CN111429257B - Transaction monitoring method and device - Google Patents
Transaction monitoring method and device Download PDFInfo
- Publication number
- CN111429257B CN111429257B CN202010196646.7A CN202010196646A CN111429257B CN 111429257 B CN111429257 B CN 111429257B CN 202010196646 A CN202010196646 A CN 202010196646A CN 111429257 B CN111429257 B CN 111429257B
- Authority
- CN
- China
- Prior art keywords
- feature data
- business feature
- business
- service
- early warning
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000012544 monitoring process Methods 0.000 title claims abstract description 24
- 238000012806 monitoring device Methods 0.000 claims abstract description 8
- 238000007637 random forest analysis Methods 0.000 claims description 48
- 238000012549 training Methods 0.000 claims description 20
- 238000012546 transfer Methods 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 14
- 238000012795 verification Methods 0.000 claims description 12
- 238000003860 storage Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 8
- 238000012216 screening Methods 0.000 claims description 5
- 238000010200 validation analysis Methods 0.000 claims description 3
- 230000002776 aggregation Effects 0.000 abstract description 6
- 238000004220 aggregation Methods 0.000 abstract description 6
- 230000002159 abnormal effect Effects 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 15
- 230000008569 process Effects 0.000 description 9
- 238000003066 decision tree Methods 0.000 description 8
- 238000004891 communication Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 230000006399 behavior Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000835 fiber Substances 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 241000876446 Lanthanotidae Species 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- 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
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention discloses a transaction monitoring method and a transaction monitoring device, and relates to the technical field of computers. One embodiment of the method includes obtaining loan account information to generate a plurality of single business feature data; selecting single business feature data with associated attribute marks from a plurality of single business feature data, and calling the associated business feature data through the single business feature data to generate combined business feature data; and inputting the single service characteristic data and the combined service characteristic data without the associated attribute marks into a preset aggregation early warning model to determine the early warning level of the loan account, and executing a corresponding wind control program based on the early warning level. Therefore, the embodiment of the invention can solve the problems of difficult monitoring and low efficiency of the existing abnormal loan fund collection.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a transaction monitoring method and apparatus.
Background
In recent years, the demand for consumed credit in China is gradually increased, and each large bank issues consumed loans for individual clients. With the rising demand and increasing volume of personal consumer loans, banks have also created a need for monitoring and early warning of consumer loans. Currently, there are some situations of using consumed loans in a violation in the market, for example, some customers may collect funds of consumed loans, that is, multiple accounts pay the loans and transfer the funds to the same account, and in the subsequent course, the act of putting the loans into the securities market or building and other violation uses occurs. Therefore, the monitoring of the collection phenomenon of loan funds has important significance for the normal recovery of loan funds and management of risks. Meanwhile, by combining the big data technology with the business knowledge of the bank, the information is mined from the massive loans, the suspicious point loans which are difficult to identify by manual analysis are found, and the risk management cost of the bank is reduced.
In the process of implementing the present invention, the inventor finds that at least the following problems exist in the prior art:
currently, early warning methods for loan fund collection anomalies include expert rule-based methods, learning-based methods, graph model-based methods, and the like. However, the expert rule-based method is easy to generate a miss judgment situation because the rule is fixed, and the combination with the data is loose. The learning-based method is often too sensitive, so that the loan misjudgment rate is high and the usability is low. The method based on the graph model is complex in theory, some models need to recalculate the full loan after adding a new loan, and the application in production has larger limit, and meanwhile, the accuracy of the judging result is difficult to grasp because the method is an unsupervised method.
Disclosure of Invention
In view of the above, the embodiment of the invention provides a transaction monitoring method and device, which can solve the problems of difficult monitoring and low efficiency of the existing abnormal collection of loan funds.
To achieve the above object, according to one aspect of the embodiments of the present invention, there is provided a transaction monitoring method including acquiring loan account information to generate a plurality of single business feature data; selecting single business feature data with associated attribute marks from a plurality of single business feature data, and calling the associated business feature data through the single business feature data to generate combined business feature data; and inputting the single service characteristic data and the combined service characteristic data without the associated attribute marks into a preset aggregation early warning model to determine the early warning level of the loan account, and executing a corresponding wind control program based on the early warning level.
