CN110264013A - Financial prediction method and system - Google Patents
Financial prediction method and system Download PDFInfo
- Publication number
- CN110264013A CN110264013A CN201910569581.3A CN201910569581A CN110264013A CN 110264013 A CN110264013 A CN 110264013A CN 201910569581 A CN201910569581 A CN 201910569581A CN 110264013 A CN110264013 A CN 110264013A
- Authority
- CN
- China
- Prior art keywords
- stock
- industry
- data
- prediction
- model
- 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
- 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
Abstract
The invention discloses a kind of financial prediction methods.The invention discloses a kind of systems for financial field industry Prediction of Stock Index, can be improved the accuracy rate of Prediction of Stock Index, and user is helped to quickly understand the trend of next all stock.The system includes that industry stock certificate data acquisition module, industry stock certificate data preprocessing module, industry stock certificate data training module, industry stock certificate data prediction module, industry Prediction of Stock Index value and true value comparison show display module.
Description
Technical field
The present invention relates to financial fields, and in particular to a kind of financial prediction method and system.
Background technique
Due to marketing campaign rule, business risk, government interference risk and purchasing power risk lead to finance in financial market
Market it is comprehensive, complexity greatly promotes.Accurate prediction for financial market, especially stock market is evaded as enterprise
Most important means in risk.It, can be with the further development of the depth learning technology of data mining technology and artificial intelligence
By these technologies to the regularity in financial market, intelligence is analyzed, and can be good at predicting stock market data
Trend.
Summary of the invention
The technical problem to be solved in the present invention is to provide a kind of financial prediction method and system, to artificial intelligence technology sum number
According to the digging technology application in various industries burning hot in recent years, propose a kind of be for financial field industry Prediction of Stock Index
System, can automatically predict the trend of next Zhou Hangye stock, while improving the accuracy rate of Prediction of Stock Index, help user quick
Solve the trend of next all stock.
In order to solve the above-mentioned technical problems, the present invention provides a kind of system for financial field industry Prediction of Stock Index,
Including industry stock certificate data acquisition module, industry stock certificate data preprocessing module, industry stock certificate data training module, industry stock
Data prediction module；
S1: the industry stock certificate data acquisition module, for obtaining various industries from initially to stock numerical value number so far
According to, include the data of the industries such as coal, steel, internet, be S3 constructed by model carry out data support；
S2: the industry stock certificate data preprocessing module is cleared up for the stock numeric data to various industries, weight
Structure；
S3: the industry stock training module, the data for constructing to S2 carry out building for prediction model；
S4: the industry stock certificate data prediction module carries out industry stock using training pattern for the model of S3 training
The data value of initial time to the following Friday day are predicted；
S5: the industry Prediction of Stock Index value and true value comparison show display module.
It is in one of the embodiments, a kind of function model similar to time series for industry stock certificate data, makes
The LSTM model for manually having good effect to time series models in smart field carries out the training of model.
The industry Prediction of Stock Index value and true value comparison show display module in one of the embodiments, and being used for will
The various industries of model prediction facilitate use from the displaying for initially carrying out line chart to the predicted value and truthful data in following next week
The credibility of family observing and nursing.
A method of for financial field industry Prediction of Stock Index, including；
S1: various industries are obtained from initially to stock numeric data so far, including the row such as coal, steel, internet
The data of industry；
S2: clearing up the stock numeric data of various industries, reconstruct；
S3: the data for constructing to S2 carry out building for prediction model；
S4: for the model of S3 training, industry stock initial time is carried out to the following Friday day using training pattern
Data value is predicted；
S5: comparison shows the industry Prediction of Stock Index value and true value.
It is in one of the embodiments, a kind of function model similar to time series for industry stock certificate data, makes
The LSTM model for manually having good effect to time series models in smart field carries out the training of model.
In one of the embodiments, by the various industries of model prediction from initially to the predicted value in following next week and very
The displaying of real data progress line chart.
A kind of computer equipment can be run on a memory and on a processor including memory, processor and storage
The step of computer program, the processor realizes any one the method when executing described program.
A kind of computer readable storage medium, is stored thereon with computer program, realization when which is executed by processor
The step of any one the method.
A kind of processor, the processor is for running program, wherein described program executes described in any item when running
Method.
Beneficial effects of the present invention:
It can automatically predict the trend of next Zhou Hangye stock, while improve the accuracy rate of Prediction of Stock Index, help user
Quickly understand the trend of next all stock.
Detailed description of the invention
Fig. 1 is the overall procedure schematic diagram of the system and method for financial industry Prediction of Stock Index.
Fig. 2 is industry stock certificate data acquisition module flow diagram.
Fig. 3 is industry stock certificate data preprocessing module flow diagram.
Fig. 4 is industry stock training module flow diagram.
Fig. 5 is industry stock certificate data prediction module flow diagram.
Fig. 6 is that industry Prediction of Stock Index value and true value comparison show display module flow diagram.
Specific embodiment
The present invention will be further explained below with reference to the attached drawings and specific examples, so that those skilled in the art can be with
It more fully understands the present invention and can be practiced, but illustrated embodiment is not as a limitation of the invention.
Fig. 1 is the overall procedure schematic diagram of the system and method for financial industry Prediction of Stock Index.In short, this method is main
Include:
Module 100) industry stock certificate data acquisition module, this module is for obtaining various industries from initially to stock so far
Numeric data includes the data of the industries such as coal, steel, internet, these data is deposited into database, for S3 institute structure
The model built carries out the support of data, specifically includes the following steps:
Step 110: the financial industry Stock Network resource for needing to crawl is determined by investigation
Step 120: crawling for data being carried out to determining resource using crawler frame
Step 130: the industry stock certificate data crawled is deposited into database
Module 200) industry stock certificate data preprocessing module, this module is for carrying out model training to industry stock certificate data
Data prediction.Specific step is as follows:
Step 210: data information is read from database
Step 220: the reason of encountering legal festivals and holidays suspension etc. for stock industry arrives up to now missing
Information carries out date completion
Step 230: it is that week is several that it is corresponding, which to convert the date, by the date-time crawled, and the logic of subsequent step is facilitated to sentence
Not, the date is converted into can be used the mode of timestamp week and converts.Such as in python, it can be used
Mktime, strptime are converted
Step 240: judge that the data corresponding time is several for week, then enter step 290 if it is Saturday, Sunday, it is on the contrary then
250 are entered step, reason was for normal condition, Saturday, Sunday suspension, so we are not processed
Step 250: the data of Mon-Fri are stored in chronological order
Step 260: to the default value of Mon-Fri, carrying out the average value filling in this week, form a complete weekly data
Set
Step 270: due to module 300 needs) carry out the sliding window in 2,3,4,5 week to data
Step 280: saving the result of preprocessed data into list
Module 300) industry stock training module, this module is for module 200) data of building, carry out prediction model
Build, the ability for enabling model precisely to predict following one week stock certificate data.Specifically comprise the following steps:
Step 310: to Sliding window data, carrying out the model training of time series models LSTM, obtain 4 LSTM training patterns
Step 320: the prediction of historical data is carried out using the model that 4 training obtain
Step 330: doing root-mean-square error calculating using model predication value and history true value, obtain the square of 4 models
Root error amount.
Step 340: the arrangement of 4 models is carried out for root mean square result
Step 350: according to step 340 as a result, obtain 4 models for this week, which model prediction it is more acurrate
Carry out the sequence of accuracy rate
Step 360: for the ranking results of step 350 model accuracy rate, carrying out the training that logic returns to and obtain logic time
Return model, determines that following one week data are higher using which accuracy rate in 4 models by Logic Regression Models
Module 400) industry stock certificate data prediction module, this module is for for module 300) model of training, use instruction
The data value for practicing model progress industry stock initial time to the following Friday day is predicted, the specific steps are as follows:
Step 410: by upper one week model accuracy rate situation, using Logic Regression Models, under predicting in four models
All most accurate models
Step 420: after obtaining which model more preferably to predict next week using, through trained LSTM model under
One weekly data is predicted
Step 430: obtained result being stored in database, front end is provided and shows use
Module 500) industry Prediction of Stock Index value and true value comparison show display module, this module is used for model prediction
Various industries facilitate user's observing and nursing from the displaying for initially carrying out line chart to the predicted value and truthful data in following next week
Credibility.Specific step is as follows:
Step 510: obtained from the database of model prediction from initially to the data of the following weekly forecasting
Step 520: two curves, including true value and predicted value are drawn by front end frame, it is intuitive to be supplied to user
Displaying.
Embodiment described above is only to absolutely prove preferred embodiment that is of the invention and being lifted, protection model of the invention
It encloses without being limited thereto.Those skilled in the art's made equivalent substitute or transformation on the basis of the present invention, in the present invention
Protection scope within.Protection scope of the present invention is subject to claims.
Claims (9)
1. a kind of system for financial field industry Prediction of Stock Index, which is characterized in that including industry stock certificate data acquisition module,
Industry stock certificate data preprocessing module, industry stock certificate data training module, industry stock certificate data prediction module.
S1: the industry stock certificate data acquisition module, for obtaining various industries from initially to stock numeric data so far, packet
The data of the industries such as coal, steel, internet have been included, have been the support that model constructed by S3 carries out data；
S2: the industry stock certificate data preprocessing module is cleared up for the stock numeric data to various industries, reconstruct；
S3: the industry stock training module, the data for constructing to S2 carry out building for prediction model；
S4: it is initial to carry out industry stock using training pattern for the model of S3 training for the industry stock certificate data prediction module
The data value of time to the following Friday day are predicted；
S5: the industry Prediction of Stock Index value and true value comparison show display module.
2. being used for the system of financial field industry Prediction of Stock Index as described in claim 1, which is characterized in that be directed to industry stock
Data are a kind of function models similar to time series, are had well using in artificial intelligence field to time series models
The LSTM model of effect carries out the training of model.
3. being used for the system of financial field industry Prediction of Stock Index as described in claim 1, which is characterized in that the industry stock
Predicted value and true value comparison show display module, for by the various industries of model prediction from initially pre- to following next week
Measured value and truthful data carry out the displaying of line chart, facilitate the credibility of user's observing and nursing.
4. a kind of method for financial field industry Prediction of Stock Index, which is characterized in that including；
S1: various industries are obtained from initially to stock numeric data so far, include the industries such as coal, steel, internet
Data；
S2: clearing up the stock numeric data of various industries, reconstruct；
S3: the data for constructing to S2 carry out building for prediction model；
S4: for the model of S3 training, the data of industry stock initial time to the following Friday day are carried out using training pattern
Value is predicted；
S5: comparison shows the industry Prediction of Stock Index value and true value.
5. being used for the method for financial field industry Prediction of Stock Index as claimed in claim 4, which is characterized in that be directed to industry stock
Data are a kind of function models similar to time series, are had well using in artificial intelligence field to time series models
The LSTM model of effect carries out the training of model.
6. a kind of method for financial field industry Prediction of Stock Index as claimed in claim 4, which is characterized in that model is pre-
The various industries of survey are from initially to the displaying of the predicted value in following next week and truthful data progress line chart.
7. 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 one of claim 4 to 6 the method when executing described program
Step.
8. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is held by processor
The step of any one of claim 4 to 6 the method is realized when row.
9. a kind of processor, which is characterized in that the processor is for running program, wherein right of execution when described program is run
Benefit requires 4 to 6 described in any item methods.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910569581.3A CN110264013A (en) | 2019-06-27 | 2019-06-27 | Financial prediction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910569581.3A CN110264013A (en) | 2019-06-27 | 2019-06-27 | Financial prediction method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110264013A true CN110264013A (en) | 2019-09-20 |
Family
ID=67922510
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910569581.3A Pending CN110264013A (en) | 2019-06-27 | 2019-06-27 | Financial prediction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110264013A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111192144A (en) * | 2020-01-03 | 2020-05-22 | 湖南工商大学 | Financial data prediction method, device, equipment and storage medium |
| WO2022141877A1 (en) * | 2020-12-31 | 2022-07-07 | 平安科技（深圳）有限公司 | Financial data processing method, apparatus and device, and storage medium |
-
2019
- 2019-06-27 CN CN201910569581.3A patent/CN110264013A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111192144A (en) * | 2020-01-03 | 2020-05-22 | 湖南工商大学 | Financial data prediction method, device, equipment and storage medium |
| WO2022141877A1 (en) * | 2020-12-31 | 2022-07-07 | 平安科技（深圳）有限公司 | Financial data processing method, apparatus and device, and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Selvan et al. | Data analysis in context-based statistical modeling in predictive analytics | |
| US10851636B1 (en) | Systems and methods for analyzing resource production | |
| CN111144542B (en) | Oil well productivity prediction method, device and equipment | |
| RU2502120C2 (en) | Systems and methods for optimisation of real-time extraction operations | |
| US20120078678A1 (en) | Method and system for estimation and analysis of operational parameters in workflow processes | |
| Montazar et al. | A fuzzy analytical hierarchy methodology for the performance assessment of irrigation projects | |
| Sahu et al. | Knowledge based decision support system for appraisement of sustainable partner under fuzzy cum non-fuzzy information | |
| CN106407305A (en) | Data mining system and method | |
| CN110264013A (en) | Financial prediction method and system | |
| CN108491956A (en) | A kind of broker's leaving office Prediction System and method | |
| El-Kholy et al. | Prediction of simulated cost contingency for steel reinforcement in building projects: ANN versus regression-based models | |
| CN105260944A (en) | Method for calculating statistical line loss based on LSSVM (Least Square Support Vector Machine) algorithm and association rule mining | |
| Calzolari et al. | Maintenance and testing effort modeled by linear and nonlinear dynamic systems | |
| CN107424026A (en) | Businessman's reputation evaluation method and device | |
| Bana | job2vec: Using language models to understand wage premia | |
| Zhang et al. | Comparative analysis of two resources-based economies: A study of policy recommendation toward sustainable development | |
| Castro-Gama et al. | A Bird’s-Eye View of Data Validation in the Drinking Water Industry of the Netherlands | |
| Kwakye et al. | Performance Management in the Oil and Gas Industry | |
| Senthurvelautham et al. | A Machine Learning-Based Job Forecasting And Trend Analysis System To Predict Future Job Markets Using Historical Data | |
| Takács et al. | Fuzzy cognitive map for student evaluation model | |
| Kumar et al. | Data Management and Visual Information Processing using Machine Learning | |
| Liu et al. | For intelligent debugging management of offshore oil engineering with big data | |
| Verheugd | Predicting water pipe failures: A Neural Hawkes Process approach | |
| US20230013443A1 (en) | Systems and processes for reconciling field costs | |
| Kherde et al. | An evaluation of project risk in Indian infrastructural projects using interpretative structural modeling |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190920 |