CN116883065A - Merchant risk prediction method and device - Google Patents
Merchant risk prediction method and device Download PDFInfo
- Publication number
- CN116883065A CN116883065A CN202310891543.6A CN202310891543A CN116883065A CN 116883065 A CN116883065 A CN 116883065A CN 202310891543 A CN202310891543 A CN 202310891543A CN 116883065 A CN116883065 A CN 116883065A
- Authority
- CN
- China
- Prior art keywords
- merchant
- data
- risk prediction
- feature
- merchant data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000012549 training Methods 0.000 claims abstract description 30
- 238000013058 risk prediction model Methods 0.000 claims abstract description 18
- 238000012216 screening Methods 0.000 claims abstract description 15
- 238000010801 machine learning Methods 0.000 claims abstract description 12
- 238000007781 pre-processing Methods 0.000 claims abstract description 12
- 239000002245 particle Substances 0.000 claims description 58
- 238000004590 computer program Methods 0.000 claims description 27
- 238000012545 processing Methods 0.000 claims description 20
- 238000004422 calculation algorithm Methods 0.000 claims description 12
- 238000003860 storage Methods 0.000 claims description 10
- 238000004140 cleaning Methods 0.000 claims description 9
- 238000010606 normalization Methods 0.000 claims description 4
- 238000007637 random forest analysis Methods 0.000 claims description 3
- 230000002159 abnormal effect Effects 0.000 claims description 2
- 230000009467 reduction Effects 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 8
- 238000004458 analytical method Methods 0.000 description 6
- 238000007726 management method Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 241000965478 Darksidea epsilon Species 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013501 data transformation Methods 0.000 description 1
- 238000011423 initialization method Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000013077 scoring method Methods 0.000 description 1
- 229910052709 silver Inorganic materials 0.000 description 1
- 239000004332 silver Substances 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000007306 turnover Effects 0.000 description 1
- 238000009827 uniform distribution Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/02—Banking, e.g. interest calculation or account maintenance
Abstract
The invention discloses a method and a device for predicting merchant risk, which can be used in the financial field, and the method comprises the following steps: acquiring merchant data; the merchant data includes: business information, financial information and merchant risk information fed back by historical users of merchants; preprocessing merchant data; screening the preprocessed merchant data to obtain a feature subset; determining a training set according to the feature subset; training the machine learning model by using the training set to obtain a merchant risk prediction model; and inputting the data sets except the feature subsets in the merchant data of the to-be-detected merchant into the merchant risk prediction model to obtain a merchant risk prediction result corresponding to the to-be-detected merchant. According to the invention, the optimal feature subset is selected from a large number of features, so that accuracy of model to merchant risk prediction is improved, complexity of the model is reduced due to feature reduction, and risk management cost of a bank is reduced.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a method and a device for predicting merchant risks.
Background
This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. The description herein is not admitted to be prior art by inclusion in this section.
Banks or other financial institutions conduct merchant risk prediction according to historical performance, management, financial conditions, market competitiveness and other aspects of merchants, and key features are screened through business specialists and domain specialists of banks in the prior art. They choose the most representative features from a plurality of points of view, based on their own business knowledge and experience, on the credit risk, transaction risk, quality of service, etc. of the merchant. However, different experts may give different answers to the same question, thereby affecting the effect of feature selection. It often takes a long time to collect expert opinions and advice, which may not be well suited for emergency tasks. In processing large-scale data, both the efficiency and feasibility of manual evaluation may be limited.
In summary, there is a need for a method for predicting risk of merchants to solve the above problems.
Disclosure of Invention
The embodiment of the invention provides a method for predicting merchant risk, which is used for improving the accuracy and efficiency of merchant risk prediction, and comprises the following steps:
acquiring merchant data; the merchant data includes: business information, financial information and merchant risk information fed back by historical users of merchants;
preprocessing merchant data;
screening the preprocessed merchant data to obtain a feature subset;
determining a training set according to the feature subset;
training the machine learning model by using the training set to obtain a merchant risk prediction model;
and inputting the data sets except the feature subsets in the merchant data of the to-be-detected merchant into the merchant risk prediction model to obtain a merchant risk prediction result corresponding to the to-be-detected merchant.