Optionally, obtaining loan account information to generate a plurality of single business feature data, comprising:
and obtaining loan account information, and selecting single business feature data based on the target attribute according to the loan flow data.
Optionally, generating the combined service feature data includes:
acquiring first single service characteristic data with associated attribute marks, and determining that the first single service characteristic data is larger than a preset first early warning threshold value;
and calling transaction flow of the associated service feature data in a preset time period through the first single service feature data, judging whether a transfer transaction with a preset value exists, generating combined service feature data based on the first single service feature data and the associated service feature data if the transfer transaction with the preset value exists, and deleting the associated attribute mark of the first single service feature data if the transfer transaction with the preset value does not exist.
Optionally, generating the combined service feature data includes:
acquiring second single business feature data with associated attribute marks, and calling all the associated business feature data through the second single business feature data;
judging whether the quantity of the associated service feature data of the second single service feature data is larger than a preset second early warning threshold value, if so, generating combined service feature data based on the second single service feature data and the associated service feature data, and if not, deleting the associated attribute mark of the second single service feature data.
Optionally, the method comprises:
and inputting the single service characteristic data and the combined service characteristic data without the associated attribute marks into a preset clustering early warning model, wherein the clustering early warning model adopts a random forest model.
Optionally, the method further comprises:
and when training the random forest model, inputting the single service feature data and the combined service feature data without the associated attribute marks into the random forest model until the accuracy of the random forest model in the verification set is determined to be larger than a preset accuracy threshold.
Optionally, determining the random forest model after the accuracy of the verification set is greater than a preset accuracy threshold includes:
and circularly executing and deriving importance values of each business feature data in the random forest model, screening out part of business feature data, and inputting the business feature data serving as new business feature data into the random forest model for training until the accuracy of the random forest model in the verification set is not improved.
In addition, the invention also provides a transaction monitoring device, which comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring loan account information so as to generate a plurality of single business characteristic data; selecting single business feature data with associated attribute marks from a plurality of single business feature data, and calling the associated business feature data through the single business feature data to generate combined business feature data; and the processing module is used for inputting the single service characteristic data and the combined service characteristic data without the associated attribute marks into a preset aggregation early warning model so as to determine the early warning level of the loan account, and executing a corresponding wind control program based on the early warning level.
One embodiment of the above invention has the following advantages or benefits: because the loan account information is acquired to generate a plurality of single business feature data; selecting single business feature data with associated attribute marks from a plurality of single business feature data, and calling the associated business feature data through the single business feature data to generate combined business feature data; the single business feature data and the combined business feature data without the associated attribute mark are input into a preset collection early warning model to determine the early warning level of the loan account, and the corresponding wind control program is executed based on the early warning level, so that the technical problems of difficult monitoring and low efficiency of the existing collection abnormality of loan funds are overcome.
Further effects of the above-described non-conventional alternatives are described below in connection with the embodiments.
Drawings
The drawings are included to provide a better understanding of the invention and are not to be construed as unduly limiting the invention. Wherein:
FIG. 1 is a schematic diagram of the main flow of a transaction monitoring method according to a first embodiment of the present invention;
FIG. 2 is a schematic diagram of the main flow of a transaction monitoring method according to a second embodiment of the present invention;
FIG. 3 is a schematic diagram of a main flow of constructing an identification model according to a third embodiment of the present invention;
FIG. 4 is a schematic diagram of the major modules of a transaction monitoring device according to an embodiment of the present invention;
FIG. 5 is an exemplary system architecture diagram in which embodiments of the present invention may be applied;
fig. 6 is a schematic diagram of a computer system suitable for use in implementing an embodiment of the invention.
Detailed Description
Exemplary embodiments of the present invention will now be described with reference to the accompanying drawings, in which various details of the embodiments of the present invention are included to facilitate understanding, and are to be considered merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Fig. 1 is a schematic diagram of the main flow of a transaction monitoring method according to a first embodiment of the present invention, and as shown in fig. 1, the transaction monitoring method includes:
step S101, obtaining loan account information to generate a plurality of single business feature data.
In some embodiments, the invention can monitor the fund collection, i.e. monitor abnormal collection behaviors, for e.g. financial express business to realize early warning and wind control treatment. The fast loan refers to self-service loan on a whole flow line of a personal client, and the client can finish the loan on line through an electronic channel, including real-time application, batch loan, subscription, payment and repayment.
In a preferred embodiment, during the generation of the plurality of single business feature data, loan account information may be obtained, based on the loan aggregate data, to select the single business feature data based on the target attribute. For example: single business feature data such as a payment amount, a payment frequency, a transaction account, and loan borrower identity information (age, occupation, etc.) is selected from the loan aggregate data based on the target attribute.
Step S102, selecting single business feature data with associated attribute marks from a plurality of single business feature data, and calling the associated business feature data through the single business feature data to generate combined business feature data.
In some embodiments, when generating the combined service feature data, first single service feature data with the associated attribute flag may be acquired, and it is determined that the first single service feature data is greater than a preset first early warning threshold; and calling transaction flow of the associated service feature data in a preset time period through the first single service feature data, judging whether a transfer transaction with a preset value exists, generating combined service feature data based on the first single service feature data and the associated service feature data if the transfer transaction with the preset value exists, and deleting the associated attribute mark of the first single service feature data if the transfer transaction with the preset value does not exist. The first single business feature data is a feature with numerical value attribute, and can be limited directly through a threshold value.
For example: and after the first single business characteristic data is the branch amount, calling the branch amount of the partner account of the related business characteristic data, judging whether the branch amount of the first single business characteristic data is 0.9-1.1 times of the transfer transaction in the transaction running water within 3 days, if so, generating combined business characteristic data by the branch amount and the branch amount of the partner account, otherwise, deleting the related attribute mark of the first single business characteristic data.
In other embodiments, when generating the combined service feature data, obtaining second single service feature data with associated attribute tags, and invoking all the associated service feature data through the second single service feature data; judging whether the quantity of the associated service feature data of the second single service feature data is larger than a preset second early warning threshold value, if so, generating combined service feature data based on the second single service feature data and the associated service feature data, and if not, deleting the associated attribute mark of the second single service feature data. The second single business feature data is a feature with a non-numerical attribute, and can reflect the commonality of a plurality of loans, such as an account of a trade opponent and the like, and set a threshold value to limit the number of loans with the commonality.
For example: the second single business feature data is a transaction receipt account, the number of times that the transaction receipt account is the same account is obtained, if the number of times is more than 3, the transaction receipt account and other loan account information taking the transaction receipt account as the transaction receipt account generate combined business feature data, otherwise, the associated attribute mark of the second single business feature data is deleted.
It should be noted that, the present invention may acquire the first single service feature data or the second single service feature data with the associated attribute flag, respectively, to generate the combined service feature data. The first single business feature data and the second single business feature data with the associated attribute marks can be acquired simultaneously to generate combined business feature data.
And step S103, inputting the single service characteristic data and the combined service characteristic data without the associated attribute marks into a preset aggregation early warning model to determine the early warning level of the loan account, and executing a corresponding wind control program based on the early warning level.
In some embodiments, the preset collection early warning model may be a random forest model, a decision tree, or the like, and the preferred embodiment of the present invention uses a random forest model. The random forest model may include a plurality of single decision trees as sub-classifiers, and after single service feature data and combined service feature data are input, each decision tree uses a random subset of the total samples as training samples, so that different decision trees can obtain parameters of different models after training. Then, when a new sample is put into the classifier, each sub-model obtains respective prediction, and votes on the prediction results, so that the prediction results of the random forest model on the new sample as a whole and the prediction probability of each type of result can be obtained.
Therefore, when the random forest model is trained, on one hand, classification of whether loan funds are collected or not can be realized, and on the other hand, the importance (namely, importance value) of each input business feature data can be obtained in training. In the decision tree, each branch point takes certain service characteristic data as a judging condition, and the branch point is taken as a greedy algorithm, and if the certain service characteristic data is selected as a branch condition earlier, the influence of the service characteristic data on classification is larger. Based on this, the importance of the business feature data for classification can be judged by the order in which the business feature data is selected as the branching points. On the other hand, the judgment of a single decision tree always results in the generation of certain errors. Thanks to the inclusion of multiple decision trees in the random forest, the error in the decision on the importance (i.e., importance value) of the business feature data can be reduced by averaging the sub-models (i.e., each decision tree contained internally). After the importance of the service feature data is obtained, the service feature data can be further screened according to the importance of the service feature data, so that the service feature data of the random forest model is refined, the training cost of the random forest model can be further improved, and the training time is saved.
As a specific example, when training the random forest model, the selected data is historical loan account information data of the fast loan business, and whether the loan is subjected to the gathering behavior is used as a label of the loan. According to the distribution of the whole historical loan account information data set, 60%,20% and 20% of data are respectively selected as a training set, a testing set and a verification set.
In a preferred embodiment, training the random forest model may input the single business feature data and the combined business feature data without the associated attribute markers into the random forest model until it is determined that the accuracy of the random forest model in the verification set is greater than a preset accuracy threshold.
Further, after determining that the accuracy of the random forest model in the verification set is greater than a preset accuracy threshold, circularly executing and deriving importance numerical values of each business feature data in the random forest model, screening out part of business feature data, and inputting the business feature data as new business feature data into the random forest model for training until the accuracy of the random forest model in the verification set is not improved. That is, single business feature data and combined business feature data of the historical loan account information data without the associated attribute marks are put into a random forest model for training, when the accuracy of the random forest model in a verification set exceeds a set threshold, importance values of each business feature data are derived from the random forest model, partial features are screened out according to the importance values, and the single business feature data and the combined business feature data are put into the random forest model as new business feature data for training. And repeating the process until the accuracy of the random forest model in the verification set is not improved.
It is also worth to say that the early warning level of the loan account can be obtained through a preset collection early warning model, and the corresponding wind control program is provided according to different early warning levels. For example: the early warning level is provided with: A. b, C, corresponding wind control program: the upper level of the management of the air control (namely, each business process on the loan account needs to send a request to the upper level of the air control process), limit the loan amount and the year, and prohibit the loan. The early warning level and the corresponding wind control program can be configured according to actual service requirements.
Fig. 2 is a schematic diagram of the main flow of a transaction monitoring method according to a second embodiment of the present invention, and as shown in fig. 2, the transaction monitoring method includes:
in step S201, loan account information is acquired to generate a plurality of single business feature data.
Step S202, selecting a first single business feature data with an associated attribute mark from a plurality of single business feature data.
Step S203, judging whether the first single business feature data is larger than a preset first early warning threshold, if yes, proceeding to step S204, otherwise proceeding to step S207.
Step S204, the transaction flow of the associated business feature data in the preset time period is invoked through the first single business feature data.
Step S205, judging whether a preset value transfer-out transaction exists, if yes, proceeding to step S206, otherwise proceeding to step S207.
Step S206, generating combined business feature data based on the first single business feature data and the associated business feature data, and proceeding to step S208.
Step S207, deleting the associated attribute mark of the first single business feature data, and proceeding to step S208.
And step S208, inputting the single service characteristic data and the combined service characteristic data without the associated attribute marks into a preset aggregation early warning model to determine the early warning level of the loan account, and executing a corresponding wind control program based on the early warning level.
FIG. 3 is a schematic diagram of a main process of constructing an identification model according to a third embodiment of the present invention, and as shown in FIG. 3, the transaction monitoring method includes:
in step S301, loan account information is acquired to generate a plurality of single business feature data.
Step S302, selecting second single business characteristic data with associated attribute marks from the plurality of single business characteristic data.
Step S303, all the associated service feature data are called through the second single service feature data.
Step S304, judging whether the number of the associated business feature data of the second single business feature data is larger than a preset second early warning threshold, if yes, proceeding to step S305, otherwise proceeding to step S306.
Step S305, generating combined service feature data based on the second single service feature data and the associated service feature data, and performing step S307.
Step S306, deleting the associated attribute mark of the second single business feature data, and proceeding to step S307.
Step S307, single business feature data and combined business feature data without associated attribute marks are input into a preset collection early warning model to determine the early warning level of the loan account, and corresponding wind control programs are executed based on the early warning level.
In summary, the transaction monitoring method provided by the invention creatively uses a random forest method and integrates business comprehensive characteristics to judge whether the consumed loan has a gathering behavior, so that the detection and early warning of the loan are more efficient. When the model features are selected, specific business features are converted into labels or quantity features on the basis of basic features such as accounts, running transactions and the like, and the labels or quantity features are used as important features of model training, such as money matching features of self and partner accounts after loan is used, transaction associated features such as transaction frequency of the same account and the like. Meanwhile, in the training process of random forests, the influence of each feature on the collection behavior judgment is obtained from the feature importance and the feature refinement is carried out by obtaining the feature importance and carrying out threshold screening in each iteration model, so that the training and the prediction of the model are accelerated, and in the actual operation, more definite indication guidance can be provided for judging whether the fund collection occurs in the business judgment express credit. In addition, the invention can tightly combine the model and the data, and compared with a single manual rule, the invention can improve the judgment accuracy to a certain extent, can improve the judgment efficiency and save the labor cost.
Fig. 4 is a schematic diagram of main modules of a transaction monitoring device according to an embodiment of the present invention, and as shown in fig. 4, the transaction monitoring device 400 includes an acquisition module 401 and a processing module 402. Wherein, the obtaining module 401 obtains loan account information to generate a plurality of single business feature data; selecting single business feature data with associated attribute marks from a plurality of single business feature data, and calling the associated business feature data through the single business feature data to generate combined business feature data; the processing module 402 inputs the single service feature data and the combined service feature data without the associated attribute tags into a preset aggregate early warning model to determine the loan account early warning level, and executes a corresponding wind control program based on the early warning level.
In some embodiments, the obtaining module 401 obtains loan account information to generate a plurality of single business feature data, including obtaining the loan account information, based on the loan aggregate data to select the single business feature data based on the target attribute.
In some embodiments, the obtaining module 401 generates the combined business feature data, including:
acquiring first single service characteristic data with associated attribute marks, and determining that the first single service characteristic data is larger than a preset first early warning threshold value; and calling transaction flow of the associated service feature data in a preset time period through the first single service feature data, judging whether a transfer transaction with a preset value exists, generating combined service feature data based on the first single service feature data and the associated service feature data if the transfer transaction with the preset value exists, and deleting the associated attribute mark of the first single service feature data if the transfer transaction with the preset value does not exist.
In some embodiments, the obtaining module 401 generates the combined business feature data, including:
acquiring second single business feature data with associated attribute marks, and calling all the associated business feature data through the second single business feature data; judging whether the quantity of the associated service feature data of the second single service feature data is larger than a preset second early warning threshold value, if so, generating combined service feature data based on the second single service feature data and the associated service feature data, and if not, deleting the associated attribute mark of the second single service feature data.
In some embodiments, the processing module 402 inputs the single business feature data and the combined business feature data without associated attribute tags into a preset clustering early warning model, wherein the clustering early warning model employs a random forest model.
In some embodiments, the processing module 402, while training the random forest model, inputs the single business feature data and the combined business feature data without the associated attribute tags into the random forest model until it is determined that the accuracy of the random forest model in the validation set is greater than a preset accuracy threshold.
In some embodiments, the processing module 402 determines that the random forest model includes, after the accuracy of the validation set is greater than a preset accuracy threshold:
and circularly executing and deriving importance values of each business feature data in the random forest model, screening out part of business feature data, and inputting the business feature data serving as new business feature data into the random forest model for training until the accuracy of the random forest model in the verification set is not improved.
It should be noted that, in the transaction monitoring method and the transaction monitoring device of the present invention, there is a corresponding relationship between the implementation contents, so the repeated contents will not be described.
Fig. 5 illustrates an exemplary system architecture 500 in which a transaction monitoring method or transaction monitoring device of embodiments of the present invention may be applied.
As shown in fig. 5, the system architecture 500 may include terminal devices 501, 502, 503, a network 504, and a server 505. The network 504 is used as a medium to provide communication links between the terminal devices 501, 502, 503 and the server 505. The network 504 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.
A user may interact with the server 505 via the network 504 using the terminal devices 501, 502, 503 to receive or send messages or the like. Various communication client applications may be installed on the terminal devices 501, 502, 503, such as shopping class applications, web browser applications, search class applications, instant messaging tools, mailbox clients, social platform software, etc. (by way of example only).
The terminal devices 501, 502, 503 may be a variety of electronic devices having transaction monitor screens and supporting web browsing, including but not limited to smartphones, tablets, laptop and desktop computers, and the like.
The server 505 may be a server providing various services, such as a background management server (by way of example only) providing support for shopping-type websites browsed by users using the terminal devices 501, 502, 503. The background management server may analyze and process the received data such as the product information query request, and feedback the processing result (e.g., the target push information, the product information—only an example) to the terminal device.
It should be noted that the transaction monitoring method provided by the embodiment of the present invention is generally executed by the server 505, and accordingly, the computing device is generally disposed in the server 505.
It should be understood that the number of terminal devices, networks and servers in fig. 5 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
Referring now to FIG. 6, there is illustrated a schematic diagram of a computer system 600 suitable for use in implementing an embodiment of the present invention. The terminal device shown in fig. 6 is only an example, and should not impose any limitation on the functions and the scope of use of the embodiment of the present invention.
As shown in fig. 6, the computer system 600 includes a Central Processing Unit (CPU) 601, which can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 602 or a program loaded from a storage section 808 into a Random Access Memory (RAM) 603. In the RAM603, various programs and data required for the operation of the computer system 600 are also stored. The CPU601, ROM602, and RAM603 are connected to each other through a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
The following components are connected to the I/O interface 605: an input portion 606 including a keyboard, mouse, etc.; an output portion 607 including a Cathode Ray Tube (CRT), a liquid crystal transaction monitor (LCD), and the like, and a speaker, and the like; a storage section 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The drive 610 is also connected to the I/O interface 605 as needed. Removable media 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is installed as needed on drive 610 so that a computer program read therefrom is installed as needed into storage section 608.
In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication section 809, and/or installed from the removable media 811. The above-described functions defined in the system of the present invention are performed when the computer program is executed by a Central Processing Unit (CPU) 801.
The computer readable medium shown in the present invention may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present invention, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules involved in the embodiments of the present invention may be implemented in software or in hardware. The described modules may also be provided in a processor, for example, as: a processor includes an acquisition module and a processing module. The names of these modules do not constitute a limitation on the module itself in some cases.
As another aspect, the present invention also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be present alone without being fitted into the device. The computer readable medium carrying one or more programs which, when executed by a device, cause the device to include obtaining loan account information to generate a plurality of single business feature data; selecting single business feature data with associated attribute marks from a plurality of single business feature data, and calling the associated business feature data through the single business feature data to generate combined business feature data; and inputting the single service characteristic data and the combined service characteristic data without the associated attribute marks into a preset aggregation early warning model to determine the early warning level of the loan account, and executing a corresponding wind control program based on the early warning level.
According to the technical scheme provided by the embodiment of the invention, the problems of difficult monitoring and low efficiency of the existing loan fund collection abnormality can be solved.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives can occur depending upon design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Claims (7)
1. A method of transaction monitoring, comprising:
acquiring loan account information to generate a plurality of single business feature data;
selecting single business feature data with associated attribute marks from a plurality of single business feature data, and calling the associated business feature data corresponding to the single business feature data through the single business feature data to generate combined business feature data, wherein the method comprises the following steps of: acquiring first single service characteristic data with associated attribute marks, and determining that the first single service characteristic data is larger than a preset first early warning threshold value; calling transaction flow of associated service feature data corresponding to the first single service feature data in a preset time period through the first single service feature data, judging whether a transfer transaction of a preset value exists, generating combined service feature data based on the first single service feature data and the corresponding associated service feature data if the transfer transaction of the preset value exists, and deleting an associated attribute mark of the first single service feature data if the transfer transaction of the preset value does not exist; meanwhile, second single business feature data with an associated attribute mark is obtained, and all associated business feature data corresponding to the second single business feature data are called through the second single business feature data; judging whether the quantity of the associated service feature data corresponding to the second single service feature data is larger than a preset second early warning threshold value, if so, generating combined service feature data based on the second single service feature data and the corresponding associated service feature data, and if not, deleting the associated attribute mark of the second single service feature data; the first single business feature data is a feature with numerical value attribute, and the second single business feature data is a feature with non-numerical value attribute and is used for reflecting the commonality of a plurality of loans;
and inputting the single business feature data and the combined business feature data without the associated attribute marks into a preset fund collection early warning model adopting a random forest model so as to determine the early warning level of the loan account, and executing a corresponding wind control program based on the early warning level.
