CN107944673A - A kind of staple commodities price risk evaluation method and system - Google Patents
A kind of staple commodities price risk evaluation method and system Download PDFInfo
- Publication number
- CN107944673A CN107944673A CN201711098860.3A CN201711098860A CN107944673A CN 107944673 A CN107944673 A CN 107944673A CN 201711098860 A CN201711098860 A CN 201711098860A CN 107944673 A CN107944673 A CN 107944673A
- Authority
- CN
- China
- Prior art keywords
- commodity
- risk
- price
- sequence
- relevance
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0283—Price estimation or determination
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of staple commodities price risk evaluation method and system, the described method includes:Determine the relevance of each commodity price fluctuation, the commodity that the relevance of price fluctuation is exceeded to default correlation threshold divide a risk kind into;Wherein, a kind of commodity are only capable of one risk kind of cut-in;The corresponding price risk of each risk kind is estimated respectively.The high commodity of the correlation of price fluctuation are classified as a risk kind by the present invention, and then by the high a variety of commodity of the correlation of price fluctuation, that is a risk kind regards entirety as to monitor its price risk, the accuracy of price risk monitoring demand can be reached, the workload of price risk monitoring is greatly reduced again, saves price risk monitoring institute's cost source.
Description
Technical field
The present invention relates to Enterprise Risk Management technical field, particularly relate to a kind of staple commodities price risk evaluation method and
System.
Background technology
Currently, with the continuous expansion of scope of the enterprise, the type of merchandize involved in enterprise be also it is more and more numerous and diverse, especially
Divided for type of merchandize for thinner field, complicated various type of merchandize is brought to the corresponding statistical management work of enterprise
Inconvenience, such as staple commodities fields.Currently, it is related to the enterprise of staple commodities, more particularly, to the enterprise of staple commodities trade,
The parameter of price risk is identified using commodity as monitoring granularity to open quantity, price, in nearly value etc., is badly in need of monitoring every kind of commodity
All kinds of openings, but this kind of enterprise's commodity are various, simultaneous and same kind, eg. iron ores, due to differences such as quality, specification and/or the places of production
Also serve as different commodity to treat, eg. Australia iron ore, Brazilian iron ore, Indonesia's iron ore etc., cause the price risk of enterprise to be supervised
It is huge, it is necessary to expend vast resources to control workload.
The content of the invention
In view of this, can it is an object of the invention to propose a kind of staple commodities price risk evaluation method and system
Reduce commodity price risk monitoring work, and then the efficiency for risk monitoring and control of improving price.
Based on a kind of above-mentioned purpose staple commodities price risk evaluation method provided by the invention, including:
Determine the relevance of each commodity price fluctuation, the commodity that the relevance of price fluctuation is exceeded to default correlation threshold are drawn
For a risk kind;Wherein, a kind of commodity are only capable of one risk kind of cut-in;
The corresponding price risk of each risk kind is estimated respectively.
Optionally, described the step of determining the relevance that each commodity price fluctuates, includes:
Determine the relevance of the first commodity and the fluctuation of the second commodity price;Judge whether the relevance of the price fluctuation is big
In default correlation threshold, if so, then dividing the first commodity and the second commodity into a risk kind;Otherwise, by the first commodity
Divide a risk kind into, divide the second commodity into another risk kind;
For any commodity outside the first commodity and the second commodity, then from risky kind each take a commodity,
The relevance for taking each commodity to be fluctuated with the commodity price is determined respectively, and whether the peak of relevance exceedes determined by judgement
Default correlation threshold, if so, then incorporating the commodity in the corresponding risk kind of the highest commodity of relevance into;If it is not, then will
The commodity divide a new risk kind into.
Optionally, described the step of determining the relevance that each commodity price fluctuates, includes:
Determine the relevance of the first commodity and the fluctuation of the second commodity price;Judge whether the relevance of the price fluctuation is big
In default correlation threshold, if so, then dividing the first commodity and the second commodity into a risk kind;Otherwise, by the first commodity
Divide a risk kind into, divide the second commodity into another risk kind;
For each risk kind, the weighted average sequence of the benchmark price sequence of each commodity in the risk kind is sought
And as the corresponding benchmark price sequence of the risk kind;Wherein, for every kind of commodity, the weight of the benchmark price sequence of commodity
For the ratio of the gross weight of commodity contained by the commodity weight of itself and the affiliated risk kind of the commodity;
For any commodity outside the first commodity and the second commodity, the benchmark price sequence based on risk kind determines each
Whether risk kind and the relevance of commodity price fluctuation, the peak of relevance determined by judgement exceed default association threshold
Value, if so, then incorporating the commodity in the corresponding risk kind of the highest commodity of relevance into;If it is not, then the commodity are divided into
One new risk kind.
Optionally, the corresponding benchmark price sequence of the risk kind is calculated by equation below:
P=(P1*W1+P2*W2+ ...+Pn*Wn)/(W1+W2+ ...+Wn);Wherein, 1,2 ... n is in same risk kind
Comprising n kind commodity;P1 is the benchmark price sequence of commodity 1;P2 is the benchmark price sequence of commodity 2;Pn is the benchmark of commodity n
Price series;W1 is the weight of commodity 1;W2 is the weight of commodity 2;Wn is the weight of commodity n;P for commodity 1,2 ... the affiliated wind of n
The benchmark price sequence of dangerous kind.
Optionally, every the default cycle, commodity price fluctuation is redefined using commodity benchmark price sequence at that time
Relevance, and repartition the affiliated risk kind of each commodity according to the relevance of the commodity price fluctuation redefined.
Optionally, when increasing commodity newly, this method further includes:
Each takes a commodity from risky kind, determines to take each commodity to fluctuate with newly-increased commodity price respectively
Relevance;
Whether the peak of relevance determined by judgement exceedes default correlation threshold, is drawn if so, then increasing this newly commodity
Return in the corresponding risk kind of the highest commodity of relevance;If it is not, then increasing commodity newly divides a newly-increased risk kind into;
Alternatively,
For each risk kind, the weighted average sequence of the benchmark price sequence of each commodity in the risk kind is sought
As the corresponding benchmark price sequence of the risk kind;Wherein, it is for every kind of commodity, the weight of the benchmark price sequence of commodity
The ratio of the commodity weight of itself and the gross weight of commodity contained by the affiliated risk kind of the commodity;
Benchmark price sequence based on risk kind determines that each risk kind is associated with what the newly-increased commodity price fluctuated
Property, whether the peak of relevance determined by judgement exceedes default correlation threshold, if so, then increasing this newly commodity incorporates association into
In the corresponding risk kind of the highest commodity of property;If it is not, then increasing this newly commodity divides a new risk kind into.
Optionally, the relevance of the commodity price fluctuation is represented with commodity price correlation coefficient value;
Correspondingly, the correlation threshold is represented with commodity price correlation coefficient value, value range 0.5-1.
Optionally, the relevance of the commodity price fluctuation is represented with the corresponding price association rate score of intercommodity spread;
Correspondingly, the correlation threshold is represented with the corresponding price association rate score of intercommodity spread, value range 0.5-
1;
The computational methods of the corresponding price association rate score of the intercommodity spread include:
The corresponding benchmark price sequences of commodity i and commodity j are obtained respectively;
Calculate the