CN109598623A - A kind of financial product future profits data predication method, apparatus and system - Google Patents
A kind of financial product future profits data predication method, apparatus and system Download PDFInfo
- Publication number
- CN109598623A CN109598623A CN201811509102.0A CN201811509102A CN109598623A CN 109598623 A CN109598623 A CN 109598623A CN 201811509102 A CN201811509102 A CN 201811509102A CN 109598623 A CN109598623 A CN 109598623A
- Authority
- CN
- China
- Prior art keywords
- enterprise
- data
- factor
- ranking
- financial product
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000003062 neural network model Methods 0.000 claims abstract description 29
- 238000013507 mapping Methods 0.000 claims abstract description 26
- 238000013528 artificial neural network Methods 0.000 claims abstract description 13
- 238000013480 data collection Methods 0.000 claims description 20
- 238000012549 training Methods 0.000 claims description 17
- 238000004458 analytical method Methods 0.000 claims description 8
- 230000007306 turnover Effects 0.000 claims description 4
- 241001269238 Data Species 0.000 description 5
- 230000008569 process Effects 0.000 description 4
- 239000012141 concentrate Substances 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 2
- 239000010931 gold Substances 0.000 description 2
- 229910052737 gold Inorganic materials 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 210000004218 nerve net Anatomy 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000007115 recruitment Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q40/06—Asset management; Financial planning or analysis
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Development Economics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Operations Research (AREA)
- Accounting & Taxation (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- Finance (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Technology Law (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The application provides a kind of financial product future profits data predication method, apparatus and system, and wherein method includes: the basic for obtaining enterprise；The basic is inputted to the neural network model constructed in advance, obtains enterprise's fluctuation data of neural network model output；Enterprise's ranking of the enterprise is determined based on the knowledge mapping constructed in advance；Data and enterprise's ranking are fluctuated in conjunction with the enterprise, predict that the enterprise corresponds to the future profits data of financial product.The application can predict the future profits data of financial product in such a way that neural network and knowledge mapping are using automation, so as to obtain the accurate future profits data of financial product.
Description
Technical field
This application involves network technique field more particularly to a kind of financial product future profits data predication methods, device
And system.
Background technique
Currently, financial market, there are many marketing enterprises, different marketing enterprises can have one or more financial products.
User can choose the financial product of different enterprises according to oneself demand and experience.
Currently, user when selecting financial product, need based on for enterprise it is subjective understand and internet in enterprise
The information of industry is as supplementary means, after artificial comprehensive analyzes company-related information, selects the corresponding financial product of enterprise.
But since understanding of the user for enterprise is less, in the case where information asymmetry, user manually can not be accurate
The financial product income for predicting enterprise, further can not accurately select suitable financial product.
Summary of the invention
In consideration of it, the application provides financial product future profits data predication method, apparatus and system, it can be using automatic
The mode of change predicts the future profits data of financial product, so as to obtain the accurate future profits number of financial product
According to.
To achieve the goals above, this application provides following technical characteristics:
A kind of financial product future profits data predication method, comprising:
Obtain the basic of enterprise；
The basic is inputted to the neural network model constructed in advance, obtains the enterprise of neural network model output
Industry fluctuates data；
Enterprise's ranking of the enterprise is determined based on the knowledge mapping constructed in advance；
Data and enterprise's ranking are fluctuated in conjunction with the enterprise, predict that the enterprise corresponds to the future profits number of financial product
According to.
Optionally, wherein enterprise's fluctuation data include future profits rate and the following stability bandwidth.
Optionally, building knowledge mapping includes: in advance
Obtain the integrated data set of multiple enterprises；Wherein, integrated data set may include that the data set of four seed types is basic
Data set, internet data collection, intellectual property data collection and general public sentiment data collection；
Pretreatment operation is executed to the integrated data set of multiple enterprises, multiple integrated datas after obtaining pretreatment operation
Collection；
Analysis operation is executed to pretreated integrated data set, determines the factor set of multiple enterprises；
Company Knowledge map is constructed using the factor set of the multiple enterprise；Wherein, each entity in Company Knowledge map
For an enterprise, Company Knowledge map is used to indicate the relationship between multiple enterprises, and, each entity uses factor set representations.
