CN107833137A - Quantization trading strategies generation method and device, equipment and storage medium based on multiple-objection optimization - Google Patents
Quantization trading strategies generation method and device, equipment and storage medium based on multiple-objection optimization Download PDFInfo
- Publication number
- CN107833137A CN107833137A CN201711068210.4A CN201711068210A CN107833137A CN 107833137 A CN107833137 A CN 107833137A CN 201711068210 A CN201711068210 A CN 201711068210A CN 107833137 A CN107833137 A CN 107833137A
- Authority
- CN
- China
- Prior art keywords
- target
- weight
- strategy
- object function
- target elements
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
-
- 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
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Technology Law (AREA)
- Educational Administration (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The present invention provides a kind of quantization trading strategies generation method and device based on multiple-objection optimization, equipment and storage medium, and method includes：The target elements of Selection Strategy generation；Each target elements are scored on the sample of section, and scoring is standardized so that the score value of section sample is in the section of definition；Object function is formed, object function is made up of target elements and its respective weights, and weight includes multigroup；Object function survey using primary strategy, generates back and surveys result；Selection meets expected return and surveys result, generates multigroup multiple target weight；Weight is selected according to investor's preference and adjusted, exports preference policy.The present invention carrys out further optimisation strategy in multigroup weight by investor's preference selection multiple target factor composition quantization strategy according to preference weight, more embodiment investor's investment preference；By selecting single target factor high score to survey result returning for Evaluation Strategy, reduce tactful quantity and corresponding return surveys run time, reduce the burden of system resource.
Description
Technical field
Data processing field of the present invention, especially, it is related to the quantization based on multiple-objection optimization in finance data process field
Trading strategies generation method and device, equipment and storage medium.
Technical background
With the continuous popularization of financing risk, increasing investment and financing products arise at the historic moment, such as fund, bond, stock
The gradual mature in financial market of the financial product such as ticket and insurance, Investment ＆ Financing is also no longer the patent of the rich, general
The logical common people also change traditional financing risk, and are more than selecting deposits funds in bank.
But for ordinary people, it is numerous and complicated multiple for the people for not having economy and finance specialty background especially for those
Miscellaneous investment and financing products can usually allow them to be at a loss, so as to can only blindly follow the wind.In addition, purchase finance product
When, it is necessary first to understand product-specific investments direction in product description, including specification, risk class and corresponding additional strip
Money, and the word term generally on various financial product specifications is all more professional, investor is not if possessed certain Knowledge-based
Plinth is then easy to by flicker, and this just needs the professional person in the field to come for the investment guidance of these investors progress related fields
And planning.
In view of the above-mentioned problems, occurred the platform of not small amount transaction Investment ＆ Financing on the market at present, to be personal or
Person's business investor provides many data analyses and suggestion in formulation investment tactics, financing planning etc..Existing quantization
Most of trading strategies write generation by financial engineer, and by going back to the side for surveying historical data and screen tactful quality
Method, strategy caused by this method take time and effort, and most of is all invalidation policy.Still an alternative is that pass through definition
Multiple-factor carries out factor availability inspection, then carries out the artificial validity for investigating Assessing parameters, such a method be also required for through
The personnel tested, efficiency are low, it is difficult to suitable for turn of the market.
Current investment tactics selects the target elements of preference built-up by investor, but undisclosed pair in the prior art
The technical literature that target elements are further optimized.
The content of the invention
The purpose of the present invention generates to avoid drawbacks described above from providing a kind of quantization trading strategies based on multiple-objection optimization
Method and device, equipment and storage medium.
To reach above-mentioned purpose, the present invention provides a kind of quantization trading strategies generation method based on multiple-objection optimization, leads to
Cross investor and like determination target elements and optimization respective weights generation compared with dominant strategy, so that investor is opened on this basis
Hair, meets investor's preference, and can greatly improve operating efficiency, allows strategy is quick to land.
A kind of quantization trading strategies generation method based on multiple-objection optimization provided by the invention, comprises the following steps：Choosing
The target elements of strategy generating are taken, the target elements are Financial Attribute parameter, and including but not limited to yield curve, Alpha receive
Benefit, beta income, Sharpe Ratio, income withdraw ratio, maximum is withdrawn, profit and loss ratio, continuously lose the cycle, continuously get a profit the cycle；
Each target elements are scored on the sample of section, and scoring is standardized so that section sample
This score value is calculated as f in the section of definition, the target elements score valuei；
Object function is formed, the object function is made up of target elements and its respective weights, and the weight includes multigroup；
Object function survey using primary strategy, generates back and surveys result；
Arrange returning survey result, selection meets expected return and surveys result, the multigroup corresponding multiple target weight of generation；
Weight is selected according to investor's preference and adjusted, exports preference policy.
The section sample includes but is not limited to the market data of multiple stocks, bond, fund.
The object function is expressed as:
Wherein, n be selection participates in back survey target elements quantity, fiFor the score value of i-th of target, wiFor i-th of mesh
Target weight.
In the target elements that the determination participates in back surveying, the target elements are Financial Attribute parameter, are included but is not limited to
Yield curve, Alpha's income, beta income, Sharpe Ratio, income withdraw ratio, maximum is withdrawn, profit and loss ratio, continuously loss week
Before phase, continuous profit cycle step, in addition to primary strategy generating step, the primary strategy are used to enter the object function
Go back survey.
The present invention also provides a kind of quantization trading strategies generating means based on multiple-objection optimization, and above-mentioned strategy system accordingly exists
Optimize generation in the system.Accordingly include：
Selecting module, for the target elements of Selection Strategy generation, the target elements are Financial Attribute parameter, including but
It is not limited to that yield curve, Alpha's income, beta income, Sharpe Ratio, income withdraw ratio, maximum is withdrawn, profit and loss ratio, continuous lose
The damage cycle, continuously get a profit the cycle；
Grading module, place is standardized for being scored on the sample of section each target elements, and to scoring
Reason so that the score value of section sample is in the section of definition；
Object function comprising modules, object function being formed, the object function is made up of target elements and its respective weights,
The weight includes multigroup；
Return and survey module, for object function survey using primary strategy, generate back and survey result；
Return survey result and select excellent module, for arranging returning survey result, selection meets expected time and surveys result, generates more
The corresponding multiple target weight of group；
Tactful output module, for selecting weight according to investor's preference and adjusting, export preference policy.
A kind of quantization trading strategies generating means based on multiple-objection optimization of the present invention also include：
Primary policy generation module, the primary strategy are used to the object function survey.
Tactful pushing module, for the target of counting user preference, and corresponding strategy will be pushed to user.
The present invention also provides a kind of quantization trading strategies generation equipment based on multiple-objection optimization, including：
One or more processors；Memory；And one or more programs, wherein one or more of program storages
In the memory and it is configured as by one or more of computing devices, one or more of programs include being used for
Perform the instruction for quantifying the either method in trading strategies generation method based on multiple-objection optimization.
The present invention also provides a kind of computer-readable storage medium, and the storage medium is stored with one or more programs, described
One or more programs include instruction, and the instruction makes when being performed by the quantization trading strategies equipment based on multiple-objection optimization
Obtain the trading strategies equipment that quantifies based on multiple-objection optimization and perform the quantization trading strategies generation side based on multiple-objection optimization
Either method in method.
Compared with prior art, beneficial effects of the present invention are：
The present invention is weighed by investor's preference selection multiple target factor composition quantization strategy in multigroup weight according to preference
Carry out further optimisation strategy again, quantization strategy more refines, and more embodies investor's investment preference；
By selecting single target factor high score to survey result returning for Evaluation Strategy, reduce tactful quantity and corresponding time
Run time is surveyed, reduces the burden of system resource.
Brief description of the drawings
Fig. 1 is the quantization trading strategies generation method flow chart of the invention based on multiple-objection optimization.
Fig. 2 is the quantization trading strategies generation method device architecture figure of the invention based on multiple-objection optimization.
Embodiment
For a kind of quantization trading strategies generation method based on multiple-objection optimization of the present invention, in practical application scene
In, those skilled in the art can be developed according to method provided by the present invention corresponding function computer background program or
Computer software realizes, further, with reference to mobile terminal (or computer terminal) and financial institution, (including investment securities are public
Department) etc. service terminal can realize technical scheme provided by the present invention.
Embodiment one
Fig. 1 shows the first embodiment of the present invention, a kind of quantization trading strategies generation method based on multiple-objection optimization
Flow, comprise the following steps：
Step 101, the target elements of strategy generating are determined, the target elements are Financial Attribute parameter.
Selected to determine the target elements of strategy generating by user, selected by the investment preference of user, participate in strategy generating
Target elements can include one or more.Specifically, the factor is Financial Attribute parameter, and including but not limited to income is bent
Line, Alpha's income, beta income, Sharpe Ratio, income withdraw ratio, maximum is withdrawn, profit and loss ratio, continuously lose the cycle, be continuous
Get a profit the cycle.
Step 102, each target elements are scored on the sample of section, and scoring is standardized, made
The score value of section sample is obtained in user-defined section, for example [0,100] section, the target elements score value are calculated as fi。
Section sample includes but is not limited to the market data of multiple stocks, bond, fund.Specifically, by taking stock as an example, mark
The target elements of the stock pond interval censored data are scored by the stock pond that quasi- screening needs, and are standardized place to scoring
Reason so that score value is in user-defined section, for example (the positive bigger score value of index is higher, and negative sense index is smaller for [0,100] scope
Score value is higher), the score value of target elements corresponding to personal share is obtained, the score value of target elements is with fiRepresent.
Step 103, multiple-factor object function is built, using weighting method by target elements and its respective weights combination producing institute
Object function is stated, the weight includes multigroup.
Multiple-factor object function is built, the object function of composition includes one or more target elements, in this implementation
In example, multiple target elements composition object functions, each target elements relative set weight, by single target elements of selecting stocks are selected
High score and its respective weights collect carry out comprehensive grading, the weight is variable multigroup.The object function is expressed as:
Wherein, n be selection participates in back survey destination number, fiFor the score value of i-th of target, wiFor i-th target
Weight.
Step 104, object function survey using primary strategy, generate back and survey result.
The present embodiment also includes primary strategy generating step, in the multiple primary strategies of strategy generating system generation, the plan
Slightly generated through system optimization, can also write and form for investor.Object function survey using primary strategy, generates back survey
As a result.Specifically, in addition to returning survey result it is standardized so that return the score value for surveying result in user-defined area
Between, for example [0,100] section, the method for standardization be identical with step 102.
Step 105, arrange returning survey result, selection meets expected return and surveys result, the multigroup corresponding more mesh of generation
Mark weight.
It is ranked up to returning survey result, results are surveyed in several forward times of screening score value, determine each target weight.Specifically
Three Alpha's income, beta income, Sharpe Ratio target elements structure target letters are chosen in ground, in the present embodiment, investor
Number, it is assumed that the score value of three target elements is respectively 91,93,95, then the output score value expression way of the object function is：
F=91*w1+93*w2+95*w3
Screen back the highest score 92 for surveying result, i.e. 92=91*w1+93*w2+95*w3, thus can determine that multigroup weight
(w1,w2,w3), in the present embodiment, the weight of multiple objective function includes two or more numbers for 0, it is preferable that
In the present embodiment, to avoid the time-consuming increase operand of system operations, the weight takes one decimal place.Specifically, using more
Objective optimization algorithm optimizes, and obtains Pareto optimal solutions.Weight (the w of generation1,w2,w3) combination can be：(0.5,0.5,
0) user's choice is treated in, (0.6,0.3,0.1), (0.7,0.1,0.2), the weight combination.Optimized algorithm include but is not limited into
Change algorithm (Evolutionary Algorithm), particle cluster algorithm (Particle Swarm Optimization, PSO), examination
Wrong method.
Step 106, weight is selected according to investor's preference and adjusted, export preference policy.
The weight that investor can like selection respective objects function according to investment generates optimisation strategy, if investor more pays close attention to
Be Alpha's income, its can be inclined to Alpha's income weight it is larger object function structure optimisation strategy, (selection 0.7,
0.1,0.2) optimisation strategy is built with the respective objects factor；If it is more concerned with beta income, while Sharpe Ratio is also
One focus, then can be with selection target weight (0.6,0.3,0.1) and respective objects factor structure optimisation strategy；If it is from power
Think that Alpha's income and beta income more meet its investment preference from the point of view of recombination, target weight (0.5,0.5,0) may be selected
Optimisation strategy is built with the respective objects factor.