The embodiment of the invention also provides a device for predicting the risk of the commercial tenant, which is used for improving the accuracy and the efficiency of the risk prediction of the commercial tenant, and comprises the following steps:
the feature subset determining module is used for acquiring merchant data; the merchant data includes: business information, financial information and merchant risk information fed back by historical users of merchants; preprocessing merchant data; screening the preprocessed merchant data to obtain a feature subset;
the training module is used for determining a training set according to the feature subset; training the machine learning model by using the training set to obtain a merchant risk prediction model;
and the prediction module is used for inputting the data sets except the feature subsets in the merchant data of the to-be-detected merchant into the merchant risk prediction model to obtain a merchant risk prediction result corresponding to the to-be-detected merchant.
The embodiment of the invention also provides computer equipment, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the merchant risk prediction method when executing the computer program.
The embodiment of the invention also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program realizes the merchant risk prediction method when being executed by a processor.
The embodiment of the invention also provides a computer program product, which comprises a computer program, wherein the computer program realizes the merchant risk prediction method when being executed by a processor.
In the embodiment of the invention, merchant data is obtained; the merchant data includes: business information, financial information and merchant risk information fed back by historical users of merchants; preprocessing merchant data; screening the preprocessed merchant data to obtain a feature subset; determining a training set according to the feature subset; training the machine learning model by using the training set to obtain a merchant risk prediction model; and inputting the data sets except the feature subsets in the merchant data of the to-be-detected merchant into the merchant risk prediction model to obtain a merchant risk prediction result corresponding to the to-be-detected merchant. Compared with the prior art, the method has the advantages that the optimal feature subset is selected from a large number of features, the problems that the workload is large, the manual experience is relied on, the feature association is ignored, local optimality is easily involved in a traditional manual experience or mathematical analysis method are avoided, accuracy of model to merchant risk prediction is improved, complexity of the model is reduced due to feature reduction, and risk management cost of banks is reduced.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. In the drawings:
FIG. 1 is a schematic flow chart of a method for predicting risk of a merchant according to the present invention;
FIG. 2 is a schematic flow chart of a method for predicting risk of a merchant according to the present invention;
FIG. 3 is a schematic flow chart of a method for predicting risk of a merchant according to the present invention;
FIG. 4 is a schematic flow chart of a method for predicting risk of a merchant according to the present invention;
fig. 5 is a schematic structural diagram of a merchant risk prediction device provided by the invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention will be described in further detail with reference to the accompanying drawings. The exemplary embodiments of the present invention and their descriptions herein are for the purpose of explaining the present invention, but are not to be construed as limiting the invention.
Fig. 1 is a schematic flow diagram corresponding to a processing method for separating acceleration signals of a high-speed railway vehicle according to an embodiment of the present invention, where, as shown in fig. 1, the method includes:
step 101, acquiring merchant data.
It should be noted that, the merchant data includes: business information of merchants, financial information and merchant risk information fed back by historical users.
In the embodiment of the invention, the following data are acquired through a big data platform and are used as the data basis for analysis:
basic information of merchants: basic corporate information such as name, address, contact, etc., and establishes a corresponding merchant profile in the system.
Financial information: the merchant provides financial statements, such as balance sheets, damage sheets, etc., for analysis of the merchant's financial status.
Business information of merchants: silver such as sales, gross interest rate, inventory turnover rate, etc., and the business condition of the merchant is analyzed.
Historical user fed back merchant risk information: and the evaluation and feedback information of the user to the merchant, such as complaint records, refund rate and the like, are considered.
Step 102, preprocessing the merchant data.
And step 103, screening the preprocessed merchant data to obtain the feature subset.
