sample library according to the recognition results of the unsupervised algorithm model; Supervised algorithm model building modules, including: A behavior conversion unit that uses behaviors existing in the risk sample library as positive samples and behaviors with business conversion effects as negative samples; A sample splitting unit is used to construct a classification and recognition model based on the DeepFM algorithm as a supervised algorithm model; split the positive samples and negative samples into a training set and a validation set, and evaluate and iteratively tune the classification and recognition model; The risk assessment unit is used to input the traffic to be assessed into the supervised classification recognition model, output a risk score, and determine whether to execute the risk control strategy based on the risk score.
[0012] In some implementations, the anomaly identification unit specifically includes: The statistical subunit is used to collect statistics on the baseline distribution of each dimension and feature; it collects statistics on the distribution of the dimension corresponding to the traffic to be evaluated across all features; A scoring subunit is used to perform relative entropy analysis on the baseline distribution of each dimension and each feature and the distribution corresponding to the flow to be evaluated, to obtain an anomaly score of the flow to be evaluated for each feature; an accumulation subunit, configured to accumulate the anomaly scores of all features under the same dimension in the traffic to be evaluated as an anomaly score; and accumulate the anomaly scores of all features under all dimensions in the traffic to be evaluated as a total anomaly score; The evaluation subunit is used to determine whether the traffic to be evaluated triggers a risk strategy based on the total anomaly score and the distribution interval of its characteristic values.
[0013] In some implementations, the risk determination unit specifically includes: The capture subunit is used to construct a feature list to capture risky behaviors based on the understanding of historical risky behaviors; An execution subunit, configured to convert the categorical features into numerical features by preprocessing and performing LabelEncoder on the features according to the features, to serve as sample data; Using subunits to construct multiple isolated trees through random subsampling based on the sample data to form an isolation forest model; The calling subunit is used to perform anomaly score analysis by calling the isolation forest model according to the sample data corresponding to the flow to be evaluated, and execute the risk control strategy when the anomaly score is higher than the set threshold.
[0014] In a third aspect, an embodiment of the present invention provides an electronic device comprising a memory and a processor, wherein the memory is used to store one or more computer instructions, wherein when the one or more computer instructions are executed by the processor, the method described in the first aspect above is implemented.
[0015] In a fourth aspect, an embodiment of the present invention provides a computer storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it is used to implement the method described in the first aspect.
[0016] The embodiments of the present invention include the following advantages: The present invention consists of three parts: unsupervised algorithm model construction, unsupervised algorithm model recognition result validity judgment, and supervised algorithm model construction. By using an unsupervised algorithm to build a risk control recognition model that does not rely on sample labels, the relative entropy algorithm is used to identify large-scale and traffic-concentrated abnormal behaviors that differ significantly from normal behavior distribution, and the isolation forest algorithm is used to identify a small number of abnormal behaviors that differ significantly from normal data, thus building the ability to proactively discover new risks. The sample library is improved using the output of the unsupervised algorithm model. The sample accuracy judgment module is constructed by combining the output of the unsupervised recognition model and business performance data. Users with high risk rates and poor business performance conversion are screened and updated to the risk sample library. A supervised recognition model is built based on the DeepFM algorithm. By automatically learning the interactions between features, the need for manual feature engineering is reduced, and complex nonlinear relationships can be modeled, thus having stronger model expression capabilities. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] Figure 1 This is a flow chart of a method for building a risk control model for a marketing scenario provided by an embodiment of the present invention; Figure 2 This is a flowchart of constructing an unsupervised recognition model provided by an embodiment of the present invention; Figure 3 This is a flowchart of constructing an independent forest algorithm model provided by an embodiment of the present invention; Figure 4 This is a flow chart of updating a sample library based on the unsupervised algorithm model recognition results provided by the present invention; Figure 5 This is a flowchart of the construction of a supervised algorithm model provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0018] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in this application can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.
[0019] Example 1: Figure 1 A flow chart showing a method for building a risk control model for a marketing scenario is shown in FIG. Figure 1 As shown, the risk control model building method for marketing scenarios provided in this embodiment includes: First, follow step 1 to build an unsupervised algorithm model: S11, constructing a list of characteristics based on the perception of risky behavior; S12, identifying risky behaviors by identifying distribution differences according to the relative entropy algorithm; S13, identifying risky behaviors by identifying outliers according to the isolation forest algorithm; Most existing risk control models are based on supervised classification algorithms to identify known risk behaviors. This solution can only identify known risks by exploring the behavioral patterns behind risk samples, and has a delay in identifying new risk behaviors. Only when business data shows abnormal fluctuations can it be converted into known anomalies through expert analysis and identified.
[0020] This step requires the use of unsupervised algorithms to build a risk control identification model that does not rely on sample labels, the use of relative entropy algorithms to identify large-scale and traffic-concentrated abnormal behaviors that are significantly different from normal behavior distribution, and the use of isolation forests to identify "few but different" abnormal behaviors, that is, those that are small in number and significantly different from normal data, to build the ability to proactively discover new risks.
[0021] Specifically include: According to S12, risky behaviors can only obtain the desired benefits when they accumulate to a certain level. However, attackers do not know the true distribution of normal user behaviors, so abnormalities will naturally appear in some dimensions. Unsupervised relative entropy models can be used to identify risky behaviors. This model mainly includes three parts: baseline distribution calculation, feature construction, and anomaly score calculation. Figure 2 As shown, specifically including: S121, performing statistics on the baseline distribution of each dimension and feature; performing statistics on the distribution of the dimension corresponding to the flow to be evaluated in all features; For each ordering behavior, the data distribution in multiple dimensions and features is counted, including: Dimensions: Comprehensive scoring of multiple dimensions to improve the confidence of recognition results, such as C-end user identification, traffic source, product identification, etc. Features: Rich features can cover more possible attack methods and improve the recognition recall rate. S122, performing relative entropy analysis on the baseline distribution of each dimension and each feature and the distribution corresponding to the traffic to be evaluated, to obtain an anomaly score of the traffic to be evaluated for each feature; First, the anomaly scores of n features are calculated, then the anomaly scores of m dimensions are calculated, and finally the sum of the anomaly scores of all dimensions is accumulated as the anomaly score of the user.
[0022] ; ; ; Among them, p(x i ) is the normal traffic probability distribution (k-dimensional vector), q(x i ) is the probability distribution of the traffic to be evaluated.
[0023] S123, accumulating the anomaly scores of all features under the same dimension in the traffic to be evaluated as an anomaly score; accumulating the anomaly scores of all features under all dimensions in the traffic to be evaluated as a total anomaly score; S124: Determine whether the traffic to be evaluated triggers a risk strategy based on the total anomaly score and the distribution interval of its characteristic values.
[0024] All behaviors are sorted in descending order by anomaly score, and behaviors with anomaly scores above a certain threshold and corresponding feature values in the distribution anomaly interval are screened out. The corresponding risk control strategy is executed based on the risk control level.
[0025] According to S13, the risk identification model based on relative entropy determines the risk of a behavior by identifying the difference in distribution. This requires that such behavior accumulates to a certain level before it can be judged. It has a better identification effect on large-scale and highly concentrated risk behaviors. In order to improve the recall ability of small and scattered risk behaviors, the isolation forest algorithm is used to build the identification model. This algorithm belongs to unsupervised learning and is particularly suitable for detecting outliers in the data. These outliers may represent potential risks or abnormal behaviors, such as Figure 3 As shown, specifically including: S131, based on the knowledge of historical risk behaviors, construct a feature list to capture risk behaviors; S132, according to the features, preprocessing and performing LabelEncoder on the categorical features to convert them into numerical features as sample data; Fill missing values in the feature list with reasonable values such as default values, average values, etc.; perform LabelEncoder on categorical features to convert them into numerical features.
[0026] Feature screening: Since the isolation forest algorithm is based on data distribution, it finds data that is different from the majority of data distribution (low-frequency values) and regards them as outliers. Therefore, features with smaller distribution differences contribute less to the model effect and can be deleted.
[0027] S133, constructing multiple isolated trees by random subsampling based on the sample data to form an isolation forest model; M (M is much smaller than the size of the entire sample set) samples are randomly selected from the entire sample set with replacement to form a training subset. Based on this subset, an isolation binary tree is constructed by randomly selecting features and split points. This process is repeated until N (N is generally greater than 100) trees are established to form an isolation forest.
[0028] S134 , performing anomaly score analysis based on the sample data corresponding to the traffic to be evaluated by calling the isolation forest model, and executing a risk control strategy when the anomaly score is higher than a set threshold.
[0029] Abnormal score calculation: For each sample x, the abnormal score s(x, n) is calculated as follows: ; Where E(h(x)) is the average path length of the sample point x in all trees, n is the sample size of the training data, c(n) is the average path length of the tree, and the anomaly interval is [0,1].
[0030] Determination of abnormal threshold: Based on the existing risk behavior sample library, business effect conversion data and behavioral data, expert evaluation is conducted on abnormal samples screened by different abnormal score thresholds, and the abnormal score threshold is determined based on the sample recognition accuracy of the different threshold evaluations.
