CN108596630A - Fraudulent trading recognition methods, system and storage medium based on deep learning - Google Patents
Fraudulent trading recognition methods, system and storage medium based on deep learning Download PDFInfo
- Publication number
- CN108596630A CN108596630A CN201810407275.5A CN201810407275A CN108596630A CN 108596630 A CN108596630 A CN 108596630A CN 201810407275 A CN201810407275 A CN 201810407275A CN 108596630 A CN108596630 A CN 108596630A
- Authority
- CN
- China
- Prior art keywords
- layer
- fraudulent trading
- dimensionality reduction
- rbm
- rbm neural
- 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.)
- Granted
Links
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
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/38—Payment protocols; Details thereof
- G06Q20/40—Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
- G06Q20/401—Transaction verification
- G06Q20/4016—Transaction verification involving fraud or risk level assessment in transaction processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/088—Non-supervised learning, e.g. competitive learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Accounting & Taxation (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Evolutionary Biology (AREA)
- Software Systems (AREA)
- Computer Security & Cryptography (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of fraudulent trading recognition methods, system and storage medium based on deep learning, this method include：Training sample is obtained, the training sample is the transaction data for establishing fraudulent trading detection model；The RBM neural network structures stacked are built, and train the RBM neural network structures of the stacking based on the training sample, generate dimensionality reduction device；Dimensionality reduction is carried out to the training sample by the dimensionality reduction device, and the binary condition vector obtained by dimensionality reduction is clustered, to establish fraudulent trading detection model；Transaction data to be detected is obtained, and according to the fraudulent trading detection model, analyzes transaction data to be detected, to identify fraudulent trading.The present invention can improve the accuracy of fraudulent trading identification, without pre-defined method for measuring similarity, so as to reduce difficulty and cost, and to the tolerance of sample data height.
Description
Technical field
The present invention relates to Financial Risk Control field more particularly to a kind of fraudulent trading identification sides based on deep learning
Method, system and storage medium.
Background technology
Financial field is to the more demanding of transaction risk control.In the identification for carrying out fraudulent trading using deep learning,
Detection model is generally trained using supervised learning algorithm at present, and is used to train detection model to be characterized in based on there is going through for label
History transaction data and construct, therefore using supervised learning algorithm training detection model, can effectively identify history cheat class
Type, and be to the general incapability of unknown fraud type (for example do not occurred or the fraudulent trading of mutation) for lacking fraud sample
Power, this posteriority cause transaction risk identification to have hysteresis quality, accuracy relatively low.
On the other hand, when the existing progress fraudulent trading identification using unsupervised learning algorithm, K-Means algorithms are generally used
Or density-based algorithms are directly clustered to data and (do not pass through dimensionality reduction), the essence of above-mentioned clustering algorithm is to be based on
The metric learning (metric learning) of similarity, need to previously according to the distance between experience Manual definition's sample, however,
For training the feature of detection model to belong to high dimensional feature, the data of high dimensional feature are manually difficult to determine suitable similarity
Measure can only determine suitable similarity through a large number of experiments, take a substantial amount of time and manpower；And it is currently used
Feature dimension reduction method is principal component analysis (PCA), and PCA is adapted to linear and Gaussian distributed data, in practical application
Data are substantially nonlinear, it is difficult to meet the applicable conditions of PCA, PCA can not reach expected dimensionality reduction effect in practice
Even fail.In short, existing carry out fraudulent trading knowledge otherwise by unsupervised learning algorithm, difficulty and cost are huge, and
Harshness is required to sample data, the sample data provided in practical application is difficult to meet the requirements.
Invention content
The fraudulent trading recognition methods based on deep learning that the main purpose of the present invention is to provide a kind of, it is intended to solve existing
There is fraudulent trading recognition methods not accurate enough, difficulty and cost are huge, and require sample data harsh technical problem.
To achieve the above object, the present invention provides a kind of fraudulent trading recognition methods based on deep learning, the method
Including：
Training sample is obtained, the training sample is the transaction data for establishing fraudulent trading detection model；
The limited Boltzmann machine RBM neural network structures stacked are built, and the heap is trained based on the training sample
Folded RBM neural network structures generate dimensionality reduction device；
Dimensionality reduction carried out to the training sample by the dimensionality reduction device, and by the binary condition vector obtained by dimensionality reduction into
Row cluster, to establish fraudulent trading detection model；
Transaction data to be detected is obtained, and according to the fraudulent trading detection model, analyzes transaction data to be detected, to know
Fraudulent trading is not gone out.
Optionally, the step of RBM neural network structures of the structure stacking include：
The output node number of the number of plies and each layer of RBM neural network of the RBM neural network structures of the stacking is set.
Optionally, the RBM neural network structures that the stacking is trained based on the training sample generate dimensionality reduction device
Step includes：
The feature of the training sample is determined, and according to feature construction high dimensional feature vector, by the high dimensional feature
Vector constitutes high-dimensional feature space；
Based on the high-dimensional feature space, each layer of RBM god in the RBM neural network structures of the stacking is trained one by one
Through network；
Each layer RBM neural networks that training is completed are stacked, dimensionality reduction device is generated.
Optionally, described to be based on the high-dimensional feature space, in the RBM neural network structures for training the stacking one by one
The step of each layer of RBM neural network includes：
Based on the high-dimensional feature space, each layer in RBM neural network structures by training the stacking one by one
RBM neural networks, with the parameter of each layer RBM neural networks of determination.
Optionally, described to be based on the high-dimensional feature space, by the RBM neural network structures for training the stacking one by one
In each layer of RBM neural network, include with the step of parameters of each layer RBM neural networks of determination：
The initial parameter value of first layer RBM neural networks is randomly generated using normal distribution；
First layer is trained using the dimension of the high-dimensional feature space as the input number of nodes of first layer RBM neural networks
RBM neural networks obtain first layer RBM nerves by adjusting the initial parameter value of the first layer RBM neural networks when training
The parameter of network；
After the parameter for obtaining N-1 layers of RBM neural networks, n-th layer RBM neural networks are randomly generated using normal distribution
Initial parameter value；
It is instructed using the output node number of N-1 layers of RBM neural networks as the input number of nodes of n-th layer RBM neural networks
Practice n-th layer neural network, by adjusting the initial parameter value of the n-th layer RBM neural networks when training, obtains n-th layer RBM god
Parameter through network, to obtain the parameter of each layer RBM neural networks, wherein N >=2.
Optionally, each layer of RBM neural network includes visible layer and hidden layer, each layer of RBM neural network
Parameter include weight matrix between the visible layer and hidden layer, in visible layer in the offset and hidden layer of visible node
The offset of concealed nodes.
Optionally, described that dimensionality reduction, and two will obtained by dimensionality reduction are carried out to the training sample by the dimensionality reduction device
The step of first state vector is clustered include：
By the dimensionality reduction device, the training sample is mapped as binary condition vector；
Training sample with identical binary condition vector is classified as same group, if so that the training sample is divided into
Gan Ge groups.
Optionally, described that transaction data to be detected is analyzed according to the fraudulent trading detection model, to identify that fraud is handed over
Easy step includes：
By the transaction data to be detected, substitutes into the fraudulent trading detection model and carry out dimensionality reduction and cluster successively, obtain
To transaction group to be detected；
The corresponding probability of cheating of each transaction group to be detected is analyzed, needs to aggravate according to the determination of each probability of cheating of analysis
The transaction group to be detected of audit, to identify fraudulent trading.
In addition, to achieve the above object, the present invention also provides a kind of fraudulent trading identifying system based on deep learning, institute
Stating the fraudulent trading identifying system based on deep learning includes：It memory, processor and is stored on the memory and can be
The fraudulent trading recognizer based on deep learning run on the processor, the fraudulent trading based on deep learning are known
Other program realizes following steps when being executed by the processor：
Training sample is obtained, the training sample is the transaction data for establishing fraudulent trading detection model；
The limited Boltzmann machine RBM neural network structures stacked are built, and the heap is trained based on the training sample
Folded RBM neural network structures generate dimensionality reduction device；
Dimensionality reduction carried out to the training sample by the dimensionality reduction device, and by the binary condition vector obtained by dimensionality reduction into
Row cluster, to establish fraudulent trading detection model；
Transaction data to be detected is obtained, and according to the fraudulent trading detection model, analyzes transaction data to be detected, to know
Fraudulent trading is not gone out.
In addition, to achieve the above object, the present invention also provides a kind of storage medium, being stored with and being based on the storage medium
The fraudulent trading recognizer of deep learning, it is real when the fraudulent trading recognizer based on deep learning is executed by processor
Existing following steps：
Training sample is obtained, the training sample is the transaction data for establishing fraudulent trading detection model；
The limited Boltzmann machine RBM neural network structures stacked are built, and the heap is trained based on the training sample
Folded RBM neural network structures generate dimensionality reduction device；
Dimensionality reduction carried out to the training sample by the dimensionality reduction device, and by the binary condition vector obtained by dimensionality reduction into
Row cluster, to establish fraudulent trading detection model；
Transaction data to be detected is obtained, and according to the fraudulent trading detection model, analyzes transaction data to be detected, to know
Fraudulent trading is not gone out.
The present invention builds the RBM neural network structures stacked, based on unsupervised high dimensional data sample to RBM neural networks
Structure is trained, and generates dimensionality reduction device；Then dimensionality reduction is carried out to unsupervised high dimensional data sample by the dimensionality reduction device of generation, and
The binary condition vector obtained by dimensionality reduction is clustered, this process is not necessarily to pre-defined method for measuring similarity, reduces
Difficulty and cost, and it is high to sample data tolerance, to establish fraudulent trading detection model, for analyzing transaction to be detected
Data realize dimensionality reduction and cluster to transaction data to be detected based on fraudulent trading detection model, and this makes it possible to obtain with fresh
Each transaction group to be detected of bright characteristic, then risk of fraud identification is carried out to each transaction group to be detected, can effectively it know
The fraudulent trading of other history fraud type and unknown fraud type, improves the accuracy of fraudulent trading identification.
Description of the drawings
Fig. 1 is the terminal structure schematic diagram for the hardware running environment that the embodiment of the present invention is related to；
Fig. 2 is that the present invention is based on the flow diagrams of the fraudulent trading recognition methods first embodiment of deep learning；
Fig. 3 is 3 layers of RBM neural network structure schematic diagrames of the present invention；
Fig. 4 is that the present invention is based on the refinement flow diagrams of the fraudulent trading recognition methods first embodiment of deep learning；
Fig. 5 is the schematic diagram of each layer of RBM neural network of the present invention；
The present invention is based on the flow diagrams of the fraudulent trading recognition methods second embodiment of deep learning by Fig. 6.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific implementation mode
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
The primary solutions of the embodiment of the present invention are：Training sample is obtained, the training sample is to be cheated for establishing
The transaction data of transaction detection model；The RBM neural network structures stacked are built, and the heap is trained based on the training sample
Folded RBM neural network structures generate dimensionality reduction device；Dimensionality reduction is carried out to the training sample by the dimensionality reduction device, and will be passed through
The binary condition vector that dimensionality reduction obtains is clustered, to establish fraudulent trading detection model；Obtain transaction data to be detected, and root
According to the fraudulent trading detection model, transaction data to be detected is analyzed, to identify fraudulent trading.
As shown in Figure 1, the terminal structure schematic diagram for the hardware running environment that Fig. 1, which is the embodiment of the present invention, to be related to.
Terminal of the embodiment of the present invention carries the fraudulent trading identifying system based on deep learning.
As shown in Figure 1, the terminal may include：Processor 1001, such as CPU, communication bus 1002, user interface
1003, network interface 1004, memory 1005.Wherein, communication bus 1002 is for realizing the connection communication between these components.
User interface 1003 may include display screen (Display), input unit such as keyboard (Keyboard), optional user interface
1003 can also include standard wireline interface and wireless interface.Network interface 1004 may include optionally that the wired of standard connects
Mouth, wireless interface (such as WI-FI interfaces).Memory 1005 can be high-speed RAM memory, can also be stable memory
(non-volatile memory), such as magnetic disk storage.Memory 1005 optionally can also be independently of aforementioned processor
1001 storage device.
It will be understood by those skilled in the art that the restriction of the not structure paired terminal of terminal structure shown in Fig. 1, can wrap
It includes than illustrating more or fewer components, either combines certain components or different components arrangement.
As shown in Figure 1, as may include that operating system, network are logical in a kind of memory 1005 of computer storage media
Believe module, Subscriber Interface Module SIM and the fraudulent trading recognizer based on deep learning.
In terminal shown in Fig. 1, network interface 1004 is mainly used for connecting background server, is carried out with background server
Data communicate；User interface 1003 is mainly used for connecting client (user terminal), with client into row data communication；And processor
1001 can be used for calling the fraudulent trading recognizer based on deep learning stored in memory 1005, and execute following behaviour
Make：
Training sample is obtained, the training sample is the transaction data for establishing fraudulent trading detection model；
The RBM neural network structures stacked are built, and train the RBM neural networks of the stacking based on the training sample
Structure generates dimensionality reduction device；
Dimensionality reduction carried out to the training sample by the dimensionality reduction device, and by the binary condition vector obtained by dimensionality reduction into
Row cluster, to establish fraudulent trading detection model；
Transaction data to be detected is obtained, and according to the fraudulent trading detection model, analyzes transaction data to be detected, to know
Fraudulent trading is not gone out.
Further, processor 1001 can call the fraudulent trading based on deep learning stored in memory 1005 to know
Other program also executes following operation：
The output node number of the number of plies and each layer of RBM neural network of the RBM neural network structures of the stacking is set.
Further, processor 1001 can call the fraudulent trading based on deep learning stored in memory 1005 to know
Other program also executes following operation：
The feature of the training sample is determined, and according to feature construction high dimensional feature vector, by the high dimensional feature
Vector constitutes high-dimensional feature space；
Based on the high-dimensional feature space, each layer of RBM god in the RBM neural network structures of the stacking is trained one by one
Through network；
Each layer RBM neural networks that training is completed are stacked, dimensionality reduction device is generated.
Further, processor 1001 can call the fraudulent trading based on deep learning stored in memory 1005 to know
Other program also executes following operation：
Based on the high-dimensional feature space, each layer in RBM neural network structures by training the stacking one by one
RBM neural networks, with the parameter of each layer RBM neural networks of determination.
Further, processor 1001 can call the fraudulent trading based on deep learning stored in memory 1005 to know
Other program also executes following operation：
The initial parameter value of first layer RBM neural networks is randomly generated using normal distribution；
First layer is trained using the dimension of the high-dimensional feature space as the input number of nodes of first layer RBM neural networks
RBM neural networks obtain first layer RBM nerves by adjusting the initial parameter value of the first layer RBM neural networks when training
The parameter of network；
After the parameter for obtaining N-1 layers of RBM neural networks, n-th layer RBM neural networks are randomly generated using normal distribution
Initial parameter value；
It is instructed using the output node number of N-1 layers of RBM neural networks as the input number of nodes of n-th layer RBM neural networks
Practice n-th layer neural network, by adjusting the initial parameter value of the n-th layer RBM neural networks when training, obtains n-th layer RBM god
Parameter through network, to obtain the parameter of each layer RBM neural networks, wherein N >=2.
Further, each layer of RBM neural network includes visible layer and hidden layer, each layer of RBM nerve net
The parameter of network includes weight matrix between the visible layer and hidden layer, in visible layer visible node offset and hidden layer
The offset of middle concealed nodes.
Further, processor 1001 can call the fraudulent trading based on deep learning stored in memory 1005 to know
Other program also executes following operation：
By the dimensionality reduction device, the training sample is mapped as binary condition vector；
Training sample with identical binary condition vector is classified as same group, if so that the training sample is divided into
Gan Ge groups.
Further, processor 1001 can call the fraudulent trading based on deep learning stored in memory 1005 to know
Other program also executes following operation：
By the transaction data to be detected, substitutes into the fraudulent trading detection model and carry out dimensionality reduction and cluster successively, obtain
To transaction group to be detected；
The corresponding probability of cheating of each transaction group to be detected is analyzed, needs to aggravate according to the determination of each probability of cheating of analysis
The transaction group to be detected of audit, to identify fraudulent trading.
Based on above-mentioned hardware configuration, propose that the present invention is based on each implementations of the fraudulent trading recognition methods of deep learning
Example.
With reference to Fig. 2, the present invention is based on the fraudulent trading recognition methods first embodiments of deep learning to provide a kind of be based on deeply
The fraudulent trading recognition methods for spending study, the method includes：
Step S10, obtains training sample, and the training sample is the number of deals for establishing fraudulent trading detection model
According to；
In the present embodiment, it is somebody's turn to do the fraudulent trading recognition methods based on deep learning and is applied to the fraud based on deep learning
Transaction identification system.The present embodiment establishes fraudulent trading detection model using unsupervised learning method.
In the present embodiment, include the steps that the historical trading data acquired in a period of time before step S10, this is gone through
History transaction data includes the essential informations such as exchange hour, transaction IP address, transaction area, transaction amount, traction equipment, will be acquired
Historical trading data as the training sample for establishing fraudulent trading detection model, the training sample be one set,
The element of set the inside is transaction data sample one by one, such as：
Training sample=transaction data sample 1, transaction data sample 2 ...
=(exchange hour 1, transaction IP address 1, transaction area 1, transaction amount 1, traction equipment 1), (exchange hour 2,
Transaction IP address 2, transaction area 2, transaction amount 2, traction equipment 2) ... }.
That is, the high dimensional data that each sample in training sample is made of the essential information merchandised, and the training sample
This does not have data label.
Step S20 builds the RBM neural network structures of stacking, and the RBM of the stacking is trained based on the training sample
Neural network structure generates dimensionality reduction device；
In the present embodiment, the RBM neural network structures for needing structure to stack, and based on training sample to RBM nerves
Network structure is trained.RBM (Restricted Boltzmann Machine, limited Boltzmann machine) be it is a kind of it is available with
Machine neural network (Stochastic neural network) is come the probability graph model (Probabilistic that explains
graphical model)；It is so-called " random ", refer to neuron in this network it is probabilistic neural member, there are two types of outputs only
State (un-activation, activation) is generally indicated with binary zero and 1, that is to say, that RBM each output node values 0 or
1, specific value need to be determined according to probability statistics rule；There is connectionless, interlayer in layer to connect entirely for connection between neuron
The characteristics of connecing.It follows that RBM is the structure based on two points of (probability) figures.Can be arranged RBM neural network structures the number of plies and
The output node number of each layer of RBM neural network, to build the RBM neural network structures of stacking, by taking Fig. 3 as an example, Fig. 3 is 3 layers
RBM neural network structure schematic diagrames, i.e., the number of plies of RBM neural network structures is set as 3 layers, from bottom (first layer) under
On and, the output node number of each layer of RBM neural network is respectively set to 6,4,3 successively.It later, can be according to training sample
The RBM neural network structures of structure are trained, to generate dimensionality reduction device.Specifically, with reference to Fig. 4, it is based on the trained sample
This trains the RBM neural network structures of the stacking, and the step of generating dimensionality reduction device includes：
Step S21 determines the feature of the training sample, and according to feature construction high dimensional feature vector, by described
High dimensional feature vector constitutes high-dimensional feature space；
Step S22 is based on the high-dimensional feature space, trains one by one every in the RBM neural network structures of the stacking
One layer of RBM neural network；
Step S23 stacks each layer RBM neural networks that training is completed, and generates dimensionality reduction device.
When it is implemented, needing the feature of determining training sample first.Since each sample in training sample is by handing over
The high dimensional data of easy essential information composition, can construct high dimensional feature vector based on the essential information of transaction, high dimensional feature to
Amount constitutes high-dimensional feature space.For example, each sample in training sample be by exchange hour, transaction IP address, transaction area,
When 5 dimension data of transaction amount and traction equipment composition, for each sample, it can construct based on exchange hour, with merchandising IP
Location, transaction area, transaction amount, traction equipment feature vector, as a result, each sample in training sample contain 5 Wei Te
Levy space.
Based on high-dimensional feature space, each layer of RBM nerve net can be trained one by one from bottom (first layer) from bottom to top
Network stacks each layer RBM neural networks that training is completed, and just generates a dimensionality reduction device.Pass through the dimensionality reduction device, training sample
In the high-dimensional feature space of each sample can be mapped to a lower dimensional space.For example, with RBM neural networks shown in Fig. 3
For structure, have the RBM neural networks that have three layers, the output node number of top layer RBM neural networks is set as 3, then 5 dimensional features
Space will be reduced to 3 dimensions after the processing of 3 layers of RBM neural networks.
Specifically, the step S22 may include：
Step S220 is based on the high-dimensional feature space, in the RBM neural network structures by training the stacking one by one
Each layer of RBM neural network, with the parameter of each layer RBM neural networks of determination.
Wherein, step S220 may include：
Step S221 randomly generates the initial parameter value of first layer RBM neural networks using normal distribution；
Step S222, using the dimension of the high-dimensional feature space as the input number of nodes of first layer RBM neural networks
Training first layer RBM neural networks obtain the by adjusting the initial parameter value of the first layer RBM neural networks when training
The parameter of one layer of RBM neural network；
Step S223 randomly generates n-th layer after the parameter for obtaining N-1 layers of RBM neural networks using normal distribution
The initial parameter value of RBM neural networks；
Step S224, using the output node number of N-1 layers of RBM neural networks as the input of n-th layer RBM neural networks
Number of nodes trains n-th layer neural network, by adjusting the initial parameter value of the n-th layer RBM neural networks when training, obtains the
The parameter of N layers of RBM neural networks, to obtain the parameter of each layer RBM neural networks, wherein N >=2.
The training to each layer of RBM neural network is this means that adjust the parameter of each layer of RBM neural network one by one.Reference
Fig. 5, Fig. 5 are the schematic diagram of each layer of RBM neural network, and each layer of RBM neural network includes visible layer and hidden layer, each layer
The parameter of RBM neural networks includes the weight matrix w between the visible layer and hidden layeri,j, wi,jIt indicates in visible layer i-th
It can be seen that the connection weight in node (neuron) and hidden layer between j-th of concealed nodes (neuron)；Each layer of RBM nerve net
The parameter of network further includes the offset b=(b of visible node in visible layer1,b2,b3,…,bi), biIndicate visible layer in i-th can
See the offset of node；The parameter of each layer of RBM neural network further includes the offset c=(c of concealed nodes in hidden layer1,c2,
c3,…,cj), cjIndicate the offset of j-th of concealed nodes in hidden layer.
Specifically, the step of training each layer of RBM neural network one by one is as follows：
The parameter of bottom (first layer) RBM neural networks is initialized first, i.e., randomly generates bottom (the using normal distribution
One layer) initial parameter values of RBM neural networks, that is to say, that the initial parameter value of bottom (first layer) RBM neural networks is next
Random number from normal distribution (0,1), then using the dimension of above-mentioned high-dimensional feature space as bottom (first layer) RBM nerves
The input number of nodes of network trains first layer RBM neural networks, learns to obtain bottom (first layer) RBM neural networks when training
Parameter, the i.e. initial parameter value by adjusting the first layer RBM neural networks obtain bottom (first layer) RBM neural networks
Parameter；After the parameter for obtaining bottom (first layer) RBM neural networks, second layer RBM god is randomly generated using normal distribution
Initial parameter value through network, then using the output node number of bottom (first layer) RBM neural networks as second layer RBM god
Input number of nodes through network trains second layer neural network, by adjusting the ginseng of the second layer RBM neural networks when training
Number initial value, obtains the parameter of second layer RBM neural networks；And so on, that is, utilize the output of N-1 layers of RBM neural networks
Number of nodes trains n-th layer neural network as the input number of nodes of n-th layer RBM neural networks, by adjusting the N when training
The initial parameter value of layer RBM neural networks, obtains the parameter of n-th layer RBM neural networks, wherein N >=2, this makes it possible to obtain each layers
The parameter of RBM neural networks, to complete the training of each layer of RBM neural network, by each layer RBM neural networks of training completion
It is stacked, just generates a dimensionality reduction device.
Step S30 carries out dimensionality reduction, and the binary shape that will be obtained by dimensionality reduction by the dimensionality reduction device to the training sample
State vector is clustered, to establish fraudulent trading detection model；Wherein, it is described by the dimensionality reduction device to the training sample into
Row dimensionality reduction, and the step of binary condition vector obtained by dimensionality reduction is clustered may include：
The training sample is mapped as binary condition vector by step S31 by the dimensionality reduction device；
Step S32, the training sample with identical binary condition vector are classified as same group, so that the training sample is drawn
It is divided into several groups.
After the present embodiment generates dimensionality reduction device, dimensionality reduction can be carried out to training sample by the dimensionality reduction device, in this way, training sample
Each sample be mapped as a binary condition vector.Assuming that dimensionality reduction device will be dropped with the training sample of n dimensional feature spaces
Dimension ties up (m≤n) to m, can theoretically generate 2mA binary condition vector.It should be noted that can be reached when only m≤n
To the purpose of dimensionality reduction.In actual tests, the sample of one 2000 dimension is mapped as the binary condition vector of 35 dimensions：
(11101111001011111110111111111111111), i.e., as n=2000, after dimensionality reduction device dimension-reduction treatment, m=
35.In the process, it is not necessarily to pre-defined method for measuring similarity, also just without manually determining high dimensional data by many experiments
The similarity of sample, not only difficulty reduces, but also reduces cost.
Later, the binary condition vector obtained by dimensionality reduction is clustered, i.e., it will be with identical binary condition vector
Training sample is classified as same group, and the training sample is divided into several groups's (being defined as G group), in this way, can
To establish a fraudulent trading detection model with dimensionality reduction and the function of convergence.In addition, in actual tests, finally obtained group
Number G is well below 2 for groupm, this also illustrates RBM very strong ability in feature extraction and noise processed ability, tolerates sample
Degree is high.
In the present embodiment, it is a kind of unsupervised high dimensional data sample since training sample does not have data label, it can
Effectively to represent data characteristics, the RBM neural network structures built in advance using this sample training, in addition RBM has very strong spy
Sign extractability and noise processed ability, the accuracy of dimensionality reduction device greatly promote, to also improve fraudulent trading detection model
Accuracy.
Step S40 obtains transaction data to be detected, and according to the fraudulent trading detection model, analyzes transaction to be detected
Data, to identify fraudulent trading.
In the present embodiment, when receiving transaction data to be detected, so that it may be cheated with substituting into transaction data to be detected
Transaction detection model, carries out dimensionality reduction and cluster successively, can obtain each transaction group to be detected, and then identify each group
Transaction swindling risk, thus identifies fraudulent trading.
The RBM neural network structures that the present embodiment structure stacks, based on unsupervised high dimensional data sample to RBM nerve nets
Network structure is trained, and generates dimensionality reduction device；Then dimensionality reduction is carried out to unsupervised high dimensional data sample by the dimensionality reduction device of generation,
And cluster the binary condition vector obtained by dimensionality reduction, this process is not necessarily to pre-defined method for measuring similarity, drop
Low difficulty and cost, and it is high to sample data tolerance, to establish fraudulent trading detection model, for analyzing test cross to be checked
Easy data realize dimensionality reduction and cluster to transaction data to be detected based on fraudulent trading detection model, this makes it possible to obtain with
Each transaction group to be detected of distinct characteristic, then risk of fraud identification is carried out to each transaction group to be detected, it can be effective
The fraudulent trading for identifying history fraud type and unknown fraud type, improves the accuracy of fraudulent trading identification.
Further, with reference to Fig. 6, the present invention is based on the fraudulent trading recognition methods second embodiments of deep learning to provide one
Fraudulent trading recognition methods of the kind based on deep learning, is based on above-mentioned embodiment shown in Fig. 2, and the step S40 can be wrapped
It includes：
Step S41, by the transaction data to be detected, substitute into the fraudulent trading detection model carry out successively dimensionality reduction and
Cluster, obtains transaction group to be detected；
Step S42 analyzes the corresponding probability of cheating of each transaction group to be detected, true according to each probability of cheating of analysis
Surely the transaction group to be detected that audit need to be aggravated, to identify fraudulent trading.
In the present embodiment, when receiving transaction data to be detected, transaction data to be detected is substituted into fraudulent trading inspection
It surveys and carries out dimensionality reduction and cluster in model, since fraudulent trading detection model is based on unsupervised high dimensional data sample, and tool
There is the RBM of very strong ability in feature extraction and noise processed ability and establish, transaction data to be detected is detected by fraudulent trading
After the dimensionality reduction and cluster of model, each transaction group to be detected with distinct characteristic can be obtained, is then analyzed each to be checked
The corresponding probability of cheating of the easy group of test cross determines the transaction group to be detected that need to aggravate audit according to each probability of cheating of analysis
Group, then identify fraudulent trading from the transaction group to be detected that need to aggravate audit, the accuracy of fraudulent trading identification can be improved.
In addition, the embodiment of the present invention also proposes a kind of storage medium.
The fraudulent trading recognizer based on deep learning is stored on institute's storage medium of the present invention, it is described to be based on depth
Following operation is realized when the fraudulent trading recognizer of habit is executed by processor：
Training sample is obtained, the training sample is the transaction data for establishing fraudulent trading detection model；
The RBM neural network structures stacked are built, and train the RBM neural networks of the stacking based on the training sample
Structure generates dimensionality reduction device；
Dimensionality reduction carried out to the training sample by the dimensionality reduction device, and by the binary condition vector obtained by dimensionality reduction into
Row cluster, to establish fraudulent trading detection model；
Transaction data to be detected is obtained, and according to the fraudulent trading detection model, analyzes transaction data to be detected, to know
Fraudulent trading is not gone out.
The specific embodiment of storage medium of the present invention is respectively implemented with the above-mentioned fraudulent trading recognition methods based on deep learning
Example is essentially identical, and therefore not to repeat here.
It should be noted that herein, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that process, method, article or system including a series of elements include not only those elements, and
And further include other elements that are not explicitly listed, or further include for this process, method, article or system institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including this
There is also other identical elements in the process of element, method, article or system.
The embodiments of the present invention are for illustration only, can not represent the quality of embodiment.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can add the mode of required general hardware platform to realize by software, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical scheme of the present invention substantially in other words does the prior art
Going out the part of contribution can be expressed in the form of software products, which is stored in a storage medium
In (such as ROM/RAM, magnetic disc, CD), including some instructions are used so that a station terminal equipment (can be mobile phone, computer, clothes
Be engaged in device, air conditioner or the network equipment etc.) execute method described in each embodiment of the present invention.
It these are only the preferred embodiment of the present invention, be not intended to limit the scope of the invention, it is every to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of fraudulent trading recognition methods based on deep learning, which is characterized in that the method includes：
Training sample is obtained, the training sample is the transaction data for establishing fraudulent trading detection model；
The limited Boltzmann machine RBM neural network structures stacked are built, and the stacking is trained based on the training sample
RBM neural network structures generate dimensionality reduction device；
Dimensionality reduction is carried out to the training sample by the dimensionality reduction device, and the binary condition vector obtained by dimensionality reduction is gathered
Class, to establish fraudulent trading detection model；
Transaction data to be detected is obtained, and according to the fraudulent trading detection model, analyzes transaction data to be detected, to identify
Fraudulent trading.
2. the fraudulent trading recognition methods based on deep learning as described in claim 1, which is characterized in that the structure stacks
RBM neural network structures the step of include：
The output node number of the number of plies and each layer of RBM neural network of the RBM neural network structures of the stacking is set.
3. the fraudulent trading recognition methods based on deep learning as claimed in claim 2, which is characterized in that described based on described
Training sample trains the RBM neural network structures of the stacking, and the step of generating dimensionality reduction device includes：
The feature of the training sample is determined, and according to feature construction high dimensional feature vector, by high dimensional feature vector
Constitute high-dimensional feature space；
Based on the high-dimensional feature space, each layer of RBM nerve net in the RBM neural network structures of the stacking is trained one by one
Network；
Each layer RBM neural networks that training is completed are stacked, dimensionality reduction device is generated.
4. the fraudulent trading recognition methods based on deep learning as claimed in claim 3, which is characterized in that described based on described
High-dimensional feature space, one by one train the stacking RBM neural network structures in each layer of RBM neural network the step of wrap
It includes：
Based on the high-dimensional feature space, each layer of RBM god in RBM neural network structures by training the stacking one by one
Through network, with the parameter of each layer RBM neural networks of determination.
5. the fraudulent trading recognition methods based on deep learning as claimed in claim 4, which is characterized in that described based on described
High-dimensional feature space, each layer of RBM neural network in RBM neural network structures by training the stacking one by one, with true
The step of parameter of each layer RBM neural networks includes calmly：
The initial parameter value of first layer RBM neural networks is randomly generated using normal distribution；
Using the dimension of the high-dimensional feature space as the input number of nodes of first layer RBM neural networks training first layer RBM
Neural network obtains first layer RBM nerve nets by adjusting the initial parameter value of the first layer RBM neural networks when training
The parameter of network；
After the parameter for obtaining N-1 layers of RBM neural networks, the ginseng of n-th layer RBM neural networks is randomly generated using normal distribution
Number initial value；
N is trained using the output node number of N-1 layers of RBM neural networks as the input number of nodes of n-th layer RBM neural networks
Layer neural network obtains n-th layer RBM nerve nets by adjusting the initial parameter value of the n-th layer RBM neural networks when training
The parameter of network, to obtain the parameter of each layer RBM neural networks, wherein N >=2.
6. the fraudulent trading recognition methods based on deep learning as claimed in claim 5, which is characterized in that each layer
RBM neural networks include visible layer and hidden layer, and the parameter of each layer of RBM neural network includes the visible layer and hides
Weight matrix between layer, in visible layer in the offset of visible node and hidden layer concealed nodes offset.
7. the fraudulent trading recognition methods based on deep learning as described in claim 1, which is characterized in that described by described
Dimensionality reduction device carries out dimensionality reduction to the training sample, and the step of binary condition vector obtained by dimensionality reduction is clustered is wrapped
It includes：
By the dimensionality reduction device, the training sample is mapped as binary condition vector；
Training sample with identical binary condition vector is classified as same group, so that the training sample is divided into several
Group.
8. the fraudulent trading recognition methods based on deep learning as described in claim 1, which is characterized in that described in the basis
Fraudulent trading detection model analyzes transaction data to be detected, and to identify fraudulent trading the step of includes：
By the transaction data to be detected, substitutes into the fraudulent trading detection model and carry out dimensionality reduction and cluster successively, waited for
Detection transaction group；
The corresponding probability of cheating of each transaction group to be detected is analyzed, need to aggravate to audit according to the determination of each probability of cheating of analysis
Transaction group to be detected, to identify fraudulent trading.
9. a kind of fraudulent trading identifying system based on deep learning, which is characterized in that the fraud based on deep learning is handed over
System easy to identify includes：Memory, processor and be stored on the memory and can run on the processor based on
The fraudulent trading recognizer of deep learning, the fraudulent trading recognizer based on deep learning are executed by the processor
Shi Shixian following steps：
Training sample is obtained, the training sample is the transaction data for establishing fraudulent trading detection model；
The RBM neural network structures stacked are built, and train the RBM neural network knots of the stacking based on the training sample
Structure generates dimensionality reduction device；
Dimensionality reduction is carried out to the training sample by the dimensionality reduction device, and the binary condition vector obtained by dimensionality reduction is gathered
Class, to establish fraudulent trading detection model；
Transaction data to be detected is obtained, and according to the fraudulent trading detection model, analyzes transaction data to be detected, to identify
Fraudulent trading.
10. a kind of storage medium, which is characterized in that be stored with the fraudulent trading identification based on deep learning on the storage medium
Program, the fraudulent trading recognizer based on deep learning realize following steps when being executed by processor：
Training sample is obtained, the training sample is the transaction data for establishing fraudulent trading detection model；
The RBM neural network structures stacked are built, and train the RBM neural network knots of the stacking based on the training sample
Structure generates dimensionality reduction device；
Dimensionality reduction is carried out to the training sample by the dimensionality reduction device, and the binary condition vector obtained by dimensionality reduction is gathered
Class, to establish fraudulent trading detection model；
Transaction data to be detected is obtained, and according to the fraudulent trading detection model, analyzes transaction data to be detected, to identify
Fraudulent trading.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810407275.5A CN108596630B (en) | 2018-04-28 | 2018-04-28 | Fraud transaction identification method, system and storage medium based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810407275.5A CN108596630B (en) | 2018-04-28 | 2018-04-28 | Fraud transaction identification method, system and storage medium based on deep learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108596630A true CN108596630A (en) | 2018-09-28 |
| CN108596630B CN108596630B (en) | 2022-03-01 |
Family
ID=63619471
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810407275.5A Active CN108596630B (en) | 2018-04-28 | 2018-04-28 | Fraud transaction identification method, system and storage medium based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108596630B (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109544163A (en) * | 2018-11-30 | 2019-03-29 | 华青融天(北京)软件股份有限公司 | A kind of risk control method, device, equipment and the medium of user's payment behavior |
| CN109784403A (en) * | 2019-01-16 | 2019-05-21 | 武汉斗鱼鱼乐网络科技有限公司 | A kind of method and relevant device identifying risk equipment |
| CN109858930A (en) * | 2019-01-24 | 2019-06-07 | 同济大学 | Online trading fraud detection method based on associated diagram spectrum representative learning |
| CN111275098A (en) * | 2020-01-17 | 2020-06-12 | 同济大学 | Encoder-LSTM deep learning model applied to credit card fraud detection and method thereof |
| CN111340509A (en) * | 2020-05-22 | 2020-06-26 | 支付宝(杭州)信息技术有限公司 | False transaction identification method and device and electronic equipment |
| CN111401393A (en) * | 2019-01-02 | 2020-07-10 | 中国移动通信有限公司研究院 | Data processing method and device, electronic equipment and storage medium |
| CN111415167A (en) * | 2020-02-19 | 2020-07-14 | 同济大学 | Network fraud transaction detection method and device, computer storage medium and terminal |
| CN111445259A (en) * | 2018-12-27 | 2020-07-24 | 中国移动通信集团辽宁有限公司 | Method, device, equipment and medium for determining business fraud behaviors |
| CN111507382A (en) * | 2020-04-01 | 2020-08-07 | 北京互金新融科技有限公司 | Sample file clustering method and device and electronic equipment |
| CN112330328A (en) * | 2019-08-05 | 2021-02-05 | 四川大学 | Credit card fraud detection method based on feature extraction |
| CN113052266A (en) * | 2021-04-27 | 2021-06-29 | 中国工商银行股份有限公司 | Transaction mode type identification method and device |
| CN113469695A (en) * | 2020-03-30 | 2021-10-01 | 同济大学 | Electronic fraud transaction identification method, system and device based on kernel supervision Hash model |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101894130A (en) * | 2010-06-08 | 2010-11-24 | 浙江大学 | Sparse dimension reduction-based spectral hash indexing method |
| US20140079297A1 (en) * | 2012-09-17 | 2014-03-20 | Saied Tadayon | Application of Z-Webs and Z-factors to Analytics, Search Engine, Learning, Recognition, Natural Language, and Other Utilities |
| US20150260840A1 (en) * | 2014-03-13 | 2015-09-17 | Kustom Signals, Inc. | Usb/wireless based traffic radar system |
| CN106033426A (en) * | 2015-03-11 | 2016-10-19 | 中国科学院西安光学精密机械研究所 | Image retrieval method based on latent semantic minimum hash |
| US20160378902A1 (en) * | 2015-06-25 | 2016-12-29 | Globalfoundries Inc. | Generative learning for realistic and ground rule clean hot spot synthesis |
| CN106779094A (en) * | 2017-01-13 | 2017-05-31 | 湖南文理学院 | A kind of limitation Boltzmann machine learning method and device based on random feedback |
| WO2017120370A1 (en) * | 2016-01-06 | 2017-07-13 | Kla-Tencor Corporation | Feature selection and automated process window monitoring through outlier detection |
| CN106997474A (en) * | 2016-12-29 | 2017-08-01 | 南京邮电大学 | A kind of node of graph multi-tag sorting technique based on deep learning |
| CN107044976A (en) * | 2017-05-10 | 2017-08-15 | 中国科学院合肥物质科学研究院 | Heavy metal content in soil analyzing and predicting method based on LIBS Yu stack RBM depth learning technologies |
| CN107679859A (en) * | 2017-07-18 | 2018-02-09 | 中国银联股份有限公司 | A kind of Risk Identification Method and system based on Transfer Depth study |
| CN107688201A (en) * | 2017-08-23 | 2018-02-13 | 电子科技大学 | Based on RBM earthquake prestack signal clustering methods |
-
2018
- 2018-04-28 CN CN201810407275.5A patent/CN108596630B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101894130A (en) * | 2010-06-08 | 2010-11-24 | 浙江大学 | Sparse dimension reduction-based spectral hash indexing method |
| US20140079297A1 (en) * | 2012-09-17 | 2014-03-20 | Saied Tadayon | Application of Z-Webs and Z-factors to Analytics, Search Engine, Learning, Recognition, Natural Language, and Other Utilities |
| US20150260840A1 (en) * | 2014-03-13 | 2015-09-17 | Kustom Signals, Inc. | Usb/wireless based traffic radar system |
| CN106033426A (en) * | 2015-03-11 | 2016-10-19 | 中国科学院西安光学精密机械研究所 | Image retrieval method based on latent semantic minimum hash |
| US20160378902A1 (en) * | 2015-06-25 | 2016-12-29 | Globalfoundries Inc. | Generative learning for realistic and ground rule clean hot spot synthesis |
| WO2017120370A1 (en) * | 2016-01-06 | 2017-07-13 | Kla-Tencor Corporation | Feature selection and automated process window monitoring through outlier detection |
| CN106997474A (en) * | 2016-12-29 | 2017-08-01 | 南京邮电大学 | A kind of node of graph multi-tag sorting technique based on deep learning |
| CN106779094A (en) * | 2017-01-13 | 2017-05-31 | 湖南文理学院 | A kind of limitation Boltzmann machine learning method and device based on random feedback |
| CN107044976A (en) * | 2017-05-10 | 2017-08-15 | 中国科学院合肥物质科学研究院 | Heavy metal content in soil analyzing and predicting method based on LIBS Yu stack RBM depth learning technologies |
| CN107679859A (en) * | 2017-07-18 | 2018-02-09 | 中国银联股份有限公司 | A kind of Risk Identification Method and system based on Transfer Depth study |
| CN107688201A (en) * | 2017-08-23 | 2018-02-13 | 电子科技大学 | Based on RBM earthquake prestack signal clustering methods |
Non-Patent Citations (4)
| Title |
|---|
| FAN SHEN 等: "Investment time series prediction using a hybrid model based on RBMs and pattern clustering", 《2017 IEEE/ACIS 16TH INTERNATIONAL CONFERENCE ON COMPUTER AND INFORMATION SCIENCE (ICIS)》 * |
| KE ZHANG 等: "An optimized dimensionality reduction model for high-dimensional data based on Restricted Boltzmann Machines", 《THE 27TH CHINESE CONTROL AND DECISION CONFERENCE (2015 CCDC)》 * |
| 丁卫星: "基于深度学习技术的信用卡交易欺诈侦测研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 陈曦: "基于高斯伯努利受限玻尔兹曼机的过程监测研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109544163A (en) * | 2018-11-30 | 2019-03-29 | 华青融天(北京)软件股份有限公司 | A kind of risk control method, device, equipment and the medium of user's payment behavior |
| CN111445259A (en) * | 2018-12-27 | 2020-07-24 | 中国移动通信集团辽宁有限公司 | Method, device, equipment and medium for determining business fraud behaviors |
| CN111401393A (en) * | 2019-01-02 | 2020-07-10 | 中国移动通信有限公司研究院 | Data processing method and device, electronic equipment and storage medium |
| CN111401393B (en) * | 2019-01-02 | 2023-04-07 | 中国移动通信有限公司研究院 | Data processing method and device, electronic equipment and storage medium |
| CN109784403A (en) * | 2019-01-16 | 2019-05-21 | 武汉斗鱼鱼乐网络科技有限公司 | A kind of method and relevant device identifying risk equipment |
| CN109858930A (en) * | 2019-01-24 | 2019-06-07 | 同济大学 | Online trading fraud detection method based on associated diagram spectrum representative learning |
| CN109858930B (en) * | 2019-01-24 | 2023-06-09 | 同济大学 | Online transaction fraud detection method based on association graph characterization learning |
| CN112330328A (en) * | 2019-08-05 | 2021-02-05 | 四川大学 | Credit card fraud detection method based on feature extraction |
| CN111275098A (en) * | 2020-01-17 | 2020-06-12 | 同济大学 | Encoder-LSTM deep learning model applied to credit card fraud detection and method thereof |
| CN111415167A (en) * | 2020-02-19 | 2020-07-14 | 同济大学 | Network fraud transaction detection method and device, computer storage medium and terminal |
| CN113469695A (en) * | 2020-03-30 | 2021-10-01 | 同济大学 | Electronic fraud transaction identification method, system and device based on kernel supervision Hash model |
| CN113469695B (en) * | 2020-03-30 | 2023-06-30 | 同济大学 | Electronic fraud transaction identification method, system and device based on kernel supervision hash model |
| CN111507382A (en) * | 2020-04-01 | 2020-08-07 | 北京互金新融科技有限公司 | Sample file clustering method and device and electronic equipment |
| CN111507382B (en) * | 2020-04-01 | 2023-05-05 | 北京互金新融科技有限公司 | Sample file clustering method and device and electronic equipment |
| CN111340509B (en) * | 2020-05-22 | 2020-08-21 | 支付宝(杭州)信息技术有限公司 | False transaction identification method and device and electronic equipment |
| CN111340509A (en) * | 2020-05-22 | 2020-06-26 | 支付宝(杭州)信息技术有限公司 | False transaction identification method and device and electronic equipment |
| CN113052266A (en) * | 2021-04-27 | 2021-06-29 | 中国工商银行股份有限公司 | Transaction mode type identification method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108596630B (en) | 2022-03-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108596630A (en) | Fraudulent trading recognition methods, system and storage medium based on deep learning | |
| CN108629593A (en) | Fraudulent trading recognition methods, system and storage medium based on deep learning | |
| CN108351985A (en) | Method and apparatus for large-scale machines study | |
| CN112700325A (en) | Method for predicting online credit return customers based on Stacking ensemble learning | |
| CN108717663A (en) | Face label fraud judgment method, device, equipment and medium based on micro- expression | |
| CN112927072B (en) | Block chain-based money back-flushing arbitration method, system and related device | |
| CN108304853A (en) | Acquisition methods, device, storage medium and the electronic device for the degree of correlation of playing | |
| CN114238659B (en) | Method for intelligently designing network security architecture diagram | |
| US12079825B2 (en) | Automated learning of models for domain theories | |
| CN114912510B (en) | Online investigation sample quality evaluation system | |
| Abdou et al. | Credit scoring and decision making in Egyptian public sector banks | |
| CN113724061A (en) | Consumer financial product credit scoring method and device based on customer grouping | |
| US20200394711A1 (en) | Predicting market actions, directions of actions and engagement via behavioral iq analysis | |
| Ramalingam et al. | Efficient Player Prediction and Suggestion using Machine Learning for IPL Tournament | |
| CN112488821A (en) | Consumption credit scene fraud detection method based on ABC-SOM neural network | |
| CN112926989B (en) | Bank loan risk assessment method and equipment based on multi-view integrated learning | |
| CN115293783A (en) | Risk user identification method and device, computer equipment and storage medium | |
| CN115496364A (en) | Method and device for identifying heterogeneous enterprises, storage medium and electronic equipment | |
| KR100727555B1 (en) | Creating method for decision tree using time-weighted entropy and recording medium thereof | |
| CN115130619A (en) | Risk control method based on clustering selection integration | |
| CN116451050A (en) | Abnormal behavior recognition model training and abnormal behavior recognition method and device | |
| CN114418604A (en) | Method and device for predicting survival promotion success probability of palm silver easy-to-lose customers and storage medium | |
| CN112418307B (en) | Radiation source individual identification method combining deep learning and integrated learning | |
| CN116563067B (en) | Big data-based graduate crowd employment analysis method, system and medium | |
| CN113256368B (en) | Product pushing method and device, computer equipment and storage medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |