CN110363661A - Bank liquidity prediction technique and device - Google Patents
Bank liquidity prediction technique and device Download PDFInfo
- Publication number
- CN110363661A CN110363661A CN201910716624.6A CN201910716624A CN110363661A CN 110363661 A CN110363661 A CN 110363661A CN 201910716624 A CN201910716624 A CN 201910716624A CN 110363661 A CN110363661 A CN 110363661A
- Authority
- CN
- China
- Prior art keywords
- data
- bank
- history
- mobility
- prediction
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/02—Banking, e.g. interest calculation or account maintenance
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Finance (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Accounting & Taxation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Economics (AREA)
- Technology Law (AREA)
- Computing Systems (AREA)
- Development Economics (AREA)
- Medical Informatics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Mathematical Physics (AREA)
- General Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The present invention provides bank liquidity prediction technique and device, method includes: to obtain the history service data and history mobility data of Bank application service system;The machine learning model pre-established is trained according to history service data and history mobility data;Bank liquidity prediction is carried out using the machine learning model after training.By carrying out characteristics extraction to bank liquidity business datum and carrying out machine learning training, bank liquidity is predicted in realization, supports bank to make full use of remaining mobility, and provide liquidity risk early warning in time using the bank liquidity of prediction.
Description
Technical field
The present invention relates to data processing techniques, are concretely a kind of bank liquidity prediction technique and device.
Background technique
There are strict requirements in every country and area for the mobility of banking system, for there is liquidity risk
Bank will do it corresponding punishment, and the serious bank that may result in stops doing business.Therefore, bank needs to manage mobility comprehensively
Reason causes supervision to be punished, while being also required to predict the following fund state to cope with illiquidity in time.
In the prior art, bank generally passes through management of liquidity bordereau and counts, and timeliness is not high, simultaneously
Accurately future flow can not be predicted, be unable to complete and bank liquidity is made full use of.
Summary of the invention
In order to carry out to bank liquidity, bank is supported to make full use of remaining mobility, the embodiment of the invention provides one
Kind bank liquidity prediction technique, method include:
Obtain the history service data and history mobility data of Bank application service system;
The machine learning model pre-established is trained according to the history service data and history mobility data;
Bank liquidity prediction is carried out using the machine learning model after training.
In the embodiment of the present invention, the history service data and history mobility number of the acquisition Bank application service system
According to including:
Obtain Bank application service system history service data and history mobility data;
Business datum screening, the processing of missing data are carried out to the history service data of the Bank application service system
And abnormal data elimination, determine banking characteristic.
In the embodiment of the present invention, it is described according to the history service data and history mobility data to pre-establishing
Machine learning model, which is trained, includes:
Using the history service data of preset quantity and history mobility data as training sample to the machine pre-established
Learning model carries out initial training;
Using the history service data of another preset quantity and history mobility data as test samples to initial training after
Machine learning model optimize generate training after machine learning model.
In the embodiment of the present invention, described includes: using the machine learning model progress bank liquidity prediction after training
Bank liquidity is carried out using the machine learning model after training to predict to Bank application service system to be predicted
Banking business data carry out mobility prediction, generate bank liquidity prediction data;
According to the bank liquidity prediction data of preset mobility early warning rule and generation, bank liquidity is carried out pre-
It is alert.
In the embodiment of the present invention, the history service data of the Bank application service system include: deposit system business number
According to, loan system business datum and system for settling account business datum;
The banking characteristic includes: service product information, deposit loan transaction information, money transfer transactions information.
Meanwhile the present invention also provides a kind of bank liquidity prediction meanss, comprising:
Data acquisition module, for obtaining the history service data and history mobility data of Bank application service system;
Machine learning module, for according to the history service data and history mobility data to the machine pre-established
Learning model is trained;
Mobility prediction module, for carrying out bank liquidity prediction using the machine learning model after training.
