CN110458328A - Black Swan event decision method and device based on subjective and objective associated prediction - Google Patents
Black Swan event decision method and device based on subjective and objective associated prediction Download PDFInfo
- Publication number
- CN110458328A CN110458328A CN201910623881.5A CN201910623881A CN110458328A CN 110458328 A CN110458328 A CN 110458328A CN 201910623881 A CN201910623881 A CN 201910623881A CN 110458328 A CN110458328 A CN 110458328A
- Authority
- CN
- China
- Prior art keywords
- prediction
- predicted events
- subjective
- decision
- predicted
- 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 41
- 241000272778 Cygnus atratus Species 0.000 claims abstract description 44
- 238000012545 processing Methods 0.000 claims abstract description 15
- 238000007619 statistical method Methods 0.000 claims abstract description 14
- 238000010801 machine learning Methods 0.000 claims abstract description 13
- 238000004458 analytical method Methods 0.000 claims description 7
- 238000012954 risk control Methods 0.000 abstract description 8
- 238000012549 training Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 241001522296 Erithacus rubecula Species 0.000 description 2
- 241000287433 Turdus Species 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 241000272814 Anser sp. Species 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/34—Betting or bookmaking, e.g. Internet betting
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07F—COIN-FREED OR LIKE APPARATUS
- G07F17/00—Coin-freed apparatus for hiring articles; Coin-freed facilities or services
- G07F17/32—Coin-freed apparatus for hiring articles; Coin-freed facilities or services for games, toys, sports, or amusements
- G07F17/3286—Type of games
- G07F17/3288—Betting, e.g. on live events, bookmaking
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Quality & Reliability (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Software Systems (AREA)
- Operations Research (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Primary Health Care (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The black Swan event decision method and device based on subjective and objective associated prediction that the invention discloses a kind of, wherein this method comprises: obtaining predicted events and history data set；Predicted events are predicted by prediction model to obtain the first prediction data；Wherein, prediction model is by preset machine learning method to history data set generation for statistical analysis；It is searched and matched second prediction data of predicted events in default subjective experience database；First prediction data and the second prediction data are compared into work difference processing and obtain prediction difference, decision is carried out to predicted events according to prediction difference.This method, which passes through, combines subjective and objective two distinct types of prediction technique, gives a kind of effective black Swan event decision index, can be used for risk control, greatly reduce loss.
Description
Technical field
The present invention relates to technical field of risk control, in particular to a kind of black Swan event based on subjective and objective associated prediction
Decision-making technique and device.
Background technique
For risk management, black Swan event (Black Swan Event, BSE), that is, will cause very big shadow
Loud and consequence accident, can usually impact the normal production order of nature and society.Black Swan event is usually positive ordinary affair
The reverse side event of part, the two can not occur simultaneously, and normal event often has biggish probability of happening, and black Swan event is then
Only lesser probability of happening.So people again cannot be using the reverse side small probability event of all normal events as will
The black Swan event of generation is prevented and is handled, because such cost is too big.So the challenge of black Swan event is from it
Once causing tremendous influence, only focus on that then cost is too big in it, whether itself can occur and very uncertain.
Summary of the invention
The present invention is directed to solve at least some of the technical problems in related technologies.
For this purpose, an object of the present invention is to provide a kind of black Swan event decision sides based on subjective and objective associated prediction
Method, this method, which passes through, combines subjective and objective two distinct types of prediction technique, gives a kind of effective black Swan event decision
Index can be used for risk control, greatly reduce loss.
It is another object of the present invention to propose a kind of black Swan event decision device based on subjective and objective associated prediction.
In order to achieve the above objectives, one aspect of the present invention embodiment proposes a kind of black Swan based on subjective and objective associated prediction
Event decision method, comprising:
Obtain predicted events and history data set；
The predicted events are predicted by prediction model to obtain the first prediction data；Wherein, the prediction model
It is by preset machine learning method to history data set generation for statistical analysis；
It is searched and matched second prediction data of the predicted events in default subjective experience database；
First prediction data and second prediction data are compared into work difference processing and obtain prediction difference, according to
The prediction difference carries out decision to the predicted events.