[0031] Step 2: Figure 4 As shown, the risk sample library is updated according to the recognition results of the unsupervised algorithm model; Currently, risk samples are mostly accumulated by intercepting results from rule engines and manually labeling by experts, resulting in high labeling costs and an inability to cover all risk scenarios.
[0032] In this step, the unsupervised recognition model does not rely on sample labels and has the ability to automatically discover risks. Therefore, it is possible to consider using the output results of this type of model to improve the sample library, and combine the output results of the unsupervised recognition model and business effect data to build a sample accuracy judgment module, and screen out users with high risk rates and poor business effect conversion and update them to the risk sample library.
[0033] To reduce the cost of labeling risk samples and improve the timeliness of updating new abnormal risk behaviors, the sample library must be automatically updated with the identification results of the unsupervised algorithm model. To ensure sample accuracy, further filtering is required based on business conversion data and risk characteristics, excluding behaviors that have conversion effects but no obvious risk characteristics.
[0034] Step 3: Figure 5 As shown, a supervised algorithm model is constructed: S31, taking behaviors existing in the risk sample library as positive samples, and taking behaviors with business conversion effects as negative samples; Positive and negative samples are constructed based on the risk sample library and business conversion data. When the ratio of positive and negative samples is too large, negative sampling is required to keep the ratio of positive and negative samples within 1:10.
[0035] S32, constructing a classification and recognition model according to the DeepFM algorithm as a supervised algorithm model; splitting the positive samples and negative samples into a training set and a validation set, and evaluating and iteratively tuning the classification and recognition model; Based on the understanding of historical risk behaviors, a feature list is constructed and preprocessed, such as missing value processing and standardization, before the features are encapsulated. For example, continuous features can be directly concatenated into dense data. Single-valued discrete features are converted into vectors through the Embedding layer. Multi-valued discrete features are also processed through Embedding, and the average of all Embedding vectors is taken.
[0036] To improve the model's recognition capabilities, the DeepFM algorithm was used to construct a classification and recognition model. This model consists of a neural network and a factorization machine, responsible for extracting low-order and high-order features, respectively, effectively mining the patterns hidden in the data. During the model training phase, the cross-entropy loss function was used to update the model's parameters. The model's performance was evaluated based on metrics such as AUC and F1-score on the training and validation sets, and the model's performance was optimized by adjusting the learning rate, regularization, dropout, and other methods. S33: Input the traffic to be evaluated into a supervised classification recognition model, output a risk score, and determine whether to execute the risk control strategy based on the risk score.
[0037] For the newly estimated traffic, a feature list is obtained by splicing, and the trained DeepFM model is called to calculate the risk score. The corresponding risk control strategy is executed based on the risk score level.
[0038] Common machine learning classification algorithms have problems such as weak generalization ability and high dependence on feature engineering, resulting in high cost of model optimization.
[0039] In this step, a supervised recognition model is built based on the DeepFM algorithm. By automatically learning the interactions between features, the need for manual feature engineering is reduced, and complex nonlinear relationships can be modeled, thus having stronger model expression capabilities.
[0040] Example 2: An embodiment of the present invention provides a device for building a risk control model for a marketing scenario, the device comprising: Unsupervised algorithm model building modules, including: The first building block is used to construct a list of characteristics based on the perception of risky behavior; Anomaly identification unit, used to identify risky behaviors by identifying distribution differences based on the relative entropy algorithm; The risk judgment unit is used to identify risky behaviors by identifying outliers based on the isolation forest algorithm; An updating module, configured to update the risk sample library according to the recognition results of the unsupervised algorithm model; Supervised algorithm model building modules, including: A behavior conversion unit that uses behaviors existing in the risk sample library as positive samples and behaviors with business conversion effects as negative samples; A sample splitting unit is used to construct a classification and recognition model based on the DeepFM algorithm as a supervised algorithm model; split the positive samples and negative samples into a training set and a validation set, and evaluate and iteratively tune the classification and recognition model; The risk assessment unit is used to input the traffic to be assessed into the supervised classification recognition model, output a risk score, and determine whether to execute the risk control strategy based on the risk score.
[0041] Furthermore, the abnormality identification unit specifically includes: The statistical subunit is used to collect statistics on the baseline distribution of each dimension and feature; it collects statistics on the distribution of the dimension corresponding to the traffic to be evaluated across all features; A scoring subunit is used to perform relative entropy analysis on the baseline distribution of each dimension and each feature and the distribution corresponding to the flow to be evaluated, to obtain an anomaly score of the flow to be evaluated for each feature; an accumulation subunit, configured to accumulate the anomaly scores of all features under the same dimension in the traffic to be evaluated as an anomaly score; and accumulate the anomaly scores of all features under all dimensions in the traffic to be evaluated as a total anomaly score; The evaluation subunit is used to determine whether the traffic to be evaluated triggers a risk strategy based on the total anomaly score and the distribution interval of its characteristic values.