In the embodiment of the present invention, the data acquisition module includes:
Data capture unit, for obtaining Bank application service system history service data and history mobility data;
Characteristic value acquiring unit carries out business datum for the history service data to the Bank application service system
Screening, the processing and abnormal data elimination of missing data, determine banking characteristic.
In the embodiment of the present invention, the machine learning module includes:
Training unit, for using the history service data of preset quantity and history mobility data as training sample to pre-
The machine learning model first established carries out initial training;
Take another preset quantity history service data and history mobility data as test samples to initial training after
Machine learning model optimize generate training after machine learning model,
In the embodiment of the present invention, the mobility prediction module includes:
Prediction processing unit is predicted for carrying out bank liquidity using the machine learning model after training to be predicted
The banking business data of Bank application service system carries out mobility prediction, generates bank liquidity prediction data;
Prewarning unit, for the bank liquidity prediction data according to preset mobility early warning rule and generation, to silver
Row mobility carries out early warning.
Meanwhile the present invention also provides a kind of computer equipment, including memory, processor and storage are on a memory and can
The computer program run on a processor, processor realize the above method when executing computer program.
Meanwhile the present invention also provides a kind of computer readable storage medium, computer-readable recording medium storage has execution
The computer program of the above method.
The present invention provides a kind of bank liquidity prediction technique and device, special by carrying out to bank liquidity business datum
Value indicative is extracted and carries out machine learning training, and bank liquidity is predicted in realization, and bank is supported to make full use of remaining flowing
Property, and liquidity risk early warning is provided in time using the bank liquidity of prediction.
For above and other objects, features and advantages of the invention can be clearer and more comprehensible, preferred embodiment is cited below particularly,
And cooperate institute's accompanying drawings, it is described in detail below.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is the flow chart of bank liquidity prediction technique provided by the invention;
Fig. 2 is the block diagram of bank liquidity prediction meanss provided by the invention;
Fig. 3 is the structural schematic diagram of bank liquidity management provided in an embodiment of the present invention and forecasting system;
Fig. 4 show the block diagram of banking business data server in the present embodiment;
Fig. 5 show the block diagram of machine learning server in the present embodiment;
Fig. 6 show the block diagram of the mobility predictive server of the embodiment of the present invention;
Fig. 7 is the schematic block diagram that the system of the electronic equipment of the embodiment of the present invention is constituted.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
As shown in Figure 1, being bank liquidity prediction technique provided by the invention, comprising:
Step S101 obtains the history service data and history mobility data of Bank application service system;
Step S102 carries out the machine learning model pre-established according to history service data and history mobility data
Training;
Step S103 carries out bank liquidity prediction using the machine learning model after training.
In the embodiment of the present invention, the history service data and history mobility data packet of Bank application service system are obtained
It includes: obtaining Bank application service system history service data and history mobility data;To the Bank application service system
History service data carry out business datum screening, the processing of missing data and abnormal data elimination, determine banking spy
Levy data.
In the embodiment of the present invention, business datum, such as depositing by bank are obtained by obtaining each application server of bank
Money system, loan system, system for settling account obtain history service data, and the business datum in the present embodiment includes but is not limited to clear
(clearing operation product data include: position same day remaining sum, amount of money effective date to be processed, gathering to be processed gold to service product data
Volume, Payment Amount to be processed), deposit and loan transaction data (including: type of service, due date, account balance), remittance industry
It is engaged in data (including: date, cash flow effective date, the cash outflow amount of money, the cash inflow amount of money).
In the embodiment of the present invention, business datum further also is carried out to the history service data of Bank application service system
Screening, the processing and abnormal data elimination of missing data, determine banking characteristic.Include:
Make most basic legitimacy verifies to business datum, guarantees that the characteristic value data of bank's internal data is correct.Including
Screen business datum, missing information processing, exception information cleaning.
Missing information cleaning: if the characteristic value on a certain date is not present, it may be possible to which data quality problem then takes the same day special
Value indicative is the average value of the two days amount of money in front and back.