Optionally, the factor set may include that the factor is ground in the financial factor, company's factor, the share price factor and analyst's throwing；
The finance factor includes finance profit, financial valuation, accounting operations, finance growth and asset-liabilities；
Company's factor includes company's market value and shareholder's concentration degree；
The share price factor includes the fluctuation and stability bandwidth of turnover rate, opposite overall market；
It includes analyst's grading that the analyst, which throws and grinds the factor,.
Optionally, each factor includes multiple sub- factors, and, each factor is previously provided with respective weights, each height because
Element is previously provided with respective weights, then enterprise's ranking that the enterprise is determined based on the knowledge mapping constructed in advance, comprising:
Based on the knowledge mapping, sorting operation is executed to each enterprise according to each sub- factor, obtains each enterprise
Sub- factor score；
Each in Graph One factor factor score is summed the factor score again multiplied by corresponding factor weight；
Multiple factor scores of one enterprise sum to obtain enterprise's score again multiplied by corresponding Factor Weight；
Sorting operation is executed to multiple enterprises by enterprise's score, obtains enterprise's ranking of multiple enterprises.
Optionally, the fluctuation data of enterprise described in the combination and enterprise's ranking, predict that the enterprise corresponds to financial product
Future profits data, comprising:
Obtain the historical yield data of financial product under the enterprise；
Data, enterprise's ranking and default predictor formula, prediction gold are fluctuated in conjunction with the historical yield data of financial product, enterprise
Melt the future profits data of product.
Optionally, predictor formula includes:
Future profits data=current avail data+future profits rate * C 1+ (current enterprise ranking
History enterprise ranking) * C2- stability bandwidth * C3+C4；
Wherein, C1, C2, C3 and C4 are known parameters respectively.
Optionally, the neural network model of building includes:
Obtain the basic of multiple enterprises；
Pretreatment operation is executed to the basic of multiple enterprises and obtains multiple training samples；
Based on the initial neural network of training sample training until reaching termination condition, the neural network mould that training terminates is obtained
Type；Wherein, neural network model is, with basic be input, with future profits rate and the following stability bandwidth be output machine
Device model.
A kind of financial product future profits data prediction meanss, comprising:
Acquiring unit, for obtaining the basic of enterprise；
Input unit obtains the nerve net for inputting the basic to the neural network model constructed in advance
Data are fluctuated in the enterprise of network model output；
Determination unit, for determining enterprise's ranking of the enterprise based on the knowledge mapping constructed in advance；
Predicting unit predicts that the corresponding finance of the enterprise produces for fluctuating data and enterprise's ranking in conjunction with the enterprise
The future profits data of product.
A kind of financial product future profits data forecasting system, comprising:
Server and third party system；
Server, for obtaining the basic of enterprise from third party system；The basic is inputted to preparatory
The neural network model of building obtains enterprise's fluctuation data of neural network model output；Based on the knowledge graph constructed in advance
Compose the enterprise's ranking for determining the enterprise；Data and enterprise's ranking are fluctuated in conjunction with the enterprise, predict the corresponding finance of the enterprise
The future profits data of product.By the above technological means, may be implemented it is following the utility model has the advantages that
The application determines that data are fluctuated in enterprise by constructing neural network in advance, and enterprise's fluctuation number can be obtained with Accurate Prediction
According to, enterprise's ranking of the enterprise is determined by the knowledge mapping constructed in advance, it can be in conjunction with enterprise's fluctuation data and enterprise's ranking
Predict the future profits data of the corresponding financial product of the enterprise.
That is, the application can predict that the following of financial product is received in such a way that neural network and knowledge mapping are using automation
Beneficial data, so as to obtain the accurate future profits data of financial product.
Detailed description of the invention
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, 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 application 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 a kind of structural schematic diagram of financial product future profits data forecasting system disclosed in the embodiment of the present application；
Fig. 2 is a kind of flow chart of financial product future profits data predication method disclosed in the embodiment of the present application；
Fig. 3 is the flow chart of another financial product future profits data predication method disclosed in the embodiment of the present application；
Fig. 4 is the flow chart of another financial product future profits data predication method disclosed in the embodiment of the present application；
Fig. 5 is a kind of structural schematic diagram of financial product future profits data prediction meanss disclosed in the embodiment of the present application.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of embodiments of the present application, instead of all the embodiments.It is based on
Embodiment in the application, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall in the protection scope of this application.
The application provides financial product future profits data forecasting system referring to Fig. 1
Server 100, and, the multiple third party systems 200 being connected with server 100.