[0042] Furthermore, the risk judgment unit specifically includes: The capture subunit is used to construct a feature list to capture risky behaviors based on the understanding of historical risky behaviors; An execution subunit, configured to convert the categorical features into numerical features by preprocessing and performing LabelEncoder on the features according to the features, to serve as sample data; Using subunits to construct multiple isolated trees through random subsampling based on the sample data to form an isolation forest model; The calling subunit is used to perform anomaly score analysis by calling the isolation forest model according to the sample data corresponding to the flow to be evaluated, and execute the risk control strategy when the anomaly score is higher than the set threshold.
[0043] Example 3: This embodiment further provides an electronic device, including a memory and a processor, wherein the memory is used to store one or more computer instructions, wherein the one or more computer instructions, when executed by the processor, implement the method of embodiment 1; In practical applications, the processor can be an application specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a controller, a microcontroller unit (MCU), a microprocessor or other electronic components to execute the methods in the above embodiments.
[0044] The method implemented in this embodiment is as shown in Example 1.
[0045] Example 4: This embodiment further provides a computer storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by one or more processors, the method of embodiment 1 is implemented; Among them, the computer-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.
[0046] The method implemented in this embodiment is as shown in Example 1.
[0047] It should be noted that the above detailed description is exemplary and is intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the art to which the present application belongs.
[0048] It should be noted that the terms used herein are intended only to describe specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components and / or combinations thereof.
[0049] It should be noted that the terms "first," "second," and the like in the specification and claims of this application and the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, such that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.
[0050] In addition, the terms "comprises" and "comprising" and any variations thereof are intended to cover a non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, product, or apparatus.
[0051] For ease of description, spatially relative terms such as "above", "above", "on the upper surface of", "above", etc. may be used herein to describe the spatial positional relationship of a device or feature to other devices or features as shown in the figures. It should be understood that spatially relative terms are intended to include different orientations of the device in use or operation in addition to the orientation described in the figures. For example, if the device in the drawings is inverted, the device described as "above other devices or structures" or "above other devices or structures" will be subsequently positioned as "below other devices or structures" or "below other devices or structures". Thus, the exemplary term "above" can include both "above" and "below". The device can also be positioned in other different ways, such as rotated 90 degrees or in other orientations, and the spatially relative descriptions used herein are interpreted accordingly.
[0052] In the above detailed description, reference is made to the accompanying drawings, which form a part hereof. In the drawings, similar symbols typically identify similar components, unless the context dictates otherwise. The illustrated embodiments described in the detailed description, drawings, and claims are not meant to be limiting. Other embodiments may be used, and other changes may be made, without departing from the spirit or scope of the subject matter presented herein.
[0053] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.
Claims
1. A method for building a risk control model for marketing scenarios, characterized in that: The method comprises: Step 1: Build an unsupervised algorithm model: constructing a list of characteristics based on perceptions of risky behavior; Construct an unsupervised algorithm model based on the relative entropy algorithm and the isolation forest algorithm; According to the relative entropy algorithm, risk behaviors are identified by identifying distribution differences; According to the isolation forest algorithm, risky behaviors are identified by identifying outliers; Step 2: updating the risk sample library according to the recognition result of the unsupervised algorithm model; Step 3: Build a supervised algorithm model: The behaviors existing in the risk sample library are taken as positive samples, and the behaviors with business conversion effects are taken as negative samples; Constructing a classification and recognition model according to the DeepFM algorithm as a supervised algorithm model; splitting the positive samples and negative samples into a training set and a validation set, and evaluating and iteratively tuning the classification and recognition model; The traffic to be evaluated is input into a supervised classification recognition model, a risk score is output, and whether to execute a risk control strategy is determined based on the risk score.
2. The method according to claim 1, characterized in that: The step of identifying risk behaviors by identifying distribution differences according to the relative entropy algorithm specifically includes: Collect statistics on the baseline distribution of each dimension and feature; collect statistics on the distribution of the dimension corresponding to the flow to be evaluated in all features; Performing relative entropy analysis on the benchmark distribution of each dimension and each feature and the distribution corresponding to the flow to be evaluated, to obtain an abnormal score of the flow to be evaluated in each feature; The anomaly scores of all features under the same dimension in the traffic to be evaluated are accumulated as an anomaly score; the anomaly scores of all features under all dimensions in the traffic to be evaluated are accumulated as a total anomaly score; According to the total anomaly score and the distribution interval of its characteristic values, it is determined whether the traffic to be evaluated triggers a risk strategy.
3. The method according to claim 1, characterized in that The step of identifying risky behaviors by identifying outliers according to the isolation forest algorithm specifically includes: Based on the recognition of historical risk behaviors, a feature list is constructed to capture risk behaviors; According to the features, the categorical features are preprocessed and converted into numerical features by performing LabelEncoder as sample data; According to the sample data, multiple isolated trees are constructed by random subsampling to form an isolation forest model; According to the sample data corresponding to the flow to be evaluated, the anomaly score is analyzed by calling the isolation forest model, and the risk control strategy is executed when the anomaly score is higher than the set threshold.
4. The method according to claim 3, characterized in that The calculation of the anomaly score s(x, n) is shown in formula (1): ; Wherein, E(h(x)) is the average path length of the sample point x in all trees, n is the sample size of the training data, c(n) is the average path length of the tree, and the anomaly partition interval is [0,1].
5. The method according to claim 1, characterized in that The classification and recognition model specifically includes a neural network part and a factor decomposition machine part; the neural network part and the factor decomposition machine part respectively extract low-order features and high-order features.
6. A risk control model building device for marketing scenarios, characterized in that: The device comprises: Unsupervised algorithm model building modules, including: The first building block is used to construct a list of characteristics based on the perception of risky behavior; Anomaly identification unit, used to identify risky behaviors by identifying distribution differences based on a relative entropy algorithm; A risk judgment unit is used to identify risky behaviors by identifying outliers based on the isolation forest algorithm; An updating module, used to update the risk sample library according to the recognition result of the unsupervised algorithm model; Supervised algorithm model building modules, including: A behavior conversion unit, which uses behaviors existing in the risk sample library as positive samples and behaviors with business conversion effects as negative samples; A sample splitting unit is used to construct a classification recognition model according to the DeepFM algorithm as a supervised algorithm model; split the positive samples and negative samples into a training set and a validation set, and evaluate and iteratively tune the classification recognition model; The risk assessment unit is used to input the traffic to be assessed into a supervised classification recognition model, output a risk score, and determine whether to execute a risk control strategy based on the risk score.
7. The device according to claim 6, characterized in that The abnormality identification unit specifically includes: The statistical subunit is used to count the baseline distribution of each dimension and feature; and to count the distribution of the dimension corresponding to the flow to be evaluated in all features; A scoring subunit, used to perform relative entropy analysis on the reference distribution of each dimension and each feature and the distribution corresponding to the flow to be evaluated, to obtain an abnormal score of the flow to be evaluated in each feature; An accumulation subunit, configured to accumulate the anomaly scores of all features under the same dimension in the traffic to be evaluated as an anomaly score; and accumulate the anomaly scores of all features under all dimensions in the traffic to be evaluated as a total anomaly score; The evaluation subunit is used to determine whether the flow to be evaluated triggers a risk strategy according to the total anomaly score and the distribution interval of its characteristic values.
8. The device according to claim 6, characterized in that The risk judgment unit specifically includes: The capture subunit is used to construct a feature list to capture risk behaviors based on the recognition of historical risk behaviors; An execution subunit, used for converting the categorical features into numerical features by preprocessing and executing LabelEncoder on the categorical features according to the features as sample data; Using sub-units to construct multiple isolated trees through random sub-sampling according to the sample data to form an isolation forest model; The calling subunit is used to perform anomaly score analysis by calling the isolation forest model according to the sample data corresponding to the flow to be evaluated, and execute the risk control strategy when the anomaly score is higher than the set threshold.
9. An electronic device, characterized in that: It includes a memory and a processor, wherein the memory is used to store one or more computer instructions, wherein the one or more computer instructions, when executed by the processor, implement the risk control model building method for marketing scenarios as described in any one of claims 1 to 5 above.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, it is used to implement the risk control model building method for marketing scenarios as described in any one of claims 1 to 5 above.
Citation Information
Patent Citations
Construction method and system of generative marketing event risk control rule base
CN117151768A
Enterprise financial risk identification method, device and equipment and storage medium
CN117876115A
Fusion analysis method for financial big data
CN118552303A
Authentication analysis system and method based on big data
CN118608167A
Systems and methods for network risk management, cyber risk management, security ratings, and evaluation systems and methods of the same
US20220400135A1
Cited By
Enterprise risk control dynamic portrait generation method and device based on multi-modal data fusion
CN120634261A