2. The method of claim 1, wherein obtaining loan account information to generate a plurality of single business feature data comprises:
and obtaining loan account information, and selecting single business feature data based on the target attribute according to the loan flow data.
3. The method as recited in claim 1, further comprising:
and when training the random forest model, inputting the single service feature data and the combined service feature data without the associated attribute marks into the random forest model until the accuracy of the random forest model in the verification set is determined to be larger than a preset accuracy threshold.
4. A method according to claim 3, wherein determining the random forest model after the accuracy of the validation set is greater than a preset accuracy threshold comprises:
and circularly executing and deriving importance values of each business feature data in the random forest model, screening out part of business feature data, and inputting the business feature data serving as new business feature data into the random forest model for training until the accuracy of the random forest model in the verification set is not improved.
5. A transaction monitoring device, comprising:
the acquisition module is used for acquiring loan account information to generate a plurality of single business feature data; selecting single business feature data with associated attribute marks from a plurality of single business feature data, and calling the associated business feature data corresponding to the single business feature data through the single business feature data to generate combined business feature data, wherein the method comprises the following steps of: acquiring first single service characteristic data with associated attribute marks, and determining that the first single service characteristic data is larger than a preset first early warning threshold value; calling transaction flow of associated service feature data corresponding to the first single service feature data in a preset time period through the first single service feature data, judging whether a transfer transaction of a preset value exists, generating combined service feature data based on the first single service feature data and the corresponding associated service feature data if the transfer transaction of the preset value exists, and deleting an associated attribute mark of the first single service feature data if the transfer transaction of the preset value does not exist; meanwhile, second single business feature data with an associated attribute mark is obtained, and all associated business feature data corresponding to the second single business feature data are called through the second single business feature data; judging whether the quantity of the associated service feature data corresponding to the second single service feature data is larger than a preset second early warning threshold value, if so, generating combined service feature data based on the second single service feature data and the corresponding associated service feature data, and if not, deleting the associated attribute mark of the second single service feature data; the first single business feature data is a feature with numerical value attribute, and the second single business feature data is a feature with non-numerical value attribute and is used for reflecting the commonality of a plurality of loans;
and the processing module is used for inputting the single service characteristic data and the combined service characteristic data without the associated attribute marks into a preset fund collection early warning model adopting a random forest model so as to determine the early warning level of the loan account, and executing a corresponding wind control program based on the early warning level.
6. An electronic device, comprising:
one or more processors;
storage means for storing one or more programs,
when executed by the one or more processors, causes the one or more processors to implement the method of any of claims 1-4.
7. A computer readable medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method according to any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010196646.7A CN111429257B (en) | 2020-03-19 | 2020-03-19 | Transaction monitoring method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010196646.7A CN111429257B (en) | 2020-03-19 | 2020-03-19 | Transaction monitoring method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111429257A CN111429257A (en) | 2020-07-17 |
| CN111429257B true CN111429257B (en) | 2024-04-12 |
Family
ID=71548146
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010196646.7A Active CN111429257B (en) | 2020-03-19 | 2020-03-19 | Transaction monitoring method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111429257B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113765868B (en) * | 2020-08-17 | 2023-08-08 | 北京沃东天骏信息技术有限公司 | Service processing method and device |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105225151A (en) * | 2015-11-10 | 2016-01-06 | 中国建设银行股份有限公司 | A kind of bank lending risks method for early warning and device |
| CN108122163A (en) * | 2017-11-14 | 2018-06-05 | 阿里巴巴集团控股有限公司 | Risk monitoring and control method, apparatus and equipment based on internet credit |
| CN109949152A (en) * | 2019-04-15 | 2019-06-28 | 武汉理工大学 | A kind of personal credit's violation correction method |
| CN110163741A (en) * | 2019-04-16 | 2019-08-23 | 深圳壹账通智能科技有限公司 | Credit decisions method, apparatus, equipment and medium based on credit air control model |
| CN110223164A (en) * | 2019-06-10 | 2019-09-10 | 卓尔智联(武汉)研究院有限公司 | Air control method and system based on transfer learning, computer installation, storage medium |
| CN110334737A (en) * | 2019-06-04 | 2019-10-15 | 阿里巴巴集团控股有限公司 | A kind of method and system of the customer risk index screening based on random forest |
| CN110659800A (en) * | 2019-08-15 | 2020-01-07 | 平安科技（深圳）有限公司 | Risk monitoring processing method and device, computer equipment and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110309840B (en) * | 2018-03-27 | 2023-08-11 | 创新先进技术有限公司 | Risk transaction identification method, risk transaction identification device, server and storage medium |
-
2020
- 2020-03-19 CN CN202010196646.7A patent/CN111429257B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105225151A (en) * | 2015-11-10 | 2016-01-06 | 中国建设银行股份有限公司 | A kind of bank lending risks method for early warning and device |
| CN108122163A (en) * | 2017-11-14 | 2018-06-05 | 阿里巴巴集团控股有限公司 | Risk monitoring and control method, apparatus and equipment based on internet credit |
| CN109949152A (en) * | 2019-04-15 | 2019-06-28 | 武汉理工大学 | A kind of personal credit's violation correction method |
| CN110163741A (en) * | 2019-04-16 | 2019-08-23 | 深圳壹账通智能科技有限公司 | Credit decisions method, apparatus, equipment and medium based on credit air control model |
| CN110334737A (en) * | 2019-06-04 | 2019-10-15 | 阿里巴巴集团控股有限公司 | A kind of method and system of the customer risk index screening based on random forest |
| CN110223164A (en) * | 2019-06-10 | 2019-09-10 | 卓尔智联(武汉)研究院有限公司 | Air control method and system based on transfer learning, computer installation, storage medium |
| CN110659800A (en) * | 2019-08-15 | 2020-01-07 | 平安科技（深圳）有限公司 | Risk monitoring processing method and device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111429257A (en) | 2020-07-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112184154A (en) | Business approval method and device | |
| CN111127178A (en) | Data processing method and device, storage medium and electronic equipment | |
| CN112613978B (en) | Bank capital sufficiency prediction method and device, electronic equipment and medium | |
| CN114186626A (en) | Abnormity detection method and device, electronic equipment and computer readable medium | |
| CN113313279A (en) | Document auditing method and device | |
| CN111179051A (en) | Financial target customer determination method and device and electronic equipment | |
| CN112990311A (en) | Method and device for identifying admitted client | |
| CN111429257B (en) | Transaction monitoring method and device | |
| CN117911159A (en) | Real-time data processing method, device, equipment, storage medium and program product | |
| CN117934154A (en) | Transaction risk prediction method, model training method, device, equipment, medium and program product | |
| WO2019095569A1 (en) | Financial analysis method based on financial and economic event on microblog, application server, and computer readable storage medium | |
| CN116664306A (en) | Intelligent recommendation method and device for wind control rules, electronic equipment and medium | |
| CN116228429A (en) | Method and device for detecting transaction data | |
| CN112734352A (en) | Document auditing method and device based on data dimensionality | |
| CN115795345A (en) | Information processing method, device, equipment and storage medium | |
| CN116703555A (en) | Early warning method, early warning device, electronic equipment and computer readable medium | |
| CN115994819A (en) | Risk customer identification method, apparatus, device and medium | |
| CN115482094A (en) | Service processing method and device, electronic equipment and computer readable medium | |
| CN114066513A (en) | User classification method and device | |
| CN114239985A (en) | Exchange rate prediction method and device, electronic equipment and storage medium | |
| CN114187081A (en) | Estimated value table processing method and device, electronic equipment and computer readable storage medium | |
| CN111046894B (en) | Method and device for identifying waistcoat account number | |
| CN112434083A (en) | Event processing method and device based on big data | |
| CN113052509A (en) | Model evaluation method, model evaluation apparatus, electronic device, and storage medium | |
| CN112907362A (en) | Loan transaction processing method and device, electronic 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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220921 Address after: 25 Financial Street, Xicheng District, Beijing 100033 Applicant after: CHINA CONSTRUCTION BANK Corp. Address before: 25 Financial Street, Xicheng District, Beijing 100033 Applicant before: CHINA CONSTRUCTION BANK Corp. Applicant before: Jianxin Financial Science and Technology Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |