CN109345391A - Risk control method and system based on big data analysis - Google Patents
Risk control method and system based on big data analysis Download PDFInfo
- Publication number
- CN109345391A CN109345391A CN201811208219.5A CN201811208219A CN109345391A CN 109345391 A CN109345391 A CN 109345391A CN 201811208219 A CN201811208219 A CN 201811208219A CN 109345391 A CN109345391 A CN 109345391A
- Authority
- CN
- China
- Prior art keywords
- risk
- risk control
- investment
- trade mode
- storehouse
- 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The present invention relates to software fields, are based especially on the risk control method and system of big data analysis.The risk control method based on big data analysis, including raw information relevant to investment is obtained from different data sources, investment intent is carried out predicting to determine trade mode according to the raw information；The trade mode is fed back into user, and obtains the estimated account amount of money that can be put into of the user under the trade mode；According to the greateset risk coefficient under account amount of money and the trade mode, verifying maximum can bear whether risk meets preset risk control control requirement；If the maximum, which can bear risk, meets preset risk control control requirement, the prompt that transaction platform is traded can be entered in time bracket for user feedback.The present invention is determined best trade mode by the way of big data analysis and is pushed to user, provides reliable reference for user, avoids artificial irrational operation, can carry out risk control to the transaction of financial product.
Description
Technical field
The present invention relates to software fields, are based especially on the risk control method and system of big data analysis.
Background technique
With information-based high speed development, big data is come into being, and big data technology refers to that a kind of scale arrives greatly and obtaining
It takes, store, managing, analyzing the data acquisition system that aspect is well beyond traditional database software means capability range, there is magnanimity
Data scale, quick stream compression, multiplicity data type and the low four big feature of value density.The diversified formation of data
Reason of both mainly having: first is that data source is more, there are search engine, social networks, message registration, sensor etc.；Two
It is that data format is more, there is structured data, semi structured data and non-structural data.
Each investor enters stock, futures or foreign exchange market and is desirable into profit, but statistical result showed,
The people of 80%-90% is loss.For probability, the accuracy of vast majority of people's judgement is all close to 50%.Therefore, it manages
By should above there is 50% people to be to make money, and actually there was only the money-making of 10-20%, intermediate gap is huge.It causes
The very big reason of huge spread in this way is the irrational belief of deal maker.Such as carelessly trade, do not set stop loss, weight storehouse transaction,
Frequently transaction etc..
Summary of the invention
For the defects in the prior art, the present invention provides a kind of risk control method based on big data analysis and is
System can carry out risk control to the transaction of financial product, reduce transaction risk, improve investment yield.
To achieve the goals above, in a first aspect, the risk control method provided by the invention based on big data analysis, packet
Include following steps: obtaining relevant to investment raw information from different data sources, according to the raw information to investment intent into
Row is predicted to determine trade mode；The trade mode is fed back into user, and obtains the user under the trade mode it is expected that can
The account amount of money of investment；According to the greateset risk coefficient under the account amount of money and the trade mode, verifying maximum can be born
Whether risk, which meets preset risk control control, requires；If the maximum, which can bear risk, meets preset risk control control
It is required that then the prompt that transaction platform is traded can be entered in time bracket for user feedback.
Second aspect, the risk control system provided by the invention based on big data analysis, including risk control server
And user terminal, the risk control server and the user terminal communicate to connect；The risk control server is from different data
Source obtains raw information relevant to investment, carries out predicting to determine trade mode to investment intent according to the raw information；Institute
It states risk control server and the trade mode is fed back into user terminal, and obtain the user under the trade mode and expect to throw
The account amount of money entered；The risk control server is according to the greateset risk system under the account amount of money and the trade mode
Number, verifying maximum can bear whether risk meets preset risk control control requirement；If the maximum can bear risk satisfaction
Preset risk control control requires, then the risk control server is that client feeds back can enter transaction in time bracket
The prompt that platform is traded.
The beneficial effects of the present invention are: the present invention is determined best trade mode by the way of big data analysis and will
It is pushed to user, provides reliable reference for user, can bear whether risk meets preset risk control by verifying maximum
System control requires, and avoids artificial irrational operation, can carry out risk control to the transaction of financial product, reduce transaction
Risk improves investment yield.
Detailed description of the invention
Fig. 1 is the flow chart of risk control method of the first embodiment of the invention based on big data analysis；
Fig. 2 is the block diagram of risk control system of the second embodiment of the invention based on big data analysis.
Specific embodiment
Specific embodiments of the present invention are described more fully below, it should be noted that the embodiments described herein is served only for illustrating
Illustrate, is not intended to restrict the invention.In the following description, in order to provide a thorough understanding of the present invention, a large amount of spies are elaborated
Determine details.It will be apparent, however, to one skilled in the art that: this hair need not be carried out using these specific details
It is bright.In other instances, in order to avoid obscuring the present invention, well known circuit, software or method are not specifically described.
Throughout the specification, meaning is referred to " one embodiment ", " embodiment ", " example " or " example "
: a particular feature, structure, or characteristic described in conjunction with this embodiment or example is comprised at least one embodiment of the invention.
Therefore, the phrase " in one embodiment ", " in embodiment ", " example " occurred in each place of the whole instruction
Or " example " is not necessarily all referring to the same embodiment or example.Furthermore, it is possible in any suitable combination and or sub-portfolio will be specific
Feature, structure or characteristic combine in one or more embodiment or examples.In addition, those of ordinary skill in the art should manage
Solution, diagram is provided to the purpose of explanation provided herein, and diagram is not necessarily drawn to scale.
As shown in Figure 1, the risk control method based on big data analysis shown in the first embodiment of the present invention, feature
It is, includes the following steps:
S1 obtains relevant to investment raw information from different data sources, according to the raw information to investment intent into
Row is predicted to determine trade mode；
Wherein, the trade mode stock, fund, bond, futures and foreign exchange transaction mode.Crawler can be used in the present embodiment
It completes to obtain raw information relevant to investment from different data sources, crawler selectively exchanges investment according to subject content
The webpage of website is crawled, it under the premise of guaranteeing page info acquisition coverage rate primarily to while having higher
Information accuracy rate.Crawler described in this implementation is mainly improved in terms of following two: webpage quantity sharply increases, with
Ratio shared by the relevant webpage of theme is reduced therewith, in order to guarantee the coverage rate and accuracy rate of page info acquisition, to be climbed
The page is screened during row, is retained and the higher webpage of topic correlativity.Crawler creeps needs band targetedly, benefit
With the topic correlativity of certain algorithm calculating linking.
Further, URL queue to be crawled will be added with the higher URL of topic correlativity.Establish with destination server it
Between HTTP link；The webpage for obtaining investment exchange website, parses webpage, extracts the content text of the webpage；It is right
Extracted content text carries out Chinese word segmentation, counts the keyword with independent semanteme occurred in content text；Building
The text vector of Semantic Similarity is replaced the keyword for the condition that meets by calculating the semantic similarity between keyword
It changes, obtains the replaced text of semantic similar concept.
It in the present embodiment, is by the Semantic Similarity Measurement model based on distance by quantifying between keyword at this
Path length in body hierarchical network calculates similarity, it needs to pre-establish ontology hierarchical network, and the knot of network
Structure will directly affect the calculated result of semantic similarity, specific calculation formula are as follows: sim (w1, w2)=2maxlen-
Minlen, wherein maxlen is keyword w1And w2Maximum distance in ontology tree, minlen are keyword w1And w2In ontology
Minimum range in tree.
In other one or some embodiments, due to there will certainly be phase between two keywords in bulk junction paper mulberry
Same father's node, such as root node, and can have the associated path of more than one, specific calculation formula are as follows:Wherein l1And l2Refer to keyword w1And w2Between father's node w nearest to them
The shortest distance, len refers to root node to the shortest distance between w.
Further, in this embodiment using the semanteme for calculating keyword based on the Semantic Similarity Measurement model of content
Similarity.Due in this hierarchical network, if containing more how identical content in two keywords, then it represents that between the two
Semantic similarity is bigger；If containing more few identical content in two keywords, then it represents that semantic similarity between the two
It is smaller.The content that keyword includes can indicate by calculating the frequency that it occurs in a document, if there is frequency it is high,
It then indicates abundant in content；If there is frequency it is low, then it represents that content is deficient, specific calculation formula are as follows:Wherein p (w) refers to the probability that keyword w occurs, and N refers to the sum of keyword, if s (w1, w2) be
Keyword w1And w2The set of public father's node keyword, then the specific calculation formula of the public father's node of calculator are as follows:Thus keyword w1And w2Calculating formula of similarity are as follows:
sim(w1, w2)=1-pmin(w1, w2), if keyword w1And w2Included content account for including if, keyword w1
And w2Calculating formula of similarity are as follows:
Investment intent is carried out predicting to determine trade mode according to the semantic similar concept replaced text.Using institute
The replaced text of predicate justice similar concept can obtain all keywords in each webpage about trade mode, calculate
Keyword probability appeared in all texts of different trade modes is represented, it is maximum as final to choose wherein probability value
Predicted value, and then the trade mode of user's push can be determined directly as.
The trade mode is fed back to user by S2, and obtains the estimated account that can be put into of the user under the trade mode
The family amount of money；
By the way that the determining trade mode of prediction is fed back to user, reliable reference can be provided for user, help to reduce
Risk.
S3, according to the greateset risk coefficient under the account amount of money and the trade mode, risk can be born by verifying maximum
Whether meet preset risk control control to require；
First, verifying maximum can bear whether risk meets preset risk control control requirement, specifically: it will most strong wind
Dangerous factor alpha is compared with baseline risk factor beta, if greateset risk factor alpha is less than or equal to baseline risk factor beta, meets wind
Control requires, and is otherwise unsatisfactory for air control requirement；The calculation formula of the baseline risk factor beta is as follows: β=D × K (P × Rw-Q×
Rl)/(Rw× Rl) wherein: D, K, P, Q, Rw and Rl are the parameter obtained according to the statistics of previous transaction data.β is benchmark risk
Coefficient.D is tactful coefficient of efficiency, and effective strategy continues effective probability in following market before representing, this is one
Empirical value is arranged D=85% less than 100%, in the present embodiment and retains certain space come the uncertainty for future prospects.K
For tactful profitability coefficient of efficiency, the probability that the profitability of strategy can also continue in future prospects before representing,
This is also an empirical value, and less than 100%, K=70% is arranged in the present embodiment, and uncertain for future prospects retains one
Fixed space.P is the average of wins, is to win to trade to account for the percentage always traded, this is to test the statistical value obtained by history.Q
It is that loss transaction accounts for the percentage always traded, i.e. 1-P for the rate of being defeated.Rw is the net odds after winning, and is gold of getting a profit after winning
Volume accounts for the percentage of account capital, this is to test the statistical value obtained by history.Rl is the net loss rate after loss, is to lose
Deficit accounts for the percentage of account capital after damage, this is to test the statistical value obtained by history.
Second, whether the account capital meets the judgement of air control requirement, specifically: according to greateset risk coefficient inverse storehouse
Position and transaction amount meet air control requirement, are otherwise unsatisfactory for air control requirement if account capital is more than or equal to transaction amount；
Setting account capital is M, and greateset risk coefficient is α, and maximum operation amplitude is K point, and every point value is T, maximum
Loss plus warehouse receipt number are N, and i is the positive integer less than or equal to N；The greateset risk amount of money: MaxRisk=M × α；Add storehouse spacing: G=
K/(N-1)；I-th single maximum loss points: D (i)=K- (i-1) × G；I-th single risk amount: R (i)=D (i) × T ×
Lot；Then N mono- overall risk amount are as follows:It is equal to the specified calculating position in storehouse of overall risk according to the greateset risk amount of money
Lot；It enablesThen position in storehouse:Transaction amount
Y=M/Lot.
The important means of risk control, is according to account risk inverse when the transaction amount and position in storehouse of the present embodiment calculate
, it has been contemplated that the amplitude for adding storehouse and unfavorable market to run.Such as account capital is 100000 yuan, greateset risk coefficient is
20%, maximum operation amplitude is 1000 points, and every point value is 10, and maximum loss plus warehouse receipt number are 5.It is carried out by above formula
It is 0.8 hand, transaction amount=100000/0.8=125000 member that position in storehouse, which is calculated,.Because account amount of money is less than transaction amount,
Therefore it is unsatisfactory for air control requirement, system can remind deal maker to increase greateset risk coefficient or increase account amount of money, meet with this
Air control requirement.The operation of weight storehouse is the most important reason for leading to account risk, and the present embodiment does not allow deal maker oneself to select storehouse
Position, but position in storehouse is calculated automatically, and the position in storehouse calculated has covered worst situation, this, which is ensured that, does not have the transaction of weight storehouse
The case where occur.
S5 analyzes market variation in real time in process of exchange, and carries out adding storehouse according to market variation or sell shares or leave the theatre.
In the present embodiment, in process of exchange, divide from basic side grave news event, technological side operation trend etc.
Current quotations are analysed, carry out adding storehouse according to current quotations or sells shares or leaves the theatre.
First, basic side grave news event, by the media event gathered in advance for having set time point make admission,
The operation for adding storehouse, selling shares and leaving the theatre.System passes through news interface, automatic reading media event list, before set time point
Operated after judging news within 3-5 hours, these news such as: the resolution of Central Bank's interest rate, GBP data, commodity stocks variation,
Leader's speech, company annual report etc..For example advantageous news in admission or adds storehouse, for example unfavorable news, and pop-up alarm window is prohibited
Only deal maker places an order or reminds deal maker to trade or sell shares or leave the theatre with caution.For emergency event, because it announces the time not
Media event list can not be added in determination in advance, and when media event occurs, it is big that market have often been unfolded one
Wave, therefore can not evade in advance, but the trend system of can be used is filtered, such as after the generation of news time, under market
Drop range degree is bigger, has at this time generally all broken the equal line of MA20 by a fall, and distance MA20 is distant, we can be according to this
A feature-set: the equal line of price distance MA20 does not allow reversely to do more when surpassing 3 times of ATR, this way may be one
The normal market in part are mistaken for abnormal market, but can yet be regarded as a kind of effective method for the media event of this type.
Second, technological side operation trend determines to receive or refusal is traded by the judgement of the technical indicator to technological side
The instruction of member, if market are near important support resistance position, the breakthrough of cloth woods index is too far apart from equal line, well-behaved from excessive
Deng.
Such as short-swing trading mode plus storehouse error correction mode:
Because in the position in storehouse very light that head is singly used, to add storehouse to reserve enough spaces, therefore, short-swing trading in the future
Mode, which will use, in a planned way adds storehouse, by adding storehouse come cost of making thinner, realizes whole profit, entirely adding storehouse process is based on probability
What advantage calculated, more there is the art of composition compared to the subjective casual plus storehouse of deal maker, an average level of performance can be reached, system can prohibit
The only intervening act of deal maker.
It needs to calculate the Probability advantages for continuing to add storehouse when adding storehouse every time, only when Probability advantages are more than 65%
It can continue to add storehouse, otherwise continue waiting for being a better choice.
The calculations incorporated of Probability advantages three factors below:
A, average daily average fluctuation margin: add warehouse receipt plus storehouse interval require to be set in the 50% of per day fluctuating range with
On, in this way for different trade varieties can to avoid add storehouse too closely the problem of.
B, chance is remedied after adding warehouse receipt to malfunction again: using 85 percentile of average fluctuation margin of one wave band of currency
It measures, in fluctuating range of the day figure rank using ZigZag measure of criterions each wave band and sequence, chooses 85 percentages later
Fluctuating range value corresponding to position.
C, for current quotations for the degree of cooperation of short-term medium and long term trend, short-term trend cooperates is adding storehouse each time
Must all cooperate in the process, medium and long term trend cooperate in the case where, add storehouse spacing relatively small, in the hope of quick payoffs from
, in the ill-matched situation of medium and long term trend, storehouse spacing is added to need to be amplified to more than preceding primary plus storehouse interval.
If deal maker first singly do it is more after market drop at once, short-swing trading mode is not just left the theatre chance,
At this time system can be in waiting, after market are returned to rise, and system adds one single, position in storehouse and first single-phase automatically
Together, if the comprehensive profit of two lists meets the condition of leaving the theatre and can leave the theatre, short-swing trading mode most adds 5 storehouses, total storehouse
Position is still within lower level.
Short-swing trading mode obtains additional odds using storehouse is added, and actively assumes responsibility for risk in disk, its benefit is non-
Chang Mingxian, it can make the overall odds of transaction be greatly improved, and it is single that part loss is singly become profit.Add the pass in storehouse
Key content is that short-swing trading mode adds storehouse to be planned plus storehouse, and entirely plus storehouse is a part for being exactly trading program, adds storehouse
Position is all that ensure that by quantitative statistics plus storehouse strategy is still effective in the case where 85%, therefore have certain
Probability advantages.The amount of placing an order of initial position in storehouse and plus single amount of warehouse receipt be COMPREHENSIVE CALCULATING, guarantee plus storehouse after greateset risk still
So within the scope of agreement.
Such as short-swing trading mode is left the theatre:
Short-swing trading mode is left the theatre using Flat Amount, and every 10,000 yuan of 5 yuan of profits are left the theatre at once, adds storehouse, institute if having passed through
There is list to add up 5 yuan of profit to leave the theatre.
This mode of leaving the theatre is one kind of numerous modes of leaving the theatre, each mode is all each advantageous and disadvantage, without which
Mode of kind leaving the theatre with overwhelming advantage, short-swing trading mode leave the theatre be also it is the same, it, which can lose, captures a big wave and becomes
The chance of gesture, but benefit is also clearly, and it significantly improves the odds of system, compares fitting human nature.
Here key point is: short-swing trading mode has used the mode of leaving the theatre of a certain unified standard, receives this
The average probability advantage of kind of trade mode, in this way, deal maker is in different modes of leaving the theatre there is no need to wave, so as to big
The difficulty of amplitude reduction transaction.
The risk control method of commerce of the present embodiment, before being traded, further include by chain transaction method of testing or
It is the suitable trade mode of each trade variety selection that Meng Teka, which falls simulation, and the multi-exchange mould of each trade variety is arranged
Formula.Each trade variety has the characteristic of oneself, is not particularly suited for all trade modes, it is therefore desirable to assess each friendship
Easy kind for every kind of trade mode applicability, to be the suitable transaction mould of each trade variety selection according to historical data
Formula, and the trade mode of each trade variety is set.
First, chain transaction method of testing.Program chain transaction is allowed when System History test, it is vertical after terminating for one innings
Next innings of beginning of transaction is carved, trading frequency of this way in simulation test is typically all 5-10 times of real trade, is pressed
According to the transaction principles of certain mode, such way can cover worst situation, use the assessment transaction of such method
Odds and earning rate generally all can be more far short of what is expected than actual conditions, but meaningful in this, as the reference of air control.
Second, Meng Teka falls simulation.According to (average daily 3 friendships such as on 20 trade varieties of real trade frequency
Easily), it the time and direction that stochastic simulation places an order, allows automated system operation, the victory for being relatively close to truth may finally be obtained
Calculation and earning rate, because of the randomness of transaction, such way can not very likely cover worst situation, therefore can also adopt
With chain transaction method of testing.
The citing of short-swing trading mode:
It is applicable in market: foreign exchange；Minimum lever ratio: 8 times；
Compliance inspection:
Trade variety limitation are as follows: EURUSD, GBPUSD, AUDUSD, USDJPY, USDCHF, USDCAD, EURGBP,
AUDCAD, AUDNZD, EURJPY, EURAUD, GBPCAD totally 12 kinds
Greateset risk range is 10%-20%.
Minimum 2000 U.S. dollar of account capital.
Interest rate resolution relevant to currency, president of Central Bank, which talks to announcing first 5 hours, to be forbidden trading.
Forbid transaction of taking advantage of a situation when Tu and four hour rank great support resistance positions.
On H1 chart, price be more than the ATR amplitude of EMA48 three times when forbid transaction of taking advantage of a situation.
Position in storehouse: benchmark position in storehouse is that every 10,000 U.S. dollar 0.06-0.1 hand differs, and each currency is not exclusively.
Admission (does mostly example): being connected to client trading and does admission at once after multiple instructions.
Add storehouse: when storehouse condition being added to meet, according to position in storehouse plus a storehouse.
Add storehouse condition: 1) currency is generally in lossing state；2) there are no fill it up with 5 storehouses；3) apart from previous storehouse at least 0.5
Day again schemes ATR amplitude；4) 10 lines have at least been had been subjected to previous storehouse；5) price is small up to 1 above short-term line SMA20
When, during which never touch the equal line of SMA20；6) price take-up above intermediate trend Envelop (48,0.3)；7) nearest 5 is small
When it is interior without interest rate resolve, president of Central Bank speech etc. grave news event.
Leave the theatre: 5 U.S. dollars of whole profit are left the theatre.
The citing of wave band trade mode:
It is applicable in market: foreign exchange, futures.Account lever ratio is greater than 7 times.
Compliance inspection:
Trade variety limitation are as follows: XAUUSD, the GBPJPY of foreign exchange, preceding 10% kind of brisk trade in domestic futures
The stock of lever transaction can be used in (needing monthly dynamic adjustment), stock price index futures, external disk futures, external disk stock index, and lever ratio is necessary
More than 3.5 times.
Greateset risk range is the 0.4%-2.4% of capital.
Minimum 1500 U.S. dollar of foreign exchange account capital, futures account regard minimum lsp request difference of trade variety.
Without evading media event and technological side, trading instruction is preferably issued in advance before grave news event.
If it is there is the trade variety completed a business transaction, contract at least needs 30 days apart from the delivery time.
Position in storehouse: 0.5 times for being set as ATR is initially stopped loss, position in storehouse is according to greateset risk and stops loss position inverse.
Admission (does mostly example): being connected to client trading and does multiple instructions, system not admission at once, but price of waiting is prominent
It is broken, when price breaks through the last one parting high point of day figure, and price short-term fluctuation rate market price at once when rising to 1.5 or more
Admission, stopping loss the position for being placed on the admission price times ATR that subtracts 0.5 after admission.
Add storehouse for the first time: rise in price distance reaches 0.5 times of ATR, and according to position in storehouse plus a storehouse, two transactions stop loss position
It is modified to first single position that opens a position simultaneously.
Later plus storehouse: storehouse can be added by meeting following plus storehouse condition, and when adding storehouse, position in storehouse is set as one storehouse position in storehouse of front
50%, add storehouse position in storehouse to reduce mode in pyramid, the stop-loss position after adding storehouse is seated in the position of 3 times of ATR below SMA20, and same
Strokes list stops loss identical position before Shi Shangyi.
Add storehouse condition: 1) all trading cards are all in profit state before；2) the day figure apart from least 3 times of previous storehouse
ATR amplitude；3) price and SMA20 is touched, later again above take-up to SMA20.4) it stops loss when being accessible, account still is able to
Observe the 50% of maximum profit.5) plus behind storehouse stop loss position than before to stop loss position high.
It leaves the theatre: stopping loss to be accessible and leave the theatre or price breaks the low spot market prices of 20 section K lines by a fall and leaves the theatre.
In conclusion the present embodiment is not have trade variety to select suitable trade mode by analysis before being traded,
Risk judgment and quotation analysis are carried out in process of exchange, intelligence transaction avoids artificial irrational operation, can be to gold
The transaction for melting product carries out risk control, reduces transaction risk, improves investment yield.Use the technical side of the present embodiment
The deal maker of case can surmount in the market 90% dealer, survive on this market.Transaction is more felt at ease, and is no longer needed
It is on tenterhooks for a certain transaction of oneself, also more save worry, does not need whole stay in front of computer.
As shown in Fig. 2, based on the risk control system of big data analysis shown by the second embodiment of the present invention, including
Risk control server and user terminal, the risk control server and the user terminal communicate to connect.
The risk control server obtains raw information relevant to investment from different data sources, according to the original letter
Breath carries out predicting to determine trade mode to investment intent.Wherein, the trade mode stock, fund, bond, futures and outer junction
Easy mode.The present embodiment can be used crawler and complete to obtain raw information relevant to investment from different data sources, and crawler is according to master
Topic content selectively crawls the webpage of investment exchange website, it guaranteeing that page info acquires primarily to cover
Under the premise of lid rate, while there is higher information accuracy rate.Crawler described in this implementation mainly carries out in terms of following two
Improve: webpage quantity sharply increases, and ratio shared by webpage relevant to theme is reduced therewith, in order to guarantee that page info is adopted
The coverage rate and accuracy rate of collection, will screen the page in crawling process, retain and the higher webpage of topic correlativity.It climbs
Worm creeps needs band targetedly, utilizes the topic correlativity of certain algorithm calculating linking.
Further, URL queue to be crawled will be added with the higher URL of topic correlativity.Establish with destination server it
Between HTTP link；The webpage for obtaining investment exchange website, parses webpage, extracts the content text of the webpage；It is right
Extracted content text carries out Chinese word segmentation, counts the keyword with independent semanteme occurred in content text；Building
The text vector of Semantic Similarity is replaced the keyword for the condition that meets by calculating the semantic similarity between keyword
It changes, obtains the replaced text of semantic similar concept.
It in the present embodiment, is by the Semantic Similarity Measurement model based on distance by quantifying between keyword at this
Path length in body hierarchical network calculates similarity, it needs to pre-establish ontology hierarchical network, and the knot of network
Structure will directly affect the calculated result of semantic similarity, specific calculation formula are as follows: sim (w1, w2)=2maxlen-
Minlen, wherein maxlen is keyword w1And w2Maximum distance in ontology tree, minlen are keyword w1And w2In ontology
Minimum range in tree.
In other one or some embodiments, due to there will certainly be phase between two keywords in bulk junction paper mulberry
Same father's node, such as root node, and can have the associated path of more than one, specific calculation formula are as follows:Wherein l1And l2Refer to keyword w1And w2Between father's node w nearest to them
The shortest distance, len refers to root node to the shortest distance between w.
Further, in this embodiment using the semanteme for calculating keyword based on the Semantic Similarity Measurement model of content
Similarity.Due in this hierarchical network, if containing more how identical content in two keywords, then it represents that between the two
Semantic similarity is bigger；If containing more few identical content in two keywords, then it represents that semantic similarity between the two
It is smaller.The content that keyword includes can indicate by calculating the frequency that it occurs in a document, if there is frequency it is high,
It then indicates abundant in content；If there is frequency it is low, then it represents that content is deficient, specific calculation formula are as follows:Wherein p (w) refers to the probability that keyword w occurs, and N refers to the sum of keyword, if s (w1, w2) be
Keyword w1And w2The set of public father's node keyword, then the specific calculation formula of the public father's node of calculator are as follows:Thus keyword w1And w2Calculating formula of similarity are as follows:
sim(w1, w2)=1-pmin(w1, w2), if keyword w1And w2Included content account for including if, keyword w1
And w2Calculating formula of similarity are as follows:
Investment intent is carried out predicting to determine trade mode according to the semantic similar concept replaced text.Using institute
The replaced text of predicate justice similar concept can obtain all keywords in each webpage about trade mode, calculate
Keyword probability appeared in all texts of different trade modes is represented, it is maximum as final to choose wherein probability value
Predicted value, and then the trade mode of user's push can be determined directly as.
The trade mode is fed back to user terminal by the risk control server, and is obtained and used under the trade mode
The estimated account amount of money that can be put into family；By the way that the determining trade mode of prediction is fed back to user, can be provided for user reliably
With reference to, facilitate reduce risk.
The risk control server is according to the greateset risk coefficient under the account amount of money and the trade mode, verifying
Maximum can bear whether risk meets preset risk control control requirement；If the maximum, which can bear risk, meets preset wind
Danger control control requires, then the risk control server can enter transaction platform in time bracket for client feeds back and carry out
The prompt of transaction
First, verifying maximum can bear whether risk meets preset risk control control requirement, specifically: it will most strong wind
Dangerous factor alpha is compared with baseline risk factor beta, if greateset risk factor alpha is less than or equal to baseline risk factor beta, meets wind
Control requires, and is otherwise unsatisfactory for air control requirement；The calculation formula of the baseline risk factor beta is as follows: β=D × K (P × Rw-Q×
Rl)/(Rw× Rl) wherein: D, K, P, Q, Rw and Rl are the parameter obtained according to the statistics of previous transaction data.β is benchmark risk
Coefficient.D is tactful coefficient of efficiency, and effective strategy continues effective probability in following market before representing, this is one
Empirical value is arranged D=85% less than 100%, in the present embodiment and retains certain space come the uncertainty for future prospects.K
For tactful profitability coefficient of efficiency, the probability that the profitability of strategy can also continue in future prospects before representing,
This is also an empirical value, and less than 100%, K=70% is arranged in the present embodiment, and uncertain for future prospects retains one
Fixed space.P is the average of wins, is to win to trade to account for the percentage always traded, this is to test the statistical value obtained by history.Q
It is that loss transaction accounts for the percentage always traded, i.e. 1-P for the rate of being defeated.Rw is the net odds after winning, and is gold of getting a profit after winning
Volume accounts for the percentage of account capital, this is to test the statistical value obtained by history.Rl is the net loss rate after loss, is to lose
Deficit accounts for the percentage of account capital after damage, this is to test the statistical value obtained by history.
Second, whether the account capital meets the judgement of air control requirement, specifically: according to greateset risk coefficient inverse storehouse
Position and transaction amount meet air control requirement, are otherwise unsatisfactory for air control requirement if account capital is more than or equal to transaction amount；
Setting account capital is M, and greateset risk coefficient is α, and maximum operation amplitude is K point, and every point value is T, maximum
Loss plus warehouse receipt number are N, and i is the positive integer less than or equal to N；The greateset risk amount of money: MaxRisk=M × α；Add storehouse spacing: G=
K/(N-1)；I-th single maximum loss points: D (i)=K- (i-1) × G；I-th single risk amount: R (i)=D (i) × T ×
Lot；Then N mono- overall risk amount are as follows:It is equal to the specified calculating position in storehouse Lot of overall risk according to the greateset risk amount of money；
It enablesThen position in storehouse:Transaction amount Y=
M/Lot。
The important means of risk control, is according to account risk inverse when the transaction amount and position in storehouse of the present embodiment calculate
, it has been contemplated that the amplitude for adding storehouse and unfavorable market to run.Such as account capital is 100000 yuan, greateset risk coefficient is
20%, maximum operation amplitude is 1000 points, and every point value is 10, and maximum loss plus warehouse receipt number are 5.It is carried out by above formula
It is 0.8 hand, transaction amount=100000/0.8=125000 member that position in storehouse, which is calculated,.Because account amount of money is less than transaction amount,
Therefore it is unsatisfactory for air control requirement, system can remind deal maker to increase greateset risk coefficient or increase account amount of money, meet with this
Air control requirement.The operation of weight storehouse is the most important reason for leading to account risk, and the present embodiment does not allow deal maker oneself to select storehouse
Position, but position in storehouse is calculated automatically, and the position in storehouse calculated has covered worst situation, this, which is ensured that, does not have the transaction of weight storehouse
The case where occur.
The risk control server analyzes market variation in real time in process of exchange, and carries out adding storehouse according to market variation
Or it sells shares or leaves the theatre.In the present embodiment, in process of exchange, from the side such as basic side grave news event, technological side operation trend
Current quotations are analyzed in face, are carried out according to current quotations plus storehouse or are sold shares or leave the theatre.
First, basic side grave news event, by the media event gathered in advance for having set time point make admission,
The operation for adding storehouse, selling shares and leaving the theatre.System passes through news interface, automatic reading media event list, before set time point
Operated after judging news within 3-5 hours, these news such as: the resolution of Central Bank's interest rate, GBP data, commodity stocks variation,
Leader's speech, company annual report etc..For example advantageous news in admission or adds storehouse, for example unfavorable news, and pop-up alarm window is prohibited
Only deal maker places an order or reminds deal maker to trade or sell shares or leave the theatre with caution.For emergency event, because it announces the time not
Media event list can not be added in determination in advance, and when media event occurs, it is big that market have often been unfolded one
Wave, therefore can not evade in advance, but the trend system of can be used is filtered, such as after the generation of news time, under market
Drop range degree is bigger, has at this time generally all broken the equal line of MA20 by a fall, and distance MA20 is distant, we can be according to this
A feature-set: the equal line of price distance MA20 does not allow reversely to do more when surpassing 3 times of ATR, this way may be one
The normal market in part are mistaken for abnormal market, but can yet be regarded as a kind of effective method for the media event of this type.
Second, technological side operation trend determines to receive or refusal is traded by the judgement of the technical indicator to technological side
The instruction of member, if market are near important support resistance position, the breakthrough of cloth woods index is too far apart from equal line, well-behaved from excessive
Deng.
Such as short-swing trading mode plus storehouse error correction mode:
Because in the position in storehouse very light that head is singly used, to add storehouse to reserve enough spaces, therefore, short-swing trading in the future
Mode, which will use, in a planned way adds storehouse, by adding storehouse come cost of making thinner, realizes whole profit, entirely adding storehouse process is based on probability
What advantage calculated, more there is the art of composition compared to the subjective casual plus storehouse of deal maker, an average level of performance can be reached, system can prohibit
The only intervening act of deal maker.
It needs to calculate the Probability advantages for continuing to add storehouse when adding storehouse every time, only when Probability advantages are more than 65%
It can continue to add storehouse, otherwise continue waiting for being a better choice.
The calculations incorporated of Probability advantages three factors below:
A, average daily average fluctuation margin: add warehouse receipt plus storehouse interval require to be set in the 50% of per day fluctuating range with
On, in this way for different trade varieties can to avoid add storehouse too closely the problem of.
B, chance is remedied after adding warehouse receipt to malfunction again: using 85 percentile of average fluctuation margin of one wave band of currency
It measures, in fluctuating range of the day figure rank using ZigZag measure of criterions each wave band and sequence, chooses 85 percentages later
Fluctuating range value corresponding to position.
C, for current quotations for the degree of cooperation of short-term medium and long term trend, short-term trend cooperates is adding storehouse each time
Must all cooperate in the process, medium and long term trend cooperate in the case where, add storehouse spacing relatively small, in the hope of quick payoffs from
, in the ill-matched situation of medium and long term trend, storehouse spacing is added to need to be amplified to more than preceding primary plus storehouse interval.
If deal maker first singly do it is more after market drop at once, short-swing trading mode is not just left the theatre chance,
At this time system can be in waiting, after market are returned to rise, and system adds one single, position in storehouse and first single-phase automatically
Together, if the comprehensive profit of two lists meets the condition of leaving the theatre and can leave the theatre, short-swing trading mode most adds 5 storehouses, total storehouse
Position is still within lower level.
Short-swing trading mode obtains additional odds using storehouse is added, and actively assumes responsibility for risk in disk, its benefit is non-
Chang Mingxian, it can make the overall odds of transaction be greatly improved, and it is single that part loss is singly become profit.Add the pass in storehouse
Key content is that short-swing trading mode adds storehouse to be planned plus storehouse, and entirely plus storehouse is a part for being exactly trading program, adds storehouse
Position is all that ensure that by quantitative statistics plus storehouse strategy is still effective in the case where 85%, therefore have certain
Probability advantages.The amount of placing an order of initial position in storehouse and plus single amount of warehouse receipt be COMPREHENSIVE CALCULATING, guarantee plus storehouse after greateset risk still
So within the scope of agreement.
Such as short-swing trading mode is left the theatre:
Short-swing trading mode is left the theatre using Flat Amount, and every 10,000 yuan of 5 yuan of profits are left the theatre at once, adds storehouse, institute if having passed through
There is list to add up 5 yuan of profit to leave the theatre.
This mode of leaving the theatre is one kind of numerous modes of leaving the theatre, each mode is all each advantageous and disadvantage, without which
Mode of kind leaving the theatre with overwhelming advantage, short-swing trading mode leave the theatre be also it is the same, it, which can lose, captures a big wave and becomes
The chance of gesture, but benefit is also clearly, and it significantly improves the odds of system, compares fitting human nature.
Here key point is: short-swing trading mode has used the mode of leaving the theatre of a certain unified standard, receives this
The average probability advantage of kind of trade mode, in this way, deal maker is in different modes of leaving the theatre there is no need to wave, so as to big
The difficulty of amplitude reduction transaction.
The risk control method of commerce of the present embodiment, before being traded, further include by chain transaction method of testing or
It is the suitable trade mode of each trade variety selection that Meng Teka, which falls simulation, and the multi-exchange mould of each trade variety is arranged
Formula.Each trade variety has the characteristic of oneself, is not particularly suited for all trade modes, it is therefore desirable to assess each friendship
Easy kind for every kind of trade mode applicability, to be the suitable transaction mould of each trade variety selection according to historical data
Formula, and the trade mode of each trade variety is set.
First, chain transaction method of testing.Program chain transaction is allowed when System History test, it is vertical after terminating for one innings
Next innings of beginning of transaction is carved, trading frequency of this way in simulation test is typically all 5-10 times of real trade, is pressed
According to the transaction principles of certain mode, such way can cover worst situation, use the assessment transaction of such method
Odds and earning rate generally all can be more far short of what is expected than actual conditions, but meaningful in this, as the reference of air control.
Second, Meng Teka falls simulation.According to (average daily 3 friendships such as on 20 trade varieties of real trade frequency
Easily), it the time and direction that stochastic simulation places an order, allows automated system operation, the victory for being relatively close to truth may finally be obtained
Calculation and earning rate, because of the randomness of transaction, such way can not very likely cover worst situation, therefore can also adopt
With chain transaction method of testing.
The citing of short-swing trading mode:
It is applicable in market: foreign exchange；Minimum lever ratio: 8 times；
Compliance inspection:
Trade variety limitation are as follows: EURUSD, GBPUSD, AUDUSD, USDJPY, USDCHF, USDCAD, EURGBP,
AUDCAD, AUDNZD, EURJPY, EURAUD, GBPCAD totally 12 kinds
Greateset risk range is 10%-20%.
Minimum 2000 U.S. dollar of account capital.
Interest rate resolution relevant to currency, president of Central Bank, which talks to announcing first 5 hours, to be forbidden trading.
Forbid transaction of taking advantage of a situation when Tu and four hour rank great support resistance positions.
On H1 chart, price be more than the ATR amplitude of EMA48 three times when forbid transaction of taking advantage of a situation.
Position in storehouse: benchmark position in storehouse is that every 10,000 U.S. dollar 0.06-0.1 hand differs, and each currency is not exclusively.
Admission (does mostly example): being connected to client trading and does admission at once after multiple instructions.
Add storehouse: when storehouse condition being added to meet, according to position in storehouse plus a storehouse.
Add storehouse condition: 1) currency is generally in lossing state；2) there are no fill it up with 5 storehouses；3) apart from previous storehouse at least 0.5
Day again schemes ATR amplitude；4) 10 lines have at least been had been subjected to previous storehouse；5) price is small up to 1 above short-term line SMA20
When, during which never touch the equal line of SMA20；6) price take-up above intermediate trend Envelop (48,0.3)；7) nearest 5 is small
When it is interior without interest rate resolve, president of Central Bank speech etc. grave news event.
Leave the theatre: 5 U.S. dollars of whole profit are left the theatre.
The citing of wave band trade mode:
It is applicable in market: foreign exchange, futures.Account lever ratio is greater than 7 times.
Compliance inspection:
Trade variety limitation are as follows: XAUUSD, the GBPJPY of foreign exchange, preceding 10% kind of brisk trade in domestic futures
The stock of lever transaction can be used in (needing monthly dynamic adjustment), stock price index futures, external disk futures, external disk stock index, and lever ratio is necessary
More than 3.5 times.
Greateset risk range is the 0.4%-2.4% of capital.
Minimum 1500 U.S. dollar of foreign exchange account capital, futures account regard minimum lsp request difference of trade variety.
Without evading media event and technological side, trading instruction is preferably issued in advance before grave news event.
If it is there is the trade variety completed a business transaction, contract at least needs 30 days apart from the delivery time.
Position in storehouse: 0.5 times for being set as ATR is initially stopped loss, position in storehouse is according to greateset risk and stops loss position inverse.
Admission (does mostly example): being connected to client trading and does multiple instructions, system not admission at once, but price of waiting is prominent
It is broken, when price breaks through the last one parting high point of day figure, and price short-term fluctuation rate market price at once when rising to 1.5 or more
Admission, stopping loss the position for being placed on the admission price times ATR that subtracts 0.5 after admission.
Add storehouse for the first time: rise in price distance reaches 0.5 times of ATR, and according to position in storehouse plus a storehouse, two transactions stop loss position
It is modified to first single position that opens a position simultaneously.
Later plus storehouse: storehouse can be added by meeting following plus storehouse condition, and when adding storehouse, position in storehouse is set as one storehouse position in storehouse of front
50%, add storehouse position in storehouse to reduce mode in pyramid, the stop-loss position after adding storehouse is seated in the position of 3 times of ATR below SMA20, and same
Strokes list stops loss identical position before Shi Shangyi.
Add storehouse condition: 1) all trading cards are all in profit state before；2) the day figure apart from least 3 times of previous storehouse
ATR amplitude；3) price and SMA20 is touched, later again above take-up to SMA20.4) it stops loss when being accessible, account still is able to
Observe the 50% of maximum profit.5) plus behind storehouse stop loss position than before to stop loss position high.
It leaves the theatre: stopping loss to be accessible and leave the theatre or price breaks the low spot market prices of 20 section K lines by a fall and leaves the theatre.
In conclusion the present embodiment is not have trade variety to select suitable trade mode by analysis before being traded,
Risk judgment and quotation analysis are carried out in process of exchange, intelligence transaction avoids artificial irrational operation, can be to gold
The transaction for melting product carries out risk control, reduces transaction risk, improves investment yield.Use the technical side of the present embodiment
The deal maker of case can surmount in the market 90% dealer, survive on this market.Transaction is more felt at ease, and is no longer needed
It is on tenterhooks for a certain transaction of oneself, also more save worry, does not need whole stay in front of computer.
Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations；To the greatest extent
Pipe present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: its according to
So be possible to modify the technical solutions described in the foregoing embodiments, or to some or all of the technical features into
Row equivalent replacement；And these are modified or replaceed, various embodiments of the present invention technology that it does not separate the essence of the corresponding technical solution
The range of scheme should all cover within the scope of the claims and the description of the invention.
Claims (10)
1. the risk control method based on big data analysis, which comprises the steps of:
Raw information relevant to investment is obtained from different data sources, investment intent predict really according to the raw information
Determine trade mode；
The trade mode is fed back into user, and obtains the estimated account amount of money that can be put into of the user under the trade mode；
According to the greateset risk coefficient under the account amount of money and the trade mode, verifying maximum can bear whether risk meets
Preset risk control control requires；
If the maximum, which can bear risk, meets preset risk control control requirement, can be in time bracket for user feedback
The prompt traded into transaction platform.
2. the risk control method according to claim 1 based on big data analysis, which is characterized in that from different data sources
Raw information relevant to investment is obtained, investment intent is carried out according to the raw information to predict to determine that trade mode is specifically wrapped
It includes:
The exchange text information between investor is obtained from the webpage of each different investment exchange website, according to the exchange text
This information carries out predicting to determine trade mode to investment intent.
3. the risk control method according to claim 2 based on big data analysis, which is characterized in that it is described from it is each not
The exchange text information between investor is obtained in the webpage of same investment exchange website, according to the exchange text information to investment
Intention carries out predicting to determine that trade mode specifically includes:
Establish the HTTP link between destination server；
The webpage for obtaining investment exchange website, parses webpage, extracts the content text of the webpage；
Chinese word segmentation is carried out to extracted content text, counts the key with independent semanteme occurred in content text
Word；
The text vector for constructing Semantic Similarity, by calculating the semantic similarity between keyword, by the key for the condition that meets
Word is replaced, and obtains the replaced text of semantic similar concept；
Investment intent is carried out predicting to determine trade mode according to the semantic similar concept replaced text.
4. the risk control method according to claim 1 based on big data analysis, it is characterised in that: the trade mode
Stock, fund, bond, futures and foreign exchange transaction mode.
5. the risk control method according to claim 1 based on big data analysis, which is characterized in that the verifying is maximum
It can bear risk and whether meet preset risk control control to require to specifically include:
The greateset risk coefficient is compared with baseline risk coefficient；
If the greateset risk coefficient is less than or equal to baseline risk coefficient, meets preset risk control control and require；
If the greateset risk coefficient is more than or equal to baseline risk coefficient, it is unsatisfactory for preset risk control control and requires.
6. the risk control system based on big data analysis, including risk control server and user terminal, the risk control clothes
Business device and the user terminal communicate to connect, it is characterised in that:
The risk control server obtains raw information relevant to investment from different data sources, according to the raw information pair
Investment intent carries out predicting to determine trade mode；
The trade mode is fed back to user terminal by the risk control server, and to obtain the user under the trade mode pre-
Count the account amount of money that can be put into；
For the risk control server according to the greateset risk coefficient under the account amount of money and the trade mode, verifying is maximum
It can bear whether risk meets preset risk control control requirement；
If the maximum, which can bear risk, meets preset risk control control requirement, the risk control server is user
End feedback can enter the prompt that transaction platform is traded in time bracket.
7. the risk control system according to claim 1 based on big data analysis, which is characterized in that from different data sources
Raw information relevant to investment is obtained, investment intent is carried out according to the raw information to predict to determine that trade mode is specifically wrapped
It includes:
The risk control server obtains the exchange text between investor from the webpage of each different investment exchange website
Information carries out predicting to determine trade mode according to the exchange text information to investment intent.
8. the risk control system according to claim 2 based on big data analysis, which is characterized in that it is described from it is each not
The exchange text information between investor is obtained in the webpage of same investment exchange website, according to the exchange text information to investment
Intention carries out predicting to determine that trade mode specifically includes:
The risk control server establishes the HTTP link between destination server；
The risk control server obtains the webpage of investment exchange website, parses to webpage, extracts the interior of the webpage
Hold text；
The risk control server carries out Chinese word segmentation to extracted content text, counts the band occurred in content text
There is the keyword of independent semanteme；
The text vector of the risk control server construction Semantic Similarity, it is similar by calculating the semanteme between keyword
Degree, the keyword for the condition that meets is replaced, the replaced text of semantic similar concept is obtained；
The risk control server carries out prediction determination to investment intent according to the semantic replaced text of similar concept
Trade mode.
9. the risk control system according to claim 1 based on big data analysis, it is characterised in that: the trade mode
Stock, fund, bond, futures and foreign exchange transaction mode.
10. the risk control system according to claim 1 based on big data analysis, which is characterized in that the verifying is most
It can bear risk greatly and whether meet preset risk control control to require to specifically include:
The greateset risk coefficient is compared by the risk control server with baseline risk coefficient；
If the greateset risk coefficient is less than or equal to baseline risk coefficient, meets preset risk control control and require；
If the greateset risk coefficient is more than or equal to baseline risk coefficient, it is unsatisfactory for preset risk control control and requires.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811208219.5A CN109345391A (en) | 2018-10-17 | 2018-10-17 | Risk control method and system based on big data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811208219.5A CN109345391A (en) | 2018-10-17 | 2018-10-17 | Risk control method and system based on big data analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109345391A true CN109345391A (en) | 2019-02-15 |
Family
ID=65308962
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811208219.5A Pending CN109345391A (en) | 2018-10-17 | 2018-10-17 | Risk control method and system based on big data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109345391A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111563778A (en) * | 2020-05-12 | 2020-08-21 | 北京口袋财富信息科技有限公司 | Information pushing method and device |
| CN112561699A (en) * | 2020-12-11 | 2021-03-26 | 山证科技(深圳)有限公司 | Method, system and storage medium for processing dealer client data |
| CN112580917A (en) * | 2019-09-30 | 2021-03-30 | 深圳无域科技技术有限公司 | Client characteristic evaluation method and device |
| CN116342268A (en) * | 2023-01-04 | 2023-06-27 | 上甲数据服务(厦门)有限公司 | Futures data analysis method and system |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101059805A (en) * | 2007-03-29 | 2007-10-24 | 复旦大学 | Network flow and delaminated knowledge library based dynamic file clustering method |
| CN101930462A (en) * | 2010-08-20 | 2010-12-29 | 华中科技大学 | Comprehensive body similarity detection method |
| CN101986296A (en) * | 2010-10-28 | 2011-03-16 | 浙江大学 | Noise data cleaning method based on semantic ontology |
| US20150039533A1 (en) * | 2008-10-16 | 2015-02-05 | James G. GERBER | System and methods to provide for and communicate about safer and better returning asset-liability investment programs |
| CN105894376A (en) * | 2016-03-07 | 2016-08-24 | 浙江爱贷金融服务外包股份有限公司 | Financial account capital management system and method |
| CN105956924A (en) * | 2016-04-20 | 2016-09-21 | 中国科学院大学 | Financial derivative big data analysis, transaction and risk management system and method |
| CN106067083A (en) * | 2016-05-30 | 2016-11-02 | 上海二三四五网络控股集团股份有限公司 | Intellectual investment system data processing method based on magnanimity finance data |
| CN106294694A (en) * | 2016-08-08 | 2017-01-04 | 杭州麒谋网络科技有限公司 | Asset allocation big data analysis control system |
| CN108510393A (en) * | 2018-02-12 | 2018-09-07 | 岭尚（上海）科技发展有限公司 | Intelligence based on big data, which is thrown, cares for system and method |
-
2018
- 2018-10-17 CN CN201811208219.5A patent/CN109345391A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101059805A (en) * | 2007-03-29 | 2007-10-24 | 复旦大学 | Network flow and delaminated knowledge library based dynamic file clustering method |
| US20150039533A1 (en) * | 2008-10-16 | 2015-02-05 | James G. GERBER | System and methods to provide for and communicate about safer and better returning asset-liability investment programs |
| CN101930462A (en) * | 2010-08-20 | 2010-12-29 | 华中科技大学 | Comprehensive body similarity detection method |
| CN101986296A (en) * | 2010-10-28 | 2011-03-16 | 浙江大学 | Noise data cleaning method based on semantic ontology |
| CN105894376A (en) * | 2016-03-07 | 2016-08-24 | 浙江爱贷金融服务外包股份有限公司 | Financial account capital management system and method |
| CN105956924A (en) * | 2016-04-20 | 2016-09-21 | 中国科学院大学 | Financial derivative big data analysis, transaction and risk management system and method |
| CN106067083A (en) * | 2016-05-30 | 2016-11-02 | 上海二三四五网络控股集团股份有限公司 | Intellectual investment system data processing method based on magnanimity finance data |
| CN106294694A (en) * | 2016-08-08 | 2017-01-04 | 杭州麒谋网络科技有限公司 | Asset allocation big data analysis control system |
| CN108510393A (en) * | 2018-02-12 | 2018-09-07 | 岭尚（上海）科技发展有限公司 | Intelligence based on big data, which is thrown, cares for system and method |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112580917A (en) * | 2019-09-30 | 2021-03-30 | 深圳无域科技技术有限公司 | Client characteristic evaluation method and device |
| CN112580917B (en) * | 2019-09-30 | 2024-04-05 | 深圳无域科技技术有限公司 | Customer characteristic evaluation method and device |
| CN111563778A (en) * | 2020-05-12 | 2020-08-21 | 北京口袋财富信息科技有限公司 | Information pushing method and device |
| CN111563778B (en) * | 2020-05-12 | 2021-08-03 | 北京口袋财富信息科技有限公司 | Information pushing method and device |
| CN112561699A (en) * | 2020-12-11 | 2021-03-26 | 山证科技(深圳)有限公司 | Method, system and storage medium for processing dealer client data |
| CN116342268A (en) * | 2023-01-04 | 2023-06-27 | 上甲数据服务(厦门)有限公司 | Futures data analysis method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109345391A (en) | Risk control method and system based on big data analysis | |
| Easley et al. | Order form and information in securities markets | |
| Smith et al. | Market efficiency in person‐to‐person betting | |
| Hammoudeh et al. | Relationships among strategic commodities and with financial variables: A new look | |
| US20120179476A1 (en) | Method and system of remuneration for providing successful sales leads | |
| Andrén et al. | Exposure‐Based Cash‐Flow‐at‐Risk: An Alternative to VaR for Industrial Companies | |
| CN109859052A (en) | A kind of intelligent recommendation method, apparatus, storage medium and the server of investment tactics | |
| KR20160073251A (en) | Method, apparatus and computer program for managing financial product | |
| KR20210137939A (en) | The Method and System for Auto Stock Trading | |
| Jiang et al. | Technical analysis profitability without data snooping bias: evidence from Chinese stock market | |
| Zhang et al. | Celebrities and ordinaries in social networks: Who knows more information? | |
| Forbes et al. | Are financial analysts eager postmen of bubble psychology? Evidence in the United Kingdom | |
| CN102496126A (en) | Custody asset transaction data monitoring equipment | |
| Nofer | The value of social media for predicting stock returns: preconditions, instruments and performance analysis | |
| Zhang et al. | Effect of social media rumors on stock market volatility: A case of data mining in China | |
| Cucinelli et al. | Preventing the deterioration of bank loan portfolio quality: a focus on unlikely-to-pay loans | |
| Ivanov et al. | Banks' Strategic Responses to Supervisory Coverage: Evidence from a Natural Experiment | |
| Roy Trivedi | Technical analysis using Heiken Ashi Stochastic: To catch a trend, use a HASTOC | |
| Qian et al. | Does news travel slowly before a market crash? The role of margin traders | |
| CN108985931A (en) | A kind of risk control method of commerce and system | |
| Jiang | Order imbalance, liquidity, and market efficiency: evidence from the Chinese stock market | |
| Ponomareva et al. | Does monetary policy respond to uncertainty? Evidence from Australia | |
| Caporin et al. | The Ten Commandments for managing investments | |
| Bagci | Export behavior of German SMEs in the Eurozone | |
| Wilhite et al. | Corporate campaign contributions and legislative voting |
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: 20190215 |