The subsequent future profits rate for needing to predict enterprise using neural network model of the application and stability bandwidth.Referring to fig. 2,
The building process of neural network model is provided below:
Step S201: the basic of multiple enterprises is obtained.
The basic of multiple enterprises can be obtained from third party system, the basic of each enterprise may include
Assets rate, asset-liability ratio, supplier, shareholder's data, enterprise's market value, Return on Total Assets, net assets income ratio, p/e ratio,
Price value ratio and per share cash flow.Certainly, basic can also include other master datas.
Step S202: pretreatment operation is executed to the basic of multiple enterprises and obtains multiple training samples.
Pretreatment operation is executed to the basic of multiple enterprises, pretreatment operation may include Exception Filter data point
Operation, the operation such as normalization operation, pretreatment operation can unify the master data that each master data concentrates different dimensions.
The basic of enterprises multiple after pretreatment operation is determined as multiple training samples.
Step S203: based on the initial neural network of training sample training until reaching termination condition, obtain what training terminated
Neural network model.
Wherein, initial neural network model includes multiple input nodes and two output nodes, the quantity base of input node
Notebook data concentrates the quantity of basic parameter identical；Output node is the future profits rate and future stability bandwidth of enterprise.
Therefore, the neural network model finally obtained is, is input with basic, with future profits rate and non-incoming wave
Dynamic rate is the machine mould of output.
The subsequent future profits rate for needing to predict enterprise using neural network model of the application and stability bandwidth.Referring to Fig. 3,
The building process of knowledge mapping is described below:
Step S301: the integrated data set of multiple enterprises is obtained.
Integrated data set may include the data set basic, internet data collection, intellectual property number of four seed types
According to collection and general public sentiment data collection.
The first categorical data collection: basic.
The basic of each enterprise may include assets rate, asset-liability ratio, supplier, shareholder's data, city, enterprise
Value, Return on Total Assets, net assets income ratio, p/e ratio, price value ratio and per share cash flow.Certainly, basic can be with
Including other master datas.
Second of type data set: internet data collection.
Internet data, which collects, can carry out finishing analysis acquisition, internet in the process performing data on internet for enterprise
Data set includes: website user's registration amount, Intranet number of users etc..
The third categorical data collection: intellectual property data collection.
Intellectual property data collection may include foreign application quantity, domestic applications quantity, patent application quantity, utility model
Request for data amount etc. can also include other data about intellectual property certainly.Intellectual property data collection can pass through knowledge
Property right website obtains to obtain and analyze.
4th type data set: general public sentiment data collection.
General public sentiment data collection may include the recruitment temperature of enterprise, search for temperature, wage level, flow of personnel rate, certainly
It can also include other general public sentiment datas.General public sentiment data collection can be obtained by crawler mode from the webpage post analysis that obtains information
It arrives.
Step 302: pretreatment operation is executed to the integrated data set of multiple enterprises, it is multiple comprehensive after obtaining pretreatment operation
Close data set.
Integrated data concentrates the data having to belong to structural data, and some data belong to semi-structured data, some data
Belong to unstructured data, it is possible to the data of different structure be executed with different pretreatment operations, so as to pretreatment operation
The integrated data set that integrated data set afterwards is melted as same data type.
Step S303: analysis operation is executed to pretreated integrated data set, determines the factor set of multiple enterprises.
Big data analysis operation is executed to integrated data set, determines the factor set of each enterprise.Meter about each factor
Calculation process is no longer described in detail.
The factor set of each enterprise may include: that the factor is ground in the financial factor, company's factor, the share price factor and analyst's throwing.
The financial factor may include finance profit, financial valuation, accounting operations, finance growth and asset-liabilities.
Company's factor includes company's market value and shareholder's concentration degree.
The share price factor includes turnover rate, the fluctuation (beta coefficient) of opposite overall market, stability bandwidth.
It includes analyst's grading that analyst, which throws and grinds the factor,.
Step S304: Company Knowledge map is constructed using the factor set of multiple enterprises.
Each enterprise can be used as an entity, and the factor set of each enterprise is the data of presentation-entity.
Factor set based on multiple enterprises executes Entity recognition and Relation extraction operates, for example, SVM engineering can be used
The mode of habit carries out Relation extraction operation, so that it is determined that the relationship between different entities.Between last foundation different entities
Relationship constructs knowledge mapping.
It has been mature technology about building knowledge mapping technology, details are not described herein.
Step S305: multiple enterprise's rankings are determined based on Company Knowledge map.
A kind of implementation of the application offer step S305:
Step S3051: matching weight in advance for multiple Factor minutes, and, it is that the sub- factor under each analysis factor distributes power
Weight.
For example, including the case where the financial factor, company's factor, the share price factor and analyst's factor in multiple analysis factors
Under, it can be that four factors assign different weights according to the significance level of four factors, the sum of weight of four factors is 1.
Weight can be distributed for the sub- factor under each factor, to distinguish the significance level of different factors, under each factor
Multiple sub- factors weight and value be 1.
Step S3052: being based on the knowledge mapping, executes sorting operation to each enterprise according to each sub- factor, obtains
The sub- factor score of each enterprise.
Step S3053: each in Graph One factor factor score is summed the factor score again multiplied by corresponding factor weight.
Multiple factor scores of S3054: one enterprise of step sum to obtain enterprise's score again multiplied by corresponding Factor Weight.
Step S3055: sorting operation is executed to multiple enterprises by enterprise's score, obtains enterprise's ranking of multiple enterprises.
The application provides financial product future profits data forecasting system
Step S401: the basic of enterprise is obtained.
Step S402: the basic is inputted to the neural network model constructed in advance, obtains the neural network mould
Data are fluctuated in the enterprise of type output, wherein fluctuation data include the future profits rate and future stability bandwidth of enterprise.
Step S403: enterprise's ranking of the enterprise is determined based on the knowledge mapping constructed in advance.
Step S404: data and enterprise's ranking are fluctuated in conjunction with the enterprise, predict that the enterprise corresponds to financial product
Future profits data.
Wherein step S404 may include realizing in the following way:
Step S4041: the historical yield data of financial product under the enterprise are obtained；
Step S4042: data, enterprise's ranking and default prediction are fluctuated in conjunction with the historical yield data of financial product, enterprise
Formula predicts the future profits data of financial product.
It is understood that the avail data of financial product is directly proportional to the future profits rate in fluctuation data.
The avail data of each financial product is inversely proportional with the stability bandwidth in fluctuation data；
The avail data of each financial product is directly proportional to enterprise's ranking.
It can empirically determine the formula of a future profits data:
Future profits data=current avail data+future profits rate * C 1+ (current enterprise ranking
History enterprise ranking) * C2- stability bandwidth * C3+C4.Wherein, C1, C2, C3 and C4 are known parameters respectively.
Step S405: the future profits trend of financial product in enterprise is shown.
It can be seen that the application has the advantages that by the above content
The application determines that data are fluctuated in enterprise by constructing neural network in advance, and enterprise's fluctuation number can be obtained with Accurate Prediction
According to, enterprise's ranking of the enterprise is determined by the knowledge mapping constructed in advance, it can be in conjunction with enterprise's fluctuation data and enterprise's ranking
Predict the future profits data of the corresponding financial product of the enterprise.
That is, the application can predict that the following of financial product is received in such a way that neural network and knowledge mapping are using automation
Beneficial data, so as to obtain the accurate future profits data of financial product.
The application provides a kind of financial product future profits data prediction meanss, may include: referring to Fig. 5
Acquiring unit 51, for obtaining the basic of enterprise；
Input unit 52 obtains the nerve for inputting the basic to the neural network model constructed in advance
Data are fluctuated in the enterprise of network model output；
Determination unit 53, for determining enterprise's ranking of the enterprise based on the knowledge mapping constructed in advance；
Predicting unit 54 predicts the corresponding finance of the enterprise for fluctuating data and enterprise's ranking in conjunction with the enterprise
The future profits data of product.
Wherein, enterprise's fluctuation data include future profits rate and the following stability bandwidth.
Wherein building knowledge mapping includes: in advance
Obtain the integrated data set of multiple enterprises；Wherein, integrated data set may include that the data set of four seed types is basic
Data set, internet data collection, intellectual property data collection and general public sentiment data collection；
Pretreatment operation is executed to the integrated data set of multiple enterprises, multiple integrated datas after obtaining pretreatment operation
Collection；
Analysis operation is executed to pretreated integrated data set, determines the factor set of multiple enterprises；
Company Knowledge map is constructed using the factor set of the multiple enterprise；Wherein, each entity in Company Knowledge map
For an enterprise, Company Knowledge map is used to indicate the relationship between multiple enterprises, and, each entity uses factor set representations.
Wherein the factor set may include that the factor is ground in the financial factor, company's factor, the share price factor and analyst's throwing；
The finance factor includes finance profit, financial valuation, accounting operations, finance growth and asset-liabilities；
Company's factor includes company's market value and shareholder's concentration degree；
The share price factor includes the fluctuation and stability bandwidth of turnover rate, opposite overall market；
It includes analyst's grading that the analyst, which throws and grinds the factor,.
Wherein, each factor includes multiple sub- factors, and, each factor is previously provided with respective weights, each sub- factor
Respective weights are previously provided with, then enterprise's ranking that the enterprise is determined based on the knowledge mapping constructed in advance, comprising:
Based on the knowledge mapping, sorting operation is executed to each enterprise according to each sub- factor, obtains each enterprise
Sub- factor score；
Each in Graph One factor factor score is summed the factor score again multiplied by corresponding factor weight；
Multiple factor scores of one enterprise sum to obtain enterprise's score again multiplied by corresponding Factor Weight；
Sorting operation is executed to multiple enterprises by enterprise's score, obtains enterprise's ranking of multiple enterprises.
Wherein, the fluctuation data of enterprise described in the combination and enterprise's ranking, predict that the enterprise corresponds to financial product
Future profits data, comprising:
Obtain the historical yield data of financial product under the enterprise；
Data, enterprise's ranking and default predictor formula, prediction gold are fluctuated in conjunction with the historical yield data of financial product, enterprise
Melt the future profits data of product.
Wherein predictor formula includes:
Future profits data=current avail data+future profits rate * C 1+ (current enterprise ranking
History enterprise ranking) * C2- stability bandwidth * C3+C4；
Wherein, C1, C2, C3 and C4 are known parameters respectively.
The neural network model wherein constructed includes:
Obtain the basic of multiple enterprises；
Pretreatment operation is executed to the basic of multiple enterprises and obtains multiple training samples；
Based on the initial neural network of training sample training until reaching termination condition, the neural network mould that training terminates is obtained
Type；Wherein, neural network model is, with basic be input, with future profits rate and the following stability bandwidth be output machine
Device model.
Specific implementation about financial product future profits data prediction meanss may refer to embodiment shown in Fig. 2-4,
Details are not described herein.
Referring to Fig. 1, present invention also provides a kind of financial product future profits data forecasting systems, comprising:
Server and third party system；
Server, for obtaining the basic of enterprise from third party system；The basic is inputted to preparatory
The neural network model of building obtains enterprise's fluctuation data of neural network model output；Based on the knowledge graph constructed in advance
Compose the enterprise's ranking for determining the enterprise；Data and enterprise's ranking are fluctuated in conjunction with the enterprise, predict the corresponding finance of the enterprise
The future profits data of product.
Specific implementation about financial product future profits data forecasting system may refer to embodiment shown in Fig. 2-4,
Details are not described herein.
If function described in the present embodiment method is realized in the form of SFU software functional unit and as independent product pin
It sells or in use, can store in a storage medium readable by a compute device.Based on this understanding, the embodiment of the present application
The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, this is soft
Part product is stored in a storage medium, including some instructions are used so that calculating equipment (it can be personal computer,
Server, mobile computing device or network equipment etc.) execute all or part of step of each embodiment the method for the application
Suddenly.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), deposits at random
The various media that can store program code such as access to memory (RAM, Random Access Memory), magnetic or disk.
Each embodiment in this specification is described in a progressive manner, the highlights of each of the examples are with it is other
The difference of embodiment, same or similar part may refer to each other between each embodiment.
The foregoing description of the disclosed embodiments makes professional and technical personnel in the field can be realized or use the application.
Various modifications to these embodiments will be readily apparent to those skilled in the art, as defined herein
General Principle can be realized in other embodiments without departing from the spirit or scope of the application.Therefore, the application
It is not intended to be limited to the embodiments shown herein, and is to fit to and the principles and novel features disclosed herein phase one
The widest scope of cause.
Claims (10)
1. a kind of financial product future profits data predication method characterized by comprising
Obtain the basic of enterprise；
The basic is inputted to the neural network model constructed in advance, obtains enterprise's wave of neural network model output
Dynamic data；
Enterprise's ranking of the enterprise is determined based on the knowledge mapping constructed in advance；
Data and enterprise's ranking are fluctuated in conjunction with the enterprise, predict that the enterprise corresponds to the future profits data of financial product.
2. the method as described in claim 1, which is characterized in that wherein enterprise's fluctuation data include future profits rate and non-incoming wave
Dynamic rate.
3. the method as described in claim 1, which is characterized in that building knowledge mapping includes: in advance
Obtain the integrated data set of multiple enterprises；Wherein, integrated data set may include the data set master data of four seed types
Collection, internet data collection, intellectual property data collection and general public sentiment data collection；
Pretreatment operation is executed to the integrated data set of multiple enterprises, multiple integrated data sets after obtaining pretreatment operation；
Analysis operation is executed to pretreated integrated data set, determines the factor set of multiple enterprises；
Company Knowledge map is constructed using the factor set of the multiple enterprise；Wherein, each entity is one in Company Knowledge map
Enterprise, Company Knowledge map are used to indicate the relationship between multiple enterprises, and, each entity uses factor set representations.
4. method as claimed in claim 3, which is characterized in that the factor set may include the financial factor, company's factor, stock
The valence factor and analyst, which throw, grinds the factor；
The finance factor includes finance profit, financial valuation, accounting operations, finance growth and asset-liabilities；
Company's factor includes company's market value and shareholder's concentration degree；
The share price factor includes the fluctuation and stability bandwidth of turnover rate, opposite overall market；
It includes analyst's grading that the analyst, which throws and grinds the factor,.
5. the method as claimed in claim 3 or 4, which is characterized in that each factor includes multiple sub- factors, and, each factor
Respective weights are previously provided with, each sub- factor is previously provided with respective weights, then described based on the knowledge mapping constructed in advance
Determine enterprise's ranking of the enterprise, comprising:
Based on the knowledge mapping, sorting operation is executed to each enterprise according to each sub- factor, obtain each enterprise it is sub- because
Plain score；
Each in Graph One factor factor score is summed the factor score again multiplied by corresponding factor weight；
Multiple factor scores of one enterprise sum to obtain enterprise's score again multiplied by corresponding Factor Weight；
Sorting operation is executed to multiple enterprises by enterprise's score, obtains enterprise's ranking of multiple enterprises.
6. method according to claim 2, which is characterized in that data and enterprise row are fluctuated in enterprise described in the combination
Name, predicts that the enterprise corresponds to the future profits data of financial product, comprising:
Obtain the historical yield data of financial product under the enterprise；
Data, enterprise's ranking and default predictor formula are fluctuated in conjunction with the historical yield data of financial product, enterprise, predicts that finance produces
The future profits data of product.
7. method as claimed in claim 6, which is characterized in that predictor formula includes:
Future profits data=current avail data+future profits rate * C 1+ (current enterprise ranking
History enterprise ranking) * C2- stability bandwidth * C3+C4；
Wherein, C1, C2, C3 and C4 are known parameters respectively.
8. the method as described in claim 1, which is characterized in that the neural network model of building includes:
Obtain the basic of multiple enterprises；
Pretreatment operation is executed to the basic of multiple enterprises and obtains multiple training samples；
Based on the initial neural network of training sample training until reaching termination condition, the neural network model that training terminates is obtained；
Wherein, neural network model is, with basic be input, with future profits rate and the following stability bandwidth be output machine mould
Type.
9. a kind of financial product future profits data prediction meanss characterized by comprising
Acquiring unit, for obtaining the basic of enterprise；
Input unit obtains the neural network mould for inputting the basic to the neural network model constructed in advance
Data are fluctuated in the enterprise of type output；
Determination unit, for determining enterprise's ranking of the enterprise based on the knowledge mapping constructed in advance；
Predicting unit predicts that the enterprise corresponds to financial product for fluctuating data and enterprise's ranking in conjunction with the enterprise
Future profits data.
10. a kind of financial product future profits data forecasting system characterized by comprising
Server and third party system；
Server, for obtaining the basic of enterprise from third party system；The basic is inputted to preparatory building
Neural network model, obtain the neural network model output enterprise fluctuation data；It is true based on the knowledge mapping constructed in advance
Enterprise's ranking of the fixed enterprise；Data and enterprise's ranking are fluctuated in conjunction with the enterprise, predict that the enterprise corresponds to financial product
Future profits data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811509102.0A CN109598623A (en) | 2018-12-11 | 2018-12-11 | A kind of financial product future profits data predication method, apparatus and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811509102.0A CN109598623A (en) | 2018-12-11 | 2018-12-11 | A kind of financial product future profits data predication method, apparatus and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109598623A true CN109598623A (en) | 2019-04-09 |
Family
ID=65962524
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811509102.0A Pending CN109598623A (en) | 2018-12-11 | 2018-12-11 | A kind of financial product future profits data predication method, apparatus and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109598623A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112131275A (en) * | 2020-09-23 | 2020-12-25 | 中国科学技术大学智慧城市研究院(芜湖) | Enterprise portrait construction method of holographic city big data model and knowledge graph |
| CN113222471A (en) * | 2021-06-04 | 2021-08-06 | 西安交通大学 | Asset wind control method and device based on new media data |
-
2018
- 2018-12-11 CN CN201811509102.0A patent/CN109598623A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112131275A (en) * | 2020-09-23 | 2020-12-25 | 中国科学技术大学智慧城市研究院(芜湖) | Enterprise portrait construction method of holographic city big data model and knowledge graph |
| CN113222471A (en) * | 2021-06-04 | 2021-08-06 | 西安交通大学 | Asset wind control method and device based on new media data |
| CN113222471B (en) * | 2021-06-04 | 2023-06-06 | 西安交通大学 | Asset wind control method and device based on new media data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Rakhra et al. | [Retracted] Implementing Machine Learning for Smart Farming to Forecast Farmers’ Interest in Hiring Equipment | |
| Derakhshanalavijeh et al. | Cost overrun in construction projects in developing countries, Gas-Oil industry of Iran as a case study | |
| CN106156809A (en) | For updating the method and device of disaggregated model | |
| US20120296698A1 (en) | Method and Apparatus of Forecasting Repurchase Inclination | |
| Liu et al. | Effect of buyer-supplier supply chain strategic collaboration on operating performance: evidence from Chinese companies | |
| WO2007079405A2 (en) | Predicting ad quality | |
| KR102031312B1 (en) | Method for providing p2p fiancial platform based real estate loan service | |
| CN108388974A (en) | Top-tier customer Optimum Identification Method and device based on random forest and decision tree | |
| CN107609771A (en) | A kind of supplier's value assessment method | |
| CN108154311A (en) | Top-tier customer recognition methods and device based on random forest and decision tree | |
| CN108596765A (en) | A kind of Electronic Finance resource recommendation method and device | |
| Moon et al. | Technology credit rating system for funding SMEs | |
| Moon et al. | Predicting construction cost index using the autoregressive fractionally integrated moving average model | |
| CN113642923A (en) | Bad asset pack value evaluation method based on historical collection urging data | |
| CN109598623A (en) | A kind of financial product future profits data predication method, apparatus and system | |
| Harkushenko et al. | Analysis of economic and mathematical models of information and communication technology (ICT) effect on the production output: Does the solow paradox exist? | |
| CN110322347A (en) | A kind of shot and long term strategy multiple-factor quantization capitalized method and device | |
| CN112581281A (en) | Product recommendation method and device, storage medium and electronic equipment | |
| CN113450158A (en) | Bank activity information pushing method and device | |
| Härting et al. | Cost-benefit considerations for data analytics-an SME-oriented framework enhanced by a management perspective and the process of idea generation | |
| Bäurle et al. | Forecasting the production side of GDP | |
| KR102018838B1 (en) | Method for providing bigdata weighted moving average based bidding information analysis service for online bidding participation | |
| Park et al. | Recommendation of investment portfolio for peer-to-peer lending with additional consideration of bidding period | |
| Ghandar et al. | The relationship between model complexity and forecasting performance for computer intelligence optimization in finance | |
| TWI248007B (en) | Method for evaluating market trade based on trend prediction |
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 | ||
| CB02 | Change of applicant information |
Address after: 100031 Xicheng District West Chang'an Avenue, No. 86, Beijing Applicant after: STATE GRID CORPORATION OF CHINA Applicant after: STATE GRID E-COMMERCE Co.,Ltd. Applicant after: Guowang Xiongan Finance Technology Group Co.,Ltd. Address before: 100031 Xicheng District West Chang'an Avenue, No. 86, Beijing Applicant before: STATE GRID CORPORATION OF CHINA Applicant before: STATE GRID E-COMMERCE Co.,Ltd. Applicant before: STATE GRID XIONG'AN FINANCIAL TECHNOLOGY Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190409 |
|
| RJ01 | Rejection of invention patent application after publication |