Dealing of abnormal data: if the characteristic value on a certain date is sharply increased or is reduced, such as with several days difference pole in front and back
Greatly, then it is assumed that be that emergency event or incident cause, this partial data is rejected.
In the embodiment of the present invention, it is described according to the history service data and history mobility data to pre-establishing
Machine learning model, which is trained, includes:
Using the history service data of preset quantity and history mobility data as training sample to the machine pre-established
Learning model carries out initial training;
Using the history service data of another preset quantity and history mobility data as test samples to initial training after
Machine learning model optimize generate training after machine learning model.I.e. characteristic value data and history mobility data are made
For sample, wherein preceding M sample is for training, rear N number of data sample is used for the test samples of prediction effect.By adjusting calculating
Number and test samples deviation obtain regression equation.
In the embodiment of the present invention, described includes: using the machine learning model progress bank liquidity prediction after training
Bank liquidity is carried out using the machine learning model after training to predict to Bank application service system to be predicted
Banking business data carry out mobility prediction, generate bank liquidity prediction data;
According to the bank liquidity prediction data of preset mobility early warning rule and generation, bank liquidity is carried out pre-
It is alert.
Meanwhile the present invention also provides a kind of bank liquidity prediction meanss, as shown in Figure 2, comprising:
Data acquisition module 201, for obtaining the history service data and history mobility number of Bank application service system
According to;
Machine learning module 202, for according to the history service data and history mobility data to pre-establishing
Machine learning model is trained;
Mobility prediction module 203, for carrying out bank liquidity prediction using the machine learning model after training.
The present invention provides a kind of method and device of bank liquidity prediction, by carrying out to bank liquidity business datum
Characteristics extraction simultaneously carries out machine learning training, is formed and is predicted bank liquidity, bank is supported to make full use of remaining mobility,
And liquidity risk early warning is provided in time.Technical solution of the present invention is made further specifically below with reference to specific embodiment
It is bright.
As shown in figure 3, for bank liquidity management provided in this embodiment and the structural schematic diagram of forecasting system, packet
It includes: banking business data server 1, machine learning server 2 and mobility predictive server 3.
In the present embodiment, banking business data server 1 is to receive and load bank's types of applications server (for example is deposited
System, loan system, system for settling account etc.) generate business datum, effect be to all kinds of banking systems generate data
Carry out unified save and data check (quality of data for guaranteeing characteristic value data) processing.
As shown in figure 4, banking business data server system structure chart, in advance by source data loading module 11, source data
Module 12 is managed to form.It is to complete to handle the data that all kinds of operation systems of bank generate that it, which is acted on,.
Source data loading module 11: it is taken by receiving and loading with bank liquidity management and the related types of applications of prediction
It is engaged in device (such as selection period, selection operation system (deposit system, loan system, system for settling account etc.) of history service data)
The business datum of generation provides characteristic value data for machine learning module 2.
Source data preprocessing module 12: system is made most basic legitimacy verifies to data, is protected by setting verification rule
The characteristic value data for demonstrate,proving bank's internal data is correct.Including screening business datum, missing information processing, exception information cleaning.
Missing information cleaning: if the characteristic value on a certain date is not present, it may be possible to which data quality problem then takes the same day special
Value indicative is the average value of the two days amount of money in front and back, i.e.,xi-1、xi+1For the two days amount of money in front and back, xiFor same day gold
Volume.
Dealing of abnormal data: if the characteristic value on a certain date is sharply increased or is reduced, such as with several days difference pole in front and back
Greatly, then it is assumed that be that emergency event or incident cause, this partial data is rejected.
As shown in figure 5, in the present embodiment, the functional block diagram of machine learning server 2 comprising: characteristic value data is led
Enter 21, historical results data and imports 22, machine learning process 23, prediction result analysis 24.Machine learning server 2 is based on feature
Value Data and historical results data, are trained by machine learning, and pass through the optimization sustained improvement engineering to characteristic value
Practise model.