Embodiment two
There is provided with a kind of quantization trading strategies generation method embodiment one based on multiple-objection optimization of the invention described above
Method is corresponding, and referring to Fig. 2, present invention also offers a kind of quantization trading strategies generation system based on multiple-objection optimization to implement
Example two, in this embodiment, the system include：
Selecting module 201, for determining the target elements of strategy generating, the target elements are Financial Attribute parameter.
Selected to determine the target elements of strategy generating by user, selected by the investment preference of user, participate in strategy generating
Target elements can include one or more.Specifically, the factor is Financial Attribute parameter, and including but not limited to income is bent
Line, Alpha's income, beta income, Sharpe Ratio, income withdraw ratio, maximum is withdrawn, profit and loss ratio, continuously lose the cycle, be continuous
Get a profit the cycle.
Grading module 202, it is standardized for being scored on the sample of section each target elements, and to scoring
Processing so that the score value of section sample is in user-defined section, such as [0,100] section, and the target elements score value is calculated as
fi。
Section sample includes but is not limited to the market data of multiple stocks, bond, fund.Specifically, by taking stock as an example, mark
The target elements in the stock pond are scored by the stock pond that quasi- screening needs, and scoring is standardized so that point
Value is in user-defined section, for example (the positive bigger score value of index is higher, and the smaller score value of negative sense index is got over for [0,100] scope
It is high), the score value of target elements corresponding to personal share is obtained, the score value of target elements is with fiRepresent.
Object function comprising modules 203, for building multiple-factor object function, using weighting method by target elements and its phase
Object function described in weight combination producing is answered, the weight includes multigroup.
Specifically, multiple-factor object function is built, the object function of composition includes two or more target elements, often
Individual target elements relative set weight, the high score of single target elements of selecting stocks and its respective weights are collected and integrate commenting
Point, the weight is random variable multigroup.The object function is expressed as:
Wherein, n be selection participates in back survey destination number, fiResult, w are surveyed for i-th of returning for targetiFor i-th of target
Weight.
Return and survey module 204, for object function survey using primary strategy, generate back and survey result.
The present embodiment also includes primary strategy generating step, in the multiple primary strategies of strategy generating system generation, the plan
Slightly generated through system optimization, can also write and form for investor.Object function survey using primary strategy, generates back survey
As a result.Specifically, in addition to returning survey result it is standardized so that return the score value for surveying result in user-defined area
Between, for example [0,100] section, the method for standardization be identical with step 102.
Return survey result and select excellent module 205, for arranging returning survey result, selection meets expected time and surveys result, life
Into multigroup corresponding multiple target weight.
It is ranked up to returning survey result, results are surveyed in several forward times of screening score value, determine each target weight.Specifically
Three Alpha's income, beta income, Sharpe Ratio target elements structure target letters are chosen in ground, in the present embodiment, investor
Number, it is assumed that the score value of three target elements is respectively 91,93,95, then the output score value expression way of the object function is：
F=91*w1+93*w2+95*w3
Screen back the highest score 92 for surveying result, i.e. 92=91*w1+93*w2+95*w3, thus can determine that multigroup weight
(w1,w2,w3), in the present embodiment, the weight of multiple objective function includes two or more numbers for 0, it is preferable that
In the present embodiment, to avoid the time-consuming increase operand of system operations, the weight takes one decimal place.Specifically, using more
Objective optimization algorithm optimizes, and obtains Pareto optimal solutions.Weight (the w of generation1,w2,w3) combination can be：(0.5,0.5,
0) user's choice is treated in, (0.6,0.3,0.1), (0.7,0.1,0.2), the weight combination.Optimized algorithm include but is not limited into
Change algorithm (Evolutionary Algorithm), particle cluster algorithm (Particle Swarm Optimization, PSO), examination
Wrong method.
Tactful output module 206, for selecting weight according to investor's preference and adjusting, export preference policy.
The weight that investor can like selection respective objects function according to investment generates optimisation strategy, if investor more pays close attention to
Be Alpha's income, its can be inclined to Alpha's income weight it is larger object function structure optimisation strategy, (selection 0.7,
0.1,0.2) optimisation strategy is built with the respective objects factor；If it is more concerned with beta income, while Sharpe Ratio is also
One focus, then can be with selection target weight (0.6,0.3,0.1) and respective objects factor structure optimisation strategy；If it is from power
Think that Alpha's income and beta income more meet its investment preference from the point of view of recombination, target weight (0.5,0.5,0) may be selected
Optimisation strategy is built with the respective objects factor.