In one possible implementation, the preprocessed merchant data is divided into two parts, the former part is used as a data set for feature selection, and the latter part is used as a data set for merchant risk prediction after feature subset screening.
Step 104, determining a training set according to the feature subset.
And 105, training the machine learning model by using the training set to obtain a merchant risk prediction model.
The embodiment of the invention adopts a model evaluation method, namely, the risk of the commercial tenant is predicted through a neural network, and simultaneously, the prediction result is compared with the past history of the commercial tenant, the accuracy of the prediction is measured, and the accuracy is taken as an adaptation value.
Unlike mathematical prediction features, prediction is more accurate because the actual prediction model is used, which is often used as the final prediction model.
In one possible implementation, the machine learning model employs a random forest algorithm.
And 106, inputting the data sets except the feature subsets in the merchant data of the to-be-detected merchant into the merchant risk prediction model to obtain a merchant risk prediction result corresponding to the to-be-detected merchant.
According to the scheme, the optimal feature subset is selected from a large number of features, so that a series of problems that the workload is large, the manual experience is relied on, the feature association is ignored, local optimality is easily involved in a past manual experience or mathematical analysis method are avoided, accuracy of model to merchant risk prediction is improved, complexity of the model is reduced due to feature reduction, and risk management cost of a bank is reduced.
In step 102, the embodiment of the present invention preprocesses merchant data, and the step flow is shown in fig. 2, and specifically includes the following steps:
step 201, data cleaning is performed on merchant data.
The data cleansing includes one or any combination of missing value processing, outlier processing, and duplicate value processing.
And 202, normalizing the data of the commercial tenant after data cleaning.
To clean, transform, and unify the raw data for subsequent modeling and analysis. The embodiment of the invention adopts the following data preprocessing operation:
1. data cleaning: including missing value processing, outlier processing, duplicate value processing, etc. Aiming at merchant data, filling missing values or deleting records with more missing values by using an interpolation method; for outliers, statistical methods or visualization tools are used to identify and process.
2. Data conversion: including data transformation, normalization, etc. For example, normalization processing may be performed on index data of different dimensions.
In a possible implementation manner, in step 103, the embodiment of the present invention uses a particle swarm algorithm to screen out the feature subset from the preprocessed merchant data.
In order to screen redundant and invalid features, the embodiment of the invention avoids long time consumption of manually screening features and relies on manual experience, and adopts a particle swarm algorithm to screen and obtain a feature subset from preprocessed merchant data.
In the particle swarm algorithm, each solution is represented by one particle, and each particle moves within a search space to find the optimal solution. In each iteration, each particle in the population is updated based on its own experience with other particles. Specifically, each particle such as particle i All have a position x i ＝(x i1 ,x i2 ,x i3 ...,x iD ) And a velocity v i ＝(v i1 ,v i2 ,v i3 ...,v iD ). D is the dimension of the search space. In the evolution process, the velocity of a particle is updated by combining its own historical optimum position pbest with the population optimum position gbest obtained so far according to the following formula:
the position of the particle is updated by its original position and velocity according to equation 2:
d.epsilon.D represents the D-th position in the particle. T is the total number of iterations, T ε T represents the T-th iteration in the evolution process. P is the population size and i.epsilon.P represents the ith particle in the population. w is the inertial weight for controlling the effect of the previous speed. c 1 And c 2 Is the acceleration constant. r is (r) 1 And r 2 Is uniformly distributed in [0,1 ]]Random values in between. P is p id Representing the personally optimal solution of particle i in the last iteration of d in the past. P is p gd Representing the global optimal solution of the entire population in the last iteration of the past d. Particle x id Is subject to predefined minimum and maximum positions x t+1 ∈[x min ,x max ]Is limited by the speed v id Subject to a predefined minimum and maximum velocity v t+1 ∈[v min ,v max ]Is limited by the number of (a).
The embodiment of the invention adopts a particle swarm algorithm to screen and obtain the feature subset from the preprocessed merchant data, and the step flow is shown in figure 3 and specifically comprises the following steps:
step 301, initializing a particle swarm.
Initializing a particle swarm, randomly generating a plurality of particles, and determining the initial position and the initial speed of each particle.
The particle swarm initialization process affects the quality of the optimization result, and the initialization mode generally comprises the following steps:
random initialization: the position and the speed of each particle are randomly generated, which is the most basic particle swarm initialization method.
Grid initialization: the whole search space is divided into a plurality of grids, and each particle is randomly generated in one grid so as to ensure that the positions of the particles are uniformly distributed.
Cluster initialization: clustering is carried out according to known data samples, and a clustering center is used as the position of particles so as to ensure that the initial solution is closer to the globally optimal solution.
Initializing uniform distribution: the entire search space is divided uniformly into several cells, and then one particle is randomly generated within each cell.
Initializing manual design: the position and the speed of the particles are designed in advance by an expert according to the problem characteristics, so that the convergence speed and the resolution quality of the algorithm can be improved.
The method and the device have the advantages that the historic selection of the feature subsets as the initialization particles can bring the best effect, so that the embodiment of the invention selects a manual design initialization mode, and the quality of the feature subsets is convenient to further improve.
Step 302, the speed and position of the particles are updated according to the global optimal position and the individual optimal position.
The subset of features represented by the particles is evaluated by the neural network model, and the particle velocity and position are updated.
Wherein each particle remembers the optimal position it reached, called the individual optimal position; meanwhile, the optimal position in all particles is called a global optimal position.
Step 303, iterating until reaching a preset termination condition or maximum iteration number, and obtaining the optimal position of the particle.
To ensure that the population has converged, the scheme no longer presents a subset of the more optimal features over multiple iterations as the final termination condition.
Step 304, determining a feature subset according to the optimal position of the particles.
According to the embodiment of the invention, the particle swarm algorithm is adopted for feature selection, redundant and invalid features are reduced, the problems of over fitting or under fitting and the like are reduced, and the generalization capability and the prediction precision of the model are improved. The model structure is simplified, the calculation complexity and the storage space are reduced, the interference of irrelevant variables is avoided, and the quality and the reliability of data are improved. The cost of model establishment and maintenance is reduced.
Before the speed and the position of the particles are updated, the flow of the steps of the embodiment of the invention is shown in fig. 4, and the method specifically comprises the following steps:
the merchant data is encoded 401 by taking each feature of the merchant data as a bit of a population of particles.
Step 402, initializing a particle swarm.
For example, merchant deposits, flowing water may be one of the particles. When the number of features is larger, the scheme also reduces the length of the code by converting a plurality of features into a floating point number representation.
The merchant quality scoring method based on particle swarm feature selection can improve the accuracy and reliability of merchant scoring, and can reduce the risk management cost of banks at the same time:
the characteristics can be effectively screened based on particle swarm characteristic selection, and the result can be dynamically adjusted according to historical data and real-time data, so that the prediction result is more accurate and reliable. The relevance and regularity in the merchant data can be better mined, so that the accuracy and reliability of the prediction result are improved. The labor cost is reduced and the efficiency is improved.
The embodiment of the invention also provides a merchant risk prediction device, which is described in the following embodiment. The device is shown in fig. 5, and the device comprises:
a feature subset determining module 501, configured to obtain merchant data; the merchant data includes: business information, financial information and merchant risk information fed back by historical users of merchants; preprocessing merchant data; screening the preprocessed merchant data to obtain a feature subset;
a training module 502 for determining a training set from the feature subset; training the machine learning model by using the training set to obtain a merchant risk prediction model;
and the prediction module 503 is configured to input a data set except for the feature subset in the merchant data of the to-be-detected merchant into the merchant risk prediction model to obtain a merchant risk prediction result corresponding to the to-be-detected merchant.