The black Swan event decision method based on subjective and objective associated prediction of the embodiment of the present invention, by obtaining predicted events
And history data set；Predicted events are predicted by prediction model to obtain the first prediction data；In default subjective experience number
It is searched and matched second prediction data of predicted events according in library；First prediction data and the second prediction data are compared into work
Difference processing obtains prediction difference, carries out decision to predicted events according to prediction difference.As a result, by subjective and objective prediction come to prediction
Event carries out reliability prediction, to improve the performance of identification black Swan event and risk control.
In addition, the black Swan event decision method according to the above embodiment of the present invention based on subjective and objective associated prediction may be used also
With following additional technical characteristic:
Further, in one embodiment of the invention, it is described according to the prediction difference to the predicted events into
Row decision, comprising:
Judge that the prediction difference is less than preset threshold, it is determined that the predicted events are security incident；
Judge that the prediction difference is more than or equal to the preset threshold, it is determined that the predicted events are risk case.
Further, in one embodiment of the invention, the history data set be in preset period with it is described pre-
The relevant historical data of survey event.
Further, in one embodiment of the invention, by the Logic Regression Models of scikit-learn to described
History data set is for statistical analysis.
Further, in one embodiment of the invention, further includes:
Obtain multiple prediction data relevant to the predicted events；
Analysis is carried out to the multiple prediction data relevant to the predicted events and generates the default subjective experience number
According to library.
In order to achieve the above objectives, another aspect of the present invention embodiment proposes a kind of night based on subjective and objective associated prediction
Goose event decision device, comprising:
First obtains module, for obtaining predicted events and history data set；
Objective making decision module obtains the first prediction data for being predicted by prediction model the predicted events；
Wherein, the prediction model is by preset machine learning method to history data set generation for statistical analysis；
Subjective decision module, it is pre- with the predicted events matched second for being searched in default subjective experience database
Measured data；
Decision output module, for first prediction data and second prediction data to be compared work difference processing
Prediction difference is obtained, decision is carried out to the predicted events according to the prediction difference.
The black Swan event decision device based on subjective and objective associated prediction of the embodiment of the present invention, by obtaining predicted events
And history data set；Predicted events are predicted by prediction model to obtain the first prediction data；In default subjective experience number
It is searched and matched second prediction data of predicted events according in library；First prediction data and the second prediction data are compared into work
Difference processing obtains prediction difference, carries out decision to predicted events according to prediction difference.As a result, by subjective and objective prediction come to prediction
Event carries out reliability prediction, to improve the performance of identification black Swan event and risk control.
In addition, the black Swan event decision device according to the above embodiment of the present invention based on subjective and objective associated prediction may be used also
With following additional technical characteristic:
Further, in one embodiment of the invention, it is described according to the prediction difference to the predicted events into
Row decision, comprising:
Judge that the prediction difference is less than preset threshold, it is determined that the predicted events are security incident；
Judge that the prediction difference is more than or equal to the preset threshold, it is determined that the predicted events are risk case.
Further, in one embodiment of the invention, the history data set be in preset period with it is described pre-
The relevant historical data of survey event.
Further, in one embodiment of the invention, by the Logic Regression Models of scikit-learn to described
History data set is for statistical analysis.
Further, in one embodiment of the invention, further includes:
Second obtains module, for obtaining multiple prediction data relevant to the predicted events；
Generation module, it is described pre- for carrying out analysis generation to the multiple prediction data relevant to the predicted events
If subjective experience database.
The additional aspect of the present invention and advantage will be set forth in part in the description, and will partially become from the following description
Obviously, or practice through the invention is recognized.
Detailed description of the invention
Above-mentioned and/or additional aspect and advantage of the invention will become from the following description of the accompanying drawings of embodiments
Obviously and it is readily appreciated that, in which:
Fig. 1 is the black Swan event decision method flow based on subjective and objective associated prediction according to one embodiment of the invention
Figure；
Fig. 2 is to have carried out assessment schematic diagram according to 48 group round robins of world cup in 2018 of one embodiment of the invention；
Fig. 3 is the black Swan event decision apparatus structure based on subjective and objective associated prediction according to one embodiment of the invention
Schematic diagram.
Specific embodiment
The embodiment of the present invention is described below in detail, examples of the embodiments are shown in the accompanying drawings, wherein from beginning to end
Same or similar label indicates same or similar element or element with the same or similar functions.Below with reference to attached
The embodiment of figure description is exemplary, it is intended to is used to explain the present invention, and is not considered as limiting the invention.
The black Swan event based on subjective and objective associated prediction proposed according to embodiments of the present invention is described with reference to the accompanying drawings
Decision-making technique and device.
The black Swan thing based on subjective and objective associated prediction proposed according to embodiments of the present invention is described with reference to the accompanying drawings first
Part decision-making technique.
The invention solves critical issue, seek to provide a kind of index, which small probability event it can mark off
Really can not occur, but some small probability events very likely occur, and become black Swan event.Method of the invention needs
In combination with the subjective and objective prediction to object event.Subjective forecast (Subjective Prediction, SP) refers to leading to
The judgement for crossing reflection a possibility that event occurs of human brain to carry out.In this prediction judgement, the knowledge of people itself, experience
Serve with intuition main.Also, the judgement of people can be focused more in current occurent thing and variation in real time, right
The issuable influence of the generation of object event.On the contrary, objective prediction (Objective Prediction, OP) refers to passing through
To the statistics of historical data, the probability that outgoing event may occur is obtained.The probability that this event occurs in the past is used, to predict its future
A possibility that occurring.This method itself has good prediction effect for Great possibility, because occurred in history
Event, it is more likely that can occur again.But this method is also easy to erroneous judgement black Swan event, because black Swan event is usual
It is all not occur in history or infrequent event.Introduce the detailed process of this method below.
Fig. 1 is the black Swan event decision method flow based on subjective and objective associated prediction according to one embodiment of the invention
Figure.
As shown in Figure 1, should black Swan event decision method based on subjective and objective associated prediction the following steps are included:
In step s101, predicted events and history data set are obtained.
Further, history data set is the historical data relevant to predicted events in preset period.
Specifically, history data set is the historical data relevant with predicted events within one period, for example, to predict ball
Victory or defeat situation in bout of team A and team B, the then available decision of a game during the decade about team A and team B
Situation.It is understood that preset period is configured according to the actual situation, preset period should be sufficiently large.
In step s 102, predicted events are predicted by prediction model to obtain the first prediction data；Wherein, it presets
Model is by preset machine learning method to history data set generation for statistical analysis.
Specifically, prediction model be by preset machine learning method to history data set relevant with predicted events into
Row statistical analysis generates, and preset machine learning method by learning to history data set, can obtain pre- to be a variety of
Model is surveyed, predicted events are predicted to obtain the first prediction data to realize.
It is understood that the first prediction data is by the objective data for predicting to obtain.
In step s 103, it is searched and matched second prediction data of predicted events in default subjective experience database.
Further, it there are many in such a way that predicted events are predicted in subjective forecast, can be able to achieve as one kind
Mode, establish subjective experience database, pass through in subjective experience database search with the matched prediction data of predicted events
It is predicted, is specifically included:
Obtain multiple prediction data relevant to predicted events；
Analysis is carried out to multiple prediction data relevant to predicted events and generates default subjective experience database.
It is understood that can be divided by the method for machine learning when predicting a predicted events
It is that analysis obtains objective prediction as a result, it can also be predicted by the subjective experience of people to obtain subjective forecast as a result, In
In subjective forecast, by acquisition subjective data relevant to predicted events, for example by investigating under online or line, people couple are collected
The subjective forecast data of predicted events, then these data are carried out the processing such as to screen, one is generated by data library generating method
Default subjective forecast database is obtained when predicting certain part predicted events by searching in subjective forecast database
With the matched prediction data of the predicted events.
In step S104, the first prediction data and the second prediction data are compared into work difference processing and obtain pre- error of measurement
Value carries out decision to predicted events according to prediction difference.
Further, decision is carried out to predicted events according to prediction difference, comprising:
Judge that prediction difference is less than preset threshold, it is determined that predicted events are security incident；
Judge that prediction difference is more than or equal to preset threshold, it is determined that predicted events are risk case.
Specifically, prediction data has been respectively obtained by objective prediction and subjective forecast, it is poor that the prediction data of the two is made
Processing obtains prediction difference, and prediction difference is compared with preset threshold, if prediction difference is less than preset threshold, illustrates to lead
See prediction and objective prediction be it is almost the same, just judge that it is pointed out that Great possibility meeting using this consistent prediction
Occur or small probability event will not occur.If prediction difference is greater than preset threshold, then it represents that subjective forecast and objective prediction are not
Equally, difference is larger, then can courageously suspect and have the generation of black Swan event, that is, Great possibility does not occur or small general
Rate event occurs instead.
It is understood that decision index system can usually show as a threshold value, both subjective and objective prediction differs by more than this
A threshold value, being considered as black Swan event can occur, and then think that the two judgement is consistent lower than threshold value, will not surprisingly occur.
To sum up, it on the one hand makes prediction using the method for machine learning is for statistical analysis to event history data, it is another
The experience of aspect user and observation are predicted.Then the data predicted two kinds are compared, and take the difference as decision and refer to
Mark.When decision index system is lower than a specific threshold value, former prediction result is believable.And when decision index system is higher than this threshold value
When, the result of original prediction is insincere, and the Probability maximum that its reversed event, i.e. black Swan event occur.Pass through combination
Subjective and objective two distinct types of prediction technique gives a kind of effective black Swan event decision index, can be used for risk control
System, greatly reduces loss.
Method of the invention is described in detail below by a specific embodiment.
Football is the big movement of the first in the world, and 4 years primary World Cup soccer games are the football races of highest level, is gathered around
There is great attention rate.World cup bout as a result, other than this Fundamentals of both sides' strength difference, there are many more
Over-the-counter factor also will affect result of the match.So having unexpected winner match often, that is, described black Swan event occurs.Below
Russian world cup in 2018 will be used as example, to illustrate a kind of concrete application of the invention.
It is well known that bout You Liangzhi team A and B are participated in, result of the match is nothing more than being A victory, and B wins or draw.Often
A kind of result can all have certain probability of happening, and the sum of probability of happening of three is 1.Betting office (such as Bet356) is competing
Preceding all to output Pan Kou (Odds Handicap), football fan can compare the stake of race into row, and the result of stake can reflect people's comparison
Match the prediction of result.This prediction is become the subjective forecast to football match.Assuming that troop A victory disk mouth odds are a, B victory
Probability is b, draw c, can stop betting within 20 minutes generally before match, and disk mouth odds will be stablized, and formula can be passed through
(1), (2), (3) come calculate troop A triumph probability (Pa-SP), B win probability (Pb-SP) and draw probability (Pc-SP):
Pa-SP=(1/a)/((1/a)+(1/b)+(1/c)) (1)
Pb-SP=(1/b)/((1/a)+(1/b)+(1/c)) (2)
Pc-SP=(1/c)/((1/a)+(1/b)+(1/c)) (3)
On the other hand, objective prediction can be carried out by machine learning model training historical data, bout
The probability of three kinds of results is denoted as Pa-OP, Pb-OPAnd Pc-SP.Logistic regression (the Logistic of scikit-learn is used in this example
Regression) model is trained and classifies to data.International Football Union carries out national team's world ranking, institute since nineteen thirty
Using the result for the match for needing acquisition to occur between all every country teams since nineteen thirty as training history number
According to generation data set.In this data set, then filters out and participate in the match that the national team of world cup in 2018 once participated in
(it is world cup team participating in competition in 2018 that as long as bout, which has a side).The value of three features, host team, visitor are only focused in data
Team and result of the match.Result of the match is carried out labeling with the visual angle of host team, 2 represent host team's victory, and 1 representative is tied, and 0 represents host team
It is defeated.Then to possess these three characteristic values it is above screen after All Countries team between code carry out one-
Hot coding, enables these data by scikit-learn machine learning model loading processing.So far carrying out is pre-
The data set of processing is training and the total collection of test.It is trained with wherein 70% record, 30% record is tested.So
Afterwards, situation is poised for battle to the match in 32 team's group round robin stages for participating in 2018 world cups and also carries out one-hot coding.Due to generation
There is no point of host and guest team in boundary's cup match, international ranking before starting here according to 2018 world cups distinguishes team in world cup
In pouplarity, pouplarity it is high match be poised for battle in is considered as host team.Forecast set after this one-hot coding
It is consistent to close the total collection one-hot coding of the training test also needed with before, so the coding column (being denoted as 0) lacked are added.
According to above method, before every game starts, the result of subjective and objective prediction can be obtained.Using subjective and
Maximum difference in three kinds of results of the match of objective prediction is as decision judge index DMI (Decision Making
Indicator), it may be assumed that
DMI=max (| Pa-SP-Pa-OP|,|Pb-SP-Pb-OP|,|Pc-SP-Pb-OP|) (4)
Here define unexpected winner match (black Swan event) are as follows: 1, host team (i.e. strong team, the high side of international ranking) win
The probability that likelihood ratio visiting team (i.e. weak team) wins is higher by 50%, but result of the match is that weak team wins or match is tied；2, host team
Winning probability is more than visiting team's winning probability 20% and less than 50%, but result is the triumph of weak team.In addition, if strong team wins generally
Rate and weak team's winning probability difference are less than 20%, it is believed that relatively, then any result of the match can connect Liang Zhi team example
By being not in unexpected winner, such match can ignore (Ignored-Game, IG), not charge to the considerations of the competing model that produces an unexpected winner
It encloses.
For subjective and objective associated prediction, bout is regarded as negligible match, subjective and objective prediction is needed both to think it
It is negligible match.Negligible match is removed, others match is all considered as risky match (Risk Game, RG).For having
Risk match, using predicting that it can or can not become black Swan event based on the judge index of subjective and objective associated prediction: if DMI
More than some threshold value, such as it is set as 5% in this example, being considered as him will become black Swan event, and otherwise match is exactly to be
Safety match (Safe Game, SG).
48 group round robins of world cup in 2018 are assessed based on the decision-making technique of DMI with described above, such as
Shown in Fig. 2.Wherein horizontal dotted line is threshold value 0.05, is the SGs that competes safely less than threshold value.
A unexpected winner match is enumerated to illustrate.The match of this unexpected winner is Mexico poised for battle, Germany, before match starts, according to
Objective prediction, the probability of Germany's victory are 0.589, and drawing probability 0.258, the probability of Mexico's victory is 0.153；It begins shroud mouth
Odds are locked as Germany's victory 1.5, draw 4.5, and Mexico's victory 7.5 can converse the subjective forecast of people, the probability of Germany's victory
It is 0.652, drawing probability 0.217, the probability of Mexico's victory is 0.130.So can calculate this first is a RG, so
The DMI value for finding it afterwards is 0.063, is more than threshold value 0.05, therefore courageously prediction produces an unexpected winner than grand sports meet.Result verification prediction is correct
, the score on June 17 is that Germany 0:1 has been defeated by team, Mexico on the day of match.
Further, master is evaluated respectively using Accuracy, Precision, Recall and the F1 measurement standard of standard
Prediction is seen, the judgement effect of objective prediction and the match of subjective and objective associated prediction team group round robin stage unexpected winner is shown in Table 1.It can be seen that
Subjective and objective associated prediction performs more than other two kinds of predictions in every measurement standard.
The prediction result of the different prediction modes of table 1
| SOP | SP | OP | |
| Accuracy | 0.583 | 0.4375 | 0.416 |
| Precision | 0.354 | 0.25 | 0.243 |
| Recall | 1 | 1 | 1 |
| F1 | 0.523 | 0.4 | 0.391 |
In addition, a kind of investment tactics can also be provided based on above method.Assuming that there is 48 parts of capitals that can invest 48 ratios
Match, investment tactics is:
1, to negligible match, without investment；
2, it competes for the safety that associated prediction goes out, buys the Pan Kou that strong team wins；
3, for risky match, the disk that strong team wins is bought using positive operation (Forward Operation, FO)
Mouth or reverse operating (Reverse Operation, RO) buy the Pan Kou that weak team wins.
It is based on three kinds of prediction techniques in this way, just there is the method for six kinds of investments, investment repayment the results are shown in Table 2.Only host and guest
It sees associated prediction just to have the ability to filter out safe match from risky match, i.e., the match of night and event will not occur, and
Individually this life only will appreciate that risky match and insignificant match for subjective forecast and objective prediction.
2 investment repayment result of table
It can be found that the reverse operating investment tactics (SOP-RO) based on associated prediction judge index has highest from table
Return income.
The black Swan event decision method based on subjective and objective associated prediction proposed according to embodiments of the present invention, passes through acquisition
Predicted events and history data set；Predicted events are predicted by prediction model to obtain the first prediction data；In default master
It sees in experience database and searches and matched second prediction data of predicted events；By the first prediction data and the second prediction data into
Row obtains prediction difference to difference processing is compared to, and carries out decision to predicted events according to prediction difference.Pass through subjective and objective prediction as a result,
To carry out reliability prediction to predicted events, to improve the performance of identification black Swan event and risk control.
The black Swan event based on subjective and objective associated prediction proposed according to embodiments of the present invention is described referring next to attached drawing
Decision making device.
Fig. 3 is the black Swan event decision apparatus structure based on subjective and objective associated prediction according to one embodiment of the invention
Schematic diagram.
As shown in figure 3, being somebody's turn to do the black Swan event decision device based on subjective and objective associated prediction includes: the first acquisition module
100, objective making decision module 200, subjective decision module 300 and decision output module 400.
First obtains module 100, for obtaining predicted events and history data set.
Objective making decision module 200 obtains the first prediction data for being predicted by prediction model predicted events；Its
In, prediction model is by preset machine learning method to history data set generation for statistical analysis.
Subjective decision module 300, it is pre- with predicted events matched second for being searched in default subjective experience database
Measured data.
Decision output module 400 is obtained for the first prediction data and the second prediction data to be compared work difference processing
Prediction difference carries out decision to predicted events according to prediction difference.
Further, in one embodiment of the invention, decision is carried out to predicted events according to prediction difference, comprising:
Judge that prediction difference is less than preset threshold, it is determined that predicted events are security incident；
Judge that prediction difference is more than or equal to preset threshold, it is determined that predicted events are risk case.
Further, in one embodiment of the invention, history data set be in preset period with predicted events phase
The historical data of pass.
Further, in one embodiment of the invention, by the Logic Regression Models of scikit-learn to history
Data set is for statistical analysis.
Further, in one embodiment of the invention, further includes:
Second obtains module, for obtaining multiple prediction data relevant to predicted events；
Generation module generates default subjective experience number for carrying out analysis to multiple prediction data relevant to predicted events
According to library.
It should be noted that the aforementioned explanation to the black Swan event decision embodiment of the method based on subjective and objective associated prediction
Illustrate the device for being also applied for the embodiment, details are not described herein again.
The black Swan event decision device based on subjective and objective associated prediction proposed according to embodiments of the present invention, passes through acquisition
Predicted events and history data set；Predicted events are predicted by prediction model to obtain the first prediction data；In default master
It sees in experience database and searches and matched second prediction data of predicted events；By the first prediction data and the second prediction data into
Row obtains prediction difference to difference processing is compared to, and carries out decision to predicted events according to prediction difference.Pass through subjective and objective prediction as a result,
To carry out reliability prediction to predicted events, to improve the performance of identification black Swan event and risk control.
In addition, term " first ", " second " are used for descriptive purposes only and cannot be understood as indicating or suggesting relative importance
Or implicitly indicate the quantity of indicated technical characteristic.Define " first " as a result, the feature of " second " can be expressed or
Implicitly include at least one this feature.In the description of the present invention, the meaning of " plurality " is at least two, such as two, three
It is a etc., unless otherwise specifically defined.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is included at least one embodiment or example of the invention.In the present specification, schematic expression of the above terms are not
It must be directed to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described can be in office
It can be combined in any suitable manner in one or more embodiment or examples.In addition, without conflicting with each other, the skill of this field
Art personnel can tie the feature of different embodiments or examples described in this specification and different embodiments or examples
It closes and combines.
Although the embodiments of the present invention has been shown and described above, it is to be understood that above-described embodiment is example
Property, it is not considered as limiting the invention, those skilled in the art within the scope of the invention can be to above-mentioned
Embodiment is changed, modifies, replacement and variant.
Claims (10)
1. a kind of black Swan event decision method based on subjective and objective associated prediction, which comprises the following steps:
Obtain predicted events and history data set；
The predicted events are predicted by prediction model to obtain the first prediction data；Wherein, the prediction model is logical
Preset machine learning method is crossed to history data set generation for statistical analysis；
It is searched and matched second prediction data of the predicted events in default subjective experience database；
First prediction data and second prediction data are compared into work difference processing and obtain prediction difference, according to described
Prediction difference carries out decision to the predicted events.
2. the method according to claim 1, wherein it is described according to the prediction difference to the predicted events into
Row decision, comprising:
Judge that the prediction difference is less than preset threshold, it is determined that the predicted events are security incident；
Judge that the prediction difference is more than or equal to the preset threshold, it is determined that the predicted events are risk case.
3. the method according to claim 1, wherein the history data set be in preset period with it is described pre-
The relevant historical data of survey event.
4. the method according to claim 1, wherein by the Logic Regression Models of scikit-learn to described
History data set is for statistical analysis.
5. the method according to claim 1, wherein further include:
Obtain multiple prediction data relevant to the predicted events；
Analysis is carried out to the multiple prediction data relevant to the predicted events and generates the default subjective experience database.
6. a kind of black Swan event decision device based on subjective and objective associated prediction characterized by comprising
First obtains module, for obtaining predicted events and history data set；
Objective making decision module obtains the first prediction data for being predicted by prediction model the predicted events；Wherein,
The prediction model is by preset machine learning method to history data set generation for statistical analysis；
Subjective decision module, for being searched in default subjective experience database and the matched second prediction number of the predicted events
According to；
Decision output module is obtained for first prediction data and second prediction data to be compared work difference processing
Prediction difference carries out decision to the predicted events according to the prediction difference.
7. device according to claim 6, which is characterized in that it is described according to the prediction difference to the predicted events into
Row decision, comprising:
Judge that the prediction difference is less than preset threshold, it is determined that the predicted events are security incident；
Judge that the prediction difference is more than or equal to the preset threshold, it is determined that the predicted events are risk case.
8. device according to claim 6, which is characterized in that the history data set be in preset period with it is described pre-
The relevant historical data of survey event.
9. device according to claim 6, which is characterized in that by the Logic Regression Models of scikit-learn to described
History data set is for statistical analysis.
10. device according to claim 6, which is characterized in that further include:
Second obtains module, for obtaining multiple prediction data relevant to the predicted events；
Generation module generates the default master for carrying out analysis to the multiple prediction data relevant to the predicted events
See experience database.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910623881.5A CN110458328A (en) | 2019-07-11 | 2019-07-11 | Black Swan event decision method and device based on subjective and objective associated prediction |
| PCT/CN2019/099406 WO2021003791A1 (en) | 2019-07-11 | 2019-08-06 | Black swan event decision method and apparatus based on subjective and objective joint prediction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910623881.5A CN110458328A (en) | 2019-07-11 | 2019-07-11 | Black Swan event decision method and device based on subjective and objective associated prediction |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110458328A true CN110458328A (en) | 2019-11-15 |
Family
ID=68482609
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910623881.5A Pending CN110458328A (en) | 2019-07-11 | 2019-07-11 | Black Swan event decision method and device based on subjective and objective associated prediction |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110458328A (en) |
| WO (1) | WO2021003791A1 (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106682754A (en) * | 2015-11-05 | 2017-05-17 | 阿里巴巴集团控股有限公司 | Event occurrence probability prediction method and device |
| CN107807908A (en) * | 2017-09-25 | 2018-03-16 | 平安科技（深圳）有限公司 | Variety result of the match Forecasting Methodology, device and storage medium |
| CN109190834A (en) * | 2018-09-12 | 2019-01-11 | 百色学院 | Stock price trend prediction method and system neural network based |
| US20190095808A1 (en) * | 2017-09-27 | 2019-03-28 | Intel Corporation | Methods and apparatus to dynamically adjust an analytics threshold |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8751867B2 (en) * | 2011-10-12 | 2014-06-10 | Vmware, Inc. | Method and apparatus for root cause and critical pattern prediction using virtual directed graphs |
| CN109871259A (en) * | 2013-08-16 | 2019-06-11 | 运软网络科技(上海)有限公司 | A kind of imitative brain calculates the method and system of virtualization |
| CN108805337B (en) * | 2018-05-21 | 2021-06-22 | 清华大学 | Aviation operation control risk management and control method and system |
| CN109003036A (en) * | 2018-05-24 | 2018-12-14 | 重庆邮电大学 | A kind of anti-act-short-view innovation talent Salary Structure setting method |
-
2019
- 2019-07-11 CN CN201910623881.5A patent/CN110458328A/en active Pending
- 2019-08-06 WO PCT/CN2019/099406 patent/WO2021003791A1/en active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106682754A (en) * | 2015-11-05 | 2017-05-17 | 阿里巴巴集团控股有限公司 | Event occurrence probability prediction method and device |
| CN107807908A (en) * | 2017-09-25 | 2018-03-16 | 平安科技（深圳）有限公司 | Variety result of the match Forecasting Methodology, device and storage medium |
| US20190095808A1 (en) * | 2017-09-27 | 2019-03-28 | Intel Corporation | Methods and apparatus to dynamically adjust an analytics threshold |
| CN109190834A (en) * | 2018-09-12 | 2019-01-11 | 百色学院 | Stock price trend prediction method and system neural network based |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021003791A1 (en) | 2021-01-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Power et al. | Not all passes are created equal: Objectively measuring the risk and reward of passes in soccer from tracking data | |
| Jones et al. | Team performance indicators as a function of winning and losing in rugby union. | |
| Li et al. | Is international junior success a reliable predictor for international senior success in elite combat sports? | |
| Ferrari et al. | Match analysis in handball: a systematic review | |
| Bailey et al. | Predicting the match outcome in one day international cricket matches, while the game is in progress | |
| Schultze et al. | A weighted plus/minus metric for individual soccer player performance | |
| Bransen et al. | Choke or shine? Quantifying soccer players’ abilities to perform under mental pressure | |
| Davis et al. | Player evaluation in Twenty20 cricket | |
| Easton et al. | Are daily fantasy sports gambling? | |
| CN110458328A (en) | Black Swan event decision method and device based on subjective and objective associated prediction | |
| Kim et al. | March Madness prediction: Different machine learning approaches with non‐box score statistics | |
| Wu et al. | Evaluation of off-the-ball actions in soccer | |
| Farah et al. | Rough draft: The accuracy of athlete selection in North American professional sports | |
| Olthof et al. | Biomechanical loads and their effects on player performance in NCAA DI male basketball games | |
| Qureshi et al. | The impact of COVID-19 on sports betting markets | |
| WO2015168727A1 (en) | Computer implemented system and method of conducting a contest | |
| Losak | Player pricing mechanisms and the daily fantasy sport chance versus skill debate | |
| KR20210004168A (en) | A System and Method of Information Supplying the Estimated Competition Results Using Weighted Information | |
| Suss et al. | Investigating perceptual anticipation in a naturalistic task using a temporal occlusion paradigm: a method for determining optimal occlusion points | |
| Berthet | Improving MMA judging with consensus scoring: A Statistical analysis of MMA bouts from 2003 to 2023 | |
| Farah et al. | 10 Rough Draft | |
| KR102443007B1 (en) | win-loss prediction system | |
| Frank et al. | Discriminant Function Analysis Reveals Which Combination of Measures from the NFL Scouting Combine Predict NFL Performance | |
| Bradbury | Statistical performance analysis in sport | |
| Zheng | NBA Winner Prediction: A Hybrid Framework Incorporating Internal and External Factors |
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: 20191115 |