Preferably, in addition to tactful pushing module 207, for the target elements of counting user preference, and pushed to user
Corresponding strategy.
In actual applications, investor chooses target elements in selecting module 201, and is selected in tactful output module 206
While selecting respective objects Factor Weight, system programming count simultaneously records investor's selection target factor and respective weights size
Preference, the target elements and respective weights for selecting preference are carried out with statistical analysis, tactful pushing module generates statistical result, and will
The more preference generation strategy real time propelling movement of occurrence frequency optimizes based on this to investor, user, generation transaction plan
Slightly.
Embodiment three
The present invention also provides a kind of quantization trading strategies generation equipment based on multiple-objection optimization, and the equipment includes：One
Or multiple processors, memory, and one or more programs, wherein one or more program storages are in the memory
And be configured as by one or more of computing devices, one or more of programs include above-mentioned based on more for performing
The instruction for quantifying the either method in trading strategies generation method embodiment of objective optimization.
Example IV
The present invention also provides a kind of computer-readable storage medium, and the storage medium is stored with one or more programs, described
One or more programs include instruction, and the instruction makes when being performed by the quantization trading strategies equipment based on multiple-objection optimization
Obtain the trading strategies equipment that quantifies based on multiple-objection optimization and perform the above-mentioned quantization trading strategies life based on multiple-objection optimization
Into the either method in embodiment of the method.
A kind of quantization trading strategies generation method and system based on multiple-objection optimization provided by the present invention are entered above
Go detailed introduction, and applied specific case and the principle and embodiment of the present invention are set forth, above example
Explanation be only intended to help and understand the present processes and core concept.Meanwhile for those of ordinary skill in the art, according to
According to the thought of the present invention, in specific embodiments and applications there will be changes.In summary, this specification content
It should not be construed as limiting the invention.
Claims (8)
- A kind of 1. quantization trading strategies generation method based on multiple-objection optimization, suitable in the quantization transaction based on multiple-objection optimization Performed in tactful equipment, it is characterised in that comprise the following steps：A. Selection Strategy generation target elements, the target elements are Financial Attribute parameter, including but not limited to yield curve, Alpha's income, beta income, Sharpe Ratio, income withdraw ratio, maximum is withdrawn, profit and loss ratio, continuously loss cycle, continuous profit Cycle；B. each target elements are scored on the sample of section, and scoring is standardized so that section sample Score value be calculated as f in interval of definition, the target elements score valuei；C. multiple-factor object function is built, using weighting method by target letter described in target elements and its respective weights combination producing Number, the weight include multigroup；C. object function survey using primary strategy, generate back and survey result；D. arrange returning survey result, selection meets expected return and surveys result, the multigroup corresponding multiple target weight of generation；E. weight is selected according to investor's preference and adjusted, export preference policy.
- 2. trading strategies generation method is quantified based on multiple target as claimed in claim 1, it is characterised in that the section sample Including but not limited to multiple stocks, bond, the section market data of fund.
- 3. trading strategies generation method is quantified based on multiple target as claimed in claim 1, it is characterised in that the object function It is expressed as:<mrow> <mi>F</mi> <mo>=</mo> <munderover> <mo>&Sigma;</mo> <mrow> <mi>i</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>n</mi> </munderover> <msub> <mi>f</mi> <mi>i</mi> </msub> <msub> <mi>w</mi> <mi>i</mi> </msub> </mrow>Wherein, n be selection participates in back survey destination number, fiResult, w are surveyed for i-th of returning for targetiFor the power of i-th of target Weight.
- 4. trading strategies generation method is quantified based on multiple target as claimed in claim 1, it is characterised in that in the step a Before, in addition to primary strategy generating step, the primary strategy is for the object function survey.
- A kind of 5. quantization trading strategies generating means based on multiple-objection optimization, suitable for residing in the quantization based on multiple-objection optimization In trading strategies equipment, it is characterised in that including with lower module：Selecting module, for the target elements of Selection Strategy generation, the target elements are Financial Attribute parameter, including but unlimited In yield curve, Alpha's income, beta income, Sharpe Ratio, income withdraws ratio, maximum is withdrawn, profit and loss ratio, continuous loss week Phase, continuously get a profit the cycle；Grading module, it is standardized, makes for being scored on the sample of section each target elements, and to scoring The score value of section sample is obtained in the section of definition；Object function comprising modules, object function is formed, the object function is made up of target elements and its respective weights, described Weight includes multigroup；Return and survey module, for object function survey using primary strategy, generate back and survey result；Return survey result and select excellent module, for arranging returning survey result, selection meets expected time and surveys result, generates multigroup phase The multiple target weight answered；Tactful output module, for selecting weight according to investor's preference and adjusting, export preference policy.
- 6. trading strategies generating means are quantified based on multiple target as claimed in claim 5, it is characterised in that described device is also wrapped Include：Primary policy generation module, the primary strategy are used to the object function survey；Tactful pushing module, corresponding strategy is pushed for the target elements of counting user preference, and to user.
- 7. a kind of quantization trading strategies generation equipment based on multiple-objection optimization, including：One or more processors；Memory；AndOne or more programs, wherein one or more of program storages are in the memory and are configured as by described one Individual or multiple computing devices, one or more of programs include being used to perform according in claim 1-4 methods describeds The instruction of either method.
- 8. a kind of computer-readable storage medium, the storage medium is stored with one or more programs, one or more of programs Including instruction, the instruction by the quantization trading strategies equipment based on multiple-objection optimization when being performed so that described to be based on more mesh The trading strategies equipment that quantifies of mark optimization performs the either method in claim 1-4 methods describeds.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711068210.4A CN107833137A (en) | 2017-11-03 | 2017-11-03 | Quantization trading strategies generation method and device, equipment and storage medium based on multiple-objection optimization |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711068210.4A CN107833137A (en) | 2017-11-03 | 2017-11-03 | Quantization trading strategies generation method and device, equipment and storage medium based on multiple-objection optimization |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107833137A true CN107833137A (en) | 2018-03-23 |
Family
ID=61650522
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711068210.4A Pending CN107833137A (en) | 2017-11-03 | 2017-11-03 | Quantization trading strategies generation method and device, equipment and storage medium based on multiple-objection optimization |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107833137A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108629692A (en) * | 2018-05-03 | 2018-10-09 | 龙锋智能科技（福建）有限公司 | Investment decision generation, evaluation method, medium and the equipment of fund product |
| CN109711995A (en) * | 2019-01-03 | 2019-05-03 | 周鸣籁 | A method of automatically generating the trading strategies in time series |
| CN110472827A (en) * | 2019-07-10 | 2019-11-19 | 阿里巴巴集团控股有限公司 | System strategy method for early warning, device, server and readable storage medium storing program for executing |
| CN110517142A (en) * | 2019-08-28 | 2019-11-29 | 中国银行股份有限公司 | The output method and device of Policy evaluation information |
| WO2019242145A1 (en) * | 2018-06-21 | 2019-12-26 | 平安科技（深圳）有限公司 | Method and device for constructing bond etf, and computer-readable storage medium |
| WO2020000701A1 (en) * | 2018-06-25 | 2020-01-02 | 平安科技（深圳）有限公司 | Fund adaptation method and system, computer device, and storage medium |
| CN111242311A (en) * | 2020-01-06 | 2020-06-05 | 高盈量化云科技（深圳）有限公司 | Multi-line set effective output method |
| CN112035533A (en) * | 2020-09-03 | 2020-12-04 | 中山大学 | System resource scheduling method and device based on multi-parameter quantization strategy feedback |
| CN115829368A (en) * | 2022-11-04 | 2023-03-21 | 杭州牛剑资产管理有限公司 | Transaction strategy evaluation method based on multiple factors |
| CN116739789A (en) * | 2023-08-16 | 2023-09-12 | 中信证券股份有限公司 | Virtual article return information sending method and device, electronic equipment and medium |
-
2017
- 2017-11-03 CN CN201711068210.4A patent/CN107833137A/en active Pending
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108629692A (en) * | 2018-05-03 | 2018-10-09 | 龙锋智能科技（福建）有限公司 | Investment decision generation, evaluation method, medium and the equipment of fund product |
| WO2019242145A1 (en) * | 2018-06-21 | 2019-12-26 | 平安科技（深圳）有限公司 | Method and device for constructing bond etf, and computer-readable storage medium |
| WO2020000701A1 (en) * | 2018-06-25 | 2020-01-02 | 平安科技（深圳）有限公司 | Fund adaptation method and system, computer device, and storage medium |
| CN109711995A (en) * | 2019-01-03 | 2019-05-03 | 周鸣籁 | A method of automatically generating the trading strategies in time series |
| CN110472827A (en) * | 2019-07-10 | 2019-11-19 | 阿里巴巴集团控股有限公司 | System strategy method for early warning, device, server and readable storage medium storing program for executing |
| CN110517142A (en) * | 2019-08-28 | 2019-11-29 | 中国银行股份有限公司 | The output method and device of Policy evaluation information |
| CN111242311A (en) * | 2020-01-06 | 2020-06-05 | 高盈量化云科技（深圳）有限公司 | Multi-line set effective output method |
| CN112035533A (en) * | 2020-09-03 | 2020-12-04 | 中山大学 | System resource scheduling method and device based on multi-parameter quantization strategy feedback |
| CN112035533B (en) * | 2020-09-03 | 2022-07-12 | 中山大学 | System resource scheduling method and device based on multi-parameter quantization strategy feedback |
| CN115829368A (en) * | 2022-11-04 | 2023-03-21 | 杭州牛剑资产管理有限公司 | Transaction strategy evaluation method based on multiple factors |
| CN116739789A (en) * | 2023-08-16 | 2023-09-12 | 中信证券股份有限公司 | Virtual article return information sending method and device, electronic equipment and medium |
| CN116739789B (en) * | 2023-08-16 | 2023-12-19 | 中信证券股份有限公司 | Virtual article return information sending method and device, electronic equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107833137A (en) | Quantization trading strategies generation method and device, equipment and storage medium based on multiple-objection optimization | |
| Almahdi et al. | An adaptive portfolio trading system: A risk-return portfolio optimization using recurrent reinforcement learning with expected maximum drawdown | |
| Gaddy et al. | Venture capital and cleantech: The wrong model for energy innovation | |
| Chourmouziadis et al. | An intelligent short term stock trading fuzzy system for assisting investors in portfolio management | |
| Chang et al. | A hybrid financial performance evaluation model for wealth management banks following the global financial crisis | |
| CN107798609A (en) | Quantify trading strategies generation method and device, equipment and storage medium | |
| Huang et al. | An integrated DEA-MODM methodology for portfolio optimization | |
| CN106294694A (en) | Asset allocation big data analysis control system | |
| CN107808337A (en) | Factor Clustering and device, equipment and storage medium | |
| Smith et al. | Predicting firm-level bankruptcy in the Spanish economy using extreme gradient boosting | |
| Zhu et al. | [Retracted] Fuzzy Decision‐Making Analysis of Quantitative Stock Selection in VR Industry Based on Random Forest Model | |
| CN112884590A (en) | Power grid enterprise financing decision method based on machine learning algorithm | |
| Pai et al. | Metaheuristic multi-objective optimization of constrained futures portfolios for effective risk management | |
| Agarwal et al. | Merger and acquisition pricing using agent based modelling | |
| Li et al. | A medium to long-term multi-influencing factor copper price prediction method based on CNN-LSTM | |
| CN107578130A (en) | A kind of method of the copper forecasting of futures prix of the TSK fuzzy systems of structure and parameter combination learning | |
| Lin et al. | Analytically pricing European options under a new two-factor Heston model with regime switching | |
| Moubariki et al. | Enhancing cash management using machine learning | |
| Peachavanish | Dual time frame relative strength stock selection using fuzzy logic | |
| Siddiqui et al. | Comparison of garch model and artificial neural network for mutual fund's growth prediction | |
| Ghandar et al. | The relationship between model complexity and forecasting performance for computer intelligence optimization in finance | |
| Tang | [Retracted] A Study of the Spatial Effects of Financial Support and Economic Growth under Optimal Control of Nonlinear Generalized Complex Systems | |
| Luo et al. | An empirical study on the correlation structure of credit spreads based on the dynamic and pair copula functions | |
| Han | Research on influencing factors of stock returns based on multiple regression and artificial intelligence model | |
| Nawani et al. | A Quantitative approach to create a Hybrid stock filtering platform |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180323 |