In the embodiment of the present invention, the feature subset determining module 501 is specifically configured to:
preprocessing merchant data, including:
data cleaning is carried out on merchant data; the data cleaning comprises one or any combination of missing value processing, abnormal value processing and repeated value processing;
and carrying out normalization processing on the merchant data after data cleaning.
In the embodiment of the present invention, the feature subset determining module 501 is specifically configured to:
and screening the preprocessed merchant data by adopting a particle swarm algorithm to obtain a feature subset.
In the embodiment of the present invention, the feature subset determining module 501 is specifically configured to:
initializing a particle swarm;
updating the speed and the position of the particles according to the global optimal position and the individual optimal position;
repeating iteration until reaching a preset termination condition or maximum iteration times to obtain the optimal position of the particle;
and determining the feature subset according to the optimal position of the particles.
In the embodiment of the present invention, the feature subset determining module 501 is further configured to:
the merchant data is encoded by taking each feature of the merchant data as a bit of the population of particles prior to initializing the population of particles.
In the embodiment of the present invention, the prediction module 503 is specifically configured to:
the machine learning model adopts a random forest algorithm.
Because the principle of the device for solving the problems is similar to that of the merchant risk prediction method, the implementation of the device can refer to the implementation of the merchant risk prediction method, and the repetition is omitted.
The embodiment of the invention also provides computer equipment, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the merchant risk prediction method when executing the computer program.
The embodiment of the invention also provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program realizes the merchant risk prediction method when being executed by a processor.
The embodiment of the invention also provides a computer program product, which comprises a computer program, wherein the computer program realizes the merchant risk prediction method when being executed by a processor.
In the embodiment of the invention, merchant data is obtained; the merchant data includes: business information, financial information and merchant risk information fed back by historical users of merchants; preprocessing merchant data; screening the preprocessed merchant data to obtain a feature subset; determining a training set according to the feature subset; training the machine learning model by using the training set to obtain a merchant risk prediction model; and inputting the data sets except the feature subsets in the merchant data of the to-be-detected merchant into the merchant risk prediction model to obtain a merchant risk prediction result corresponding to the to-be-detected merchant. Compared with the prior art, the method has the advantages that the optimal feature subset is selected from a large number of features, the problems that the workload is large, the manual experience is relied on, the feature association is ignored, local optimality is easily involved in a traditional manual experience or mathematical analysis method are avoided, accuracy of model to merchant risk prediction is improved, complexity of the model is reduced due to feature reduction, and risk management cost of banks is reduced.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (10)
1. A method for predicting risk of a merchant, comprising:
acquiring merchant data; the merchant data includes: business information, financial information and merchant risk information fed back by historical users of merchants;
preprocessing merchant data;
screening the preprocessed merchant data to obtain a feature subset;
determining a training set according to the feature subset;
training the machine learning model by using the training set to obtain a merchant risk prediction model;
and inputting the data sets except the feature subsets in the merchant data of the to-be-detected merchant into the merchant risk prediction model to obtain a merchant risk prediction result corresponding to the to-be-detected merchant.
2. The method of claim 1, wherein preprocessing merchant data comprises:
data cleaning is carried out on merchant data; the data cleaning comprises one or any combination of missing value processing, abnormal value processing and repeated value processing;
and carrying out normalization processing on the merchant data after data cleaning.
3. The merchant risk prediction method of claim 1, wherein screening feature subsets from the preprocessed merchant data comprises:
and screening the preprocessed merchant data by adopting a particle swarm algorithm to obtain a feature subset.
4. The method of claim 3, wherein the screening feature subsets from the preprocessed merchant data using a particle swarm algorithm comprises:
initializing a particle swarm;
updating the speed and the position of the particles according to the global optimal position and the individual optimal position;
repeating iteration until reaching a preset termination condition or maximum iteration times to obtain the optimal position of the particle;
and determining the feature subset according to the optimal position of the particles.