Characteristic value data imports 21: importing characteristic value, the characteristic value in the present embodiment includes clearing operation product information (head
Very little same day remaining sum, amount of money effective date to be processed, collection amount to be processed, Payment Amount to be processed), deposit and loan transaction information
(type of service, due date, account balance), money transfer transactions (date, cash flow effective date, the cash outflow amount of money, cash inflow
The amount of money), and the data for providing one section of long period import.It as shown in table 1, is the mixed secondary attack of the present embodiment, feature value attribute and right
The attribute value table answered.
Table 1
History mobility data importing 22: the training set by history mobility data as machine learning, for feature
The different time points of Value Data match history mobility result data.
Machine learning process 23: by the multiple linear regression of Support vector regression (SVR) algorithm, by giving one
New input sample x, according to given data sample infer it corresponding to output Y be how many, this output Y be a reality
Number.Regression problem can be described with mathematical linguistics are as follows:
Given set of data samples is combined into { (xi,yi)|xi∈Rn,yi∈ R, i=1,2,3..., l }.Find RnOn one
Function f (x) obtains regression equation, to infer the corresponding y value of any x input with y=f (x).
Prediction result analysis 24: importing 22 by characteristic value data importing 21 and history mobility data and be used as sample,
In preceding 200 samples for training, rear 20 data samples are used for the test samples of prediction effect.By adjusting calculation times and
Test samples deviation obtains regression equation.
As shown in fig. 6, mobility predictive server 3 includes: mobility prediction management module 31, mobility prediction processing mould
Block 32 and mobility predict display module 33.
By mobility prediction management module 31 for configuring early-warning parameters and Early-warning Model.It is handled by mobility prediction
Module 32 calls machine learning server, generates future flow data, carries out short early warning according to Future Data and surplus is pre-
It is alert.Predict that display module 33 shows the prediction data of future flow by mobility.
Early-warning Model: pass through setting mobility early warning threshold values (such as regulatory requirements mobility fund and bank capital accounting
Cannot be below 20%) as lower limit, formulate bank liquidity surplus threshold values as the upper limit (such as bank formulate mobility fund and
40%) bank capital accounting lower than lower limit or higher than the upper limit not above, then generating mobility shortage and superfluous early warning.
Mobility prediction management module 31: mobility early-warning parameters are arranged by mobility prediction management module 31 in user,
Early warning alerting pattern and frequency;
Mobility predicts processing module 32: system loads the data of banking business data server daily, and forms feature
It is worth sample, calls the model and equation of the training of machine learning server 2, completes future flow data and calculate;
Mobility predicts display module 33: system passes through machine learning server 2 and realizes to future flow prediction data,
Predict that 32 displayed page of display module carries out prediction data displaying by mobility, and to reach the prediction data of early warning threshold values into
Row early warning modes such as (be highlighted) short message or mail reminders.
In the present embodiment, characteristic value source data: the data including each business category relevant to mobility.Include:
A service data:
B service data:
C service data:
D service data:
A service includes: clearing operation product information (date, same day remaining sum, the amount of money effective date to be processed, receipts to be processed
The money amount of money, Payment Amount to be processed)
B service includes: deposit and loan transaction information (date, type of service, due date, account balance);
C service includes: money transfer transactions (date, cash flow effective date, the cash outflow amount of money, the cash inflow amount of money);
D service includes: capital market business (date, cash flow effective date, the cash outflow amount of money, cash inflow gold
Volume).
Mobility prediction result data: according to characteristic value data and historical results data, generating future flow predicted value,
By mobility threshold values (for example regulatory requirements mobility fund and bank capital accounting cannot be below 20%) conduct of regulatory requirements
Lower limit, formulate bank liquidity surplus threshold values as the upper limit (such as bank formulate mobility fund and bank capital accounting cannot
Higher than 40%), then generating mobility shortage and superfluous early warning lower than lower limit or higher than the upper limit.
It is as follows mobility prediction data structure in the present embodiment.
The embodiment of the present invention provides the system of a kind of bank liquidity management and prediction, by bank liquidity business number
According to progress characteristics extraction and machine learning training is carried out, is formed to bank liquidity prediction model, bank is supported to make full use of
Remaining mobility, and liquidity risk early warning is provided in time.
The embodiment of the present invention also provides a kind of electronic equipment, the electronic equipment can be desktop computer, tablet computer and
Mobile terminal etc., the implementation of the electronic equipment are referred to previous embodiment, and content is incorporated in this, and it is no longer superfluous to repeat place
It states.
Fig. 7 is the schematic block diagram that the system of the electronic equipment 80 of the embodiment of the present invention is constituted.As shown in fig. 7, the electronics is set
Standby 80 may include processor 81 and memory 82;Memory 82 is coupled to processor 81 by bus 83.It is worth noting that,
The figure is exemplary;Can also use other kinds of structure, come supplement or replace the structure, with realize telecommunications functions or its
His function.
In one embodiment, bank liquidity forecast function can be integrated into processor 81.Wherein, processor 81 can be with
It is configured for control as follows: obtaining the history service data and history mobility data of Bank application service system;According to
The history service data and history mobility data are trained the machine learning model pre-established;After training
Machine learning model carries out bank liquidity prediction.
The embodiment of the present invention also provides a kind of computer-readable program, wherein when executing described program in the electronic device
When, program makes computer execute bank liquidity forecast function as described above in the electronic equipment.
The embodiment of the present invention also provides a kind of storage medium for being stored with computer-readable program, wherein computer-readable journey
Sequence makes computer execute bank liquidity forecast function described in above example in the electronic device.
The preferred embodiment of the present invention is described above by reference to attached drawing.The many features and advantage root of these embodiments
According to the detailed description be clearly, therefore appended claims be intended to cover these embodiments fall into its true spirit
With all these feature and advantage in range.Further, since those skilled in the art is readily apparent that many modifications and changes,
Therefore it is not meant to for embodiments of the present invention to be limited to illustrated and description precision architecture and operation, but can cover and fall into
All suitable modifications and equivalent within the scope of its.
It should be understood by those skilled in the art that, the embodiment of the present invention can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the present invention
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the present invention, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The present invention be referring to according to the method for the embodiment of the present invention, the process of equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
Specific embodiment is applied in the present invention, and principle and implementation of the present invention are described, above embodiments
Explanation be merely used to help understand method and its core concept of the invention;At the same time, for those skilled in the art,
According to the thought of the present invention, there will be changes in the specific implementation manner and application range, in conclusion in this specification
Appearance should not be construed as limiting the invention.
Claims (12)
1. a kind of bank liquidity prediction technique, which is characterized in that the method includes:
Obtain the history service data and history mobility data of Bank application service system;
The machine learning model pre-established is trained according to the history service data and history mobility data;
Bank liquidity prediction is carried out using the machine learning model after training.
2. bank liquidity prediction technique as described in claim 1, which is characterized in that the acquisition Bank application service system
The history service data and history mobility data of system include:
Obtain Bank application service system history service data and history mobility data;
To the history service data of the Bank application service system carry out business datum screening, the processing of missing data and
Abnormal data elimination determines banking characteristic.
3. bank liquidity prediction technique as claimed in claim 2, which is characterized in that described according to the history service number
Include: according to being trained with history mobility data to the machine learning model pre-established
Machine learning using the history service data and history mobility data of preset quantity as training sample to pre-establishing
Model carries out initial training;
Using the history service data of another preset quantity and history mobility data as test samples to the machine after initial training
Device learning model optimizes the machine learning model after generating training.
4. bank liquidity prediction technique as described in claim 1, which is characterized in that described utilizes the engineering after training
Practising model progress bank liquidity prediction includes:
Bank liquidity prediction is carried out to the silver of Bank application service system to be predicted using the machine learning model after training
Row business datum carries out mobility prediction, generates bank liquidity prediction data;
According to the bank liquidity prediction data of preset mobility early warning rule and generation, early warning is carried out to bank liquidity.
5. bank liquidity prediction technique as claimed in claim 2, which is characterized in that
The history service data of the Bank application service system include: deposit system business datum, loan system business datum
And system for settling account business datum;
The banking characteristic includes: service product information, deposit loan transaction information, money transfer transactions information.
6. a kind of bank liquidity prediction meanss, which is characterized in that the device includes:
Data acquisition module, for obtaining the history service data and history mobility data of Bank application service system;
Machine learning module, for the machine learning according to the history service data and history mobility data to pre-establishing
Model is trained;
Mobility prediction module, for carrying out bank liquidity prediction using the machine learning model after training.
7. bank liquidity prediction meanss as claimed in claim 6, which is characterized in that the data acquisition module includes:
Data capture unit, for obtaining Bank application service system history service data and history mobility data;
Characteristic value acquiring unit carries out business datum sieve for the history service data to the Bank application service system
Choosing, the processing and abnormal data elimination of missing data, determine banking characteristic.
8. bank liquidity prediction meanss as claimed in claim 7, which is characterized in that the machine learning module includes:
Training unit, for using the history service data of preset quantity and history mobility data as training sample to building in advance
Vertical machine learning model carries out initial training;
Take another preset quantity history service data and history mobility data as test samples to the machine after initial training
Device learning model optimizes the machine learning model after generating training.
9. bank liquidity prediction meanss as claimed in claim 6, which is characterized in that the mobility prediction module packet
It includes:
Prediction processing unit is predicted for carrying out bank liquidity using the machine learning model after training to bank to be predicted
The banking business data of application service system carries out mobility prediction, generates bank liquidity prediction data;
Prewarning unit flows bank for the bank liquidity prediction data according to preset mobility early warning rule and generation
Dynamic property carries out early warning.
10. bank liquidity prediction meanss as claimed in claim 7, which is characterized in that
The history service data of the Bank application service system include: deposit system business datum, loan system business datum
And system for settling account business datum;
The banking characteristic includes: service product information, deposit loan transaction information, money transfer transactions information.
11. a kind of computer equipment including memory, processor and stores the meter that can be run on a memory and on a processor
Calculation machine program, which is characterized in that the processor realizes any side of claim 1 to 5 when executing the computer program
Method.
12. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage has perform claim
It is required that the computer program of 1 to 5 any the method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910716624.6A CN110363661A (en) | 2019-08-05 | 2019-08-05 | Bank liquidity prediction technique and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910716624.6A CN110363661A (en) | 2019-08-05 | 2019-08-05 | Bank liquidity prediction technique and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110363661A true CN110363661A (en) | 2019-10-22 |
Family
ID=68223140
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910716624.6A Pending CN110363661A (en) | 2019-08-05 | 2019-08-05 | Bank liquidity prediction technique and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110363661A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111882428A (en) * | 2020-07-27 | 2020-11-03 | 上海应用技术大学 | Commercial bank liquidity risk assessment method and device |
CN112085497A (en) * | 2020-08-28 | 2020-12-15 | 银清科技有限公司 | User account data processing method and device |
CN112613978A (en) * | 2020-12-18 | 2021-04-06 | 中国工商银行股份有限公司 | Bank capital abundance prediction method, device, electronic equipment and medium |
CN113487425A (en) * | 2021-08-03 | 2021-10-08 | 北京神州数字科技有限公司 | Method and system for backtracking daytime liquidity condition based on historical data |
CN114240626A (en) * | 2021-12-17 | 2022-03-25 | 中国建设银行股份有限公司 | Position frame calculation processing method and device, electronic equipment and computer readable medium |
CN114638439A (en) * | 2022-04-11 | 2022-06-17 | 中国工商银行股份有限公司 | Prediction method and device for large-amount exposure risk |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107977754A (en) * | 2017-12-18 | 2018-05-01 | 深圳前海微众银行股份有限公司 | Data predication method, system and computer-readable recording medium |
CN108921688A (en) * | 2018-07-02 | 2018-11-30 | 阿里巴巴集团控股有限公司 | Construct the method and device of prediction model |
CN109598618A (en) * | 2018-09-12 | 2019-04-09 | 阿里巴巴集团控股有限公司 | Data processing method, the determination method and apparatus of mobility time limit notch |
-
2019
- 2019-08-05 CN CN201910716624.6A patent/CN110363661A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107977754A (en) * | 2017-12-18 | 2018-05-01 | 深圳前海微众银行股份有限公司 | Data predication method, system and computer-readable recording medium |
CN108921688A (en) * | 2018-07-02 | 2018-11-30 | 阿里巴巴集团控股有限公司 | Construct the method and device of prediction model |
CN109598618A (en) * | 2018-09-12 | 2019-04-09 | 阿里巴巴集团控股有限公司 | Data processing method, the determination method and apparatus of mobility time limit notch |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111882428A (en) * | 2020-07-27 | 2020-11-03 | 上海应用技术大学 | Commercial bank liquidity risk assessment method and device |
CN112085497A (en) * | 2020-08-28 | 2020-12-15 | 银清科技有限公司 | User account data processing method and device |
CN112613978A (en) * | 2020-12-18 | 2021-04-06 | 中国工商银行股份有限公司 | Bank capital abundance prediction method, device, electronic equipment and medium |
CN112613978B (en) * | 2020-12-18 | 2024-02-06 | 中国工商银行股份有限公司 | Bank capital sufficiency prediction method and device, electronic equipment and medium |
CN113487425A (en) * | 2021-08-03 | 2021-10-08 | 北京神州数字科技有限公司 | Method and system for backtracking daytime liquidity condition based on historical data |
CN114240626A (en) * | 2021-12-17 | 2022-03-25 | 中国建设银行股份有限公司 | Position frame calculation processing method and device, electronic equipment and computer readable medium |
CN114638439A (en) * | 2022-04-11 | 2022-06-17 | 中国工商银行股份有限公司 | Prediction method and device for large-amount exposure risk |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110363661A (en) | Bank liquidity prediction technique and device | |
CN108846520B (en) | Loan overdue prediction method, loan overdue prediction device and computer-readable storage medium | |
WO2020143344A1 (en) | Method and device for warehouse receipt pledge financing based on blockchain architecture | |
TW202008251A (en) | Payment instrument recommendation method and apparatus, device, and computer readable storage medium | |
CN111008896A (en) | Financial risk early warning method and device, electronic equipment and storage medium | |
CN108492177A (en) | Domestic assets cross-border transaction method, server and storage medium | |
CN102117469A (en) | System and method for estimating credit risks | |
CN109034493A (en) | A kind of account balance prediction technique and device | |
CN108537460A (en) | Consumer's risk prediction technique and system | |
CN109598618A (en) | Data processing method, the determination method and apparatus of mobility time limit notch | |
CN108399566A (en) | A kind of data processing method and terminal | |
CN111985914A (en) | Settlement method, settlement device, node and readable storage medium | |
CN109615384A (en) | Generation method, device and the server of timeliness verification rule | |
CN111899093A (en) | Method and device for predicting default loss rate | |
CN114254846A (en) | Engineering project information management system | |
CN107862067A (en) | A kind of screening technique and device of bank loan data query | |
CN110245985B (en) | Information processing method and device | |
CN111429251A (en) | Method and device for processing data under multiple modes | |
CN112085497A (en) | User account data processing method and device | |
JP2017084229A (en) | Investment simulation device and method | |
CN114819721A (en) | Business outlet evaluation method and device, electronic equipment and storage medium | |
CN114936920A (en) | Bank interest-metering method, device, equipment and storage medium based on daily record | |
CN114282881A (en) | Depreciation measuring and calculating method and device, storage medium and computer equipment | |
CN113409119A (en) | Method and device for assessing capital risk of financing lease enterprise, storage medium and electronic equipment | |
CN112085264A (en) | Processing method and device of quota account data |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191022 |
|
RJ01 | Rejection of invention patent application after publication |