5. The method of claim 4, further comprising, prior to initializing the population of particles:
the merchant data is encoded by taking each feature of the merchant data as one bit of the population of particles.
6. The merchant risk prediction method of claim 1, wherein the machine learning model employs a random forest algorithm.
7. A merchant risk prediction apparatus, comprising:
the feature subset determining module is used for acquiring merchant data; the merchant data includes: business information, financial information and merchant risk information fed back by historical users of merchants; preprocessing merchant data; screening the preprocessed merchant data to obtain a feature subset;
the training module is used for determining a training set according to the feature subset; training the machine learning model by using the training set to obtain a merchant risk prediction model;
and the prediction module is used for inputting the data sets except the feature subsets in the merchant data of the to-be-detected merchant into the merchant risk prediction model to obtain a merchant risk prediction result corresponding to the to-be-detected merchant.
8. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method of any of claims 1 to 6 when executing the computer program.
9. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program which, when executed by a processor, implements the method of any one of claims 1 to 6.
10. A computer program product, characterized in that the computer program product comprises a computer program which, when executed by a processor, implements the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310891543.6A CN116883065A (en) | 2023-07-19 | 2023-07-19 | Merchant risk prediction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310891543.6A CN116883065A (en) | 2023-07-19 | 2023-07-19 | Merchant risk prediction method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116883065A true CN116883065A (en) | 2023-10-13 |
Family
ID=88261930
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310891543.6A Pending CN116883065A (en) | 2023-07-19 | 2023-07-19 | Merchant risk prediction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116883065A (en) |
-
2023
- 2023-07-19 CN CN202310891543.6A patent/CN116883065A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102044205B1 (en) | Target information prediction system using big data and machine learning and method thereof | |
| CN110717535B (en) | Automatic modeling method and system based on data analysis processing system | |
| CN110738564A (en) | Post-loan risk assessment method and device and storage medium | |
| CA3097449A1 (en) | Method and system for model auto-selection using an ensemble of machine learning models | |
| CN109934301B (en) | Power load cluster analysis method, device and equipment | |
| CN111369344B (en) | Method and device for dynamically generating early warning rules | |
| CN109636482B (en) | Data processing method and system based on similarity model | |
| CN114048436A (en) | Construction method and construction device for forecasting enterprise financial data model | |
| US10963802B1 (en) | Distributed decision variable tuning system for machine learning | |
| WO2023103527A1 (en) | Access frequency prediction method and device | |
| CN111738331A (en) | User classification method and device, computer-readable storage medium and electronic device | |
| CN114202243A (en) | Engineering project management risk early warning method and system based on random forest | |
| CN116187835A (en) | Data-driven-based method and system for estimating theoretical line loss interval of transformer area | |
| CN115983900A (en) | Method, apparatus, device, medium, and program product for constructing user marketing strategy | |
| Bi et al. | Accurate Prediction of Workloads and Resources with Multi-head Attention and Hybrid LSTM for Cloud Data Centers | |
| CN110740063B (en) | Network flow characteristic index prediction method based on signal decomposition and periodic characteristics | |
| CN107590747A (en) | Power grid asset turnover rate computational methods based on the analysis of comprehensive energy big data | |
| CN116862658A (en) | Credit evaluation method, apparatus, electronic device, medium and program product | |
| CN110738565A (en) | Real estate finance artificial intelligence composite wind control model based on data set | |
| CN116883065A (en) | Merchant risk prediction method and device | |
| US11823066B2 (en) | Enterprise market volatility predictions through synthetic DNA and mutant nucleotides | |
| CN116228284A (en) | Goods demand prediction method, training device, computer system and medium | |
| TWI792101B (en) | Data Quantification Method Based on Confirmed Value and Predicted Value | |
| Ntaliakouras et al. | An apache spark methodology for forecasting tourism demand in greece | |
| Nagashima et al. | Data Imputation Method based on Programming by Example: APREP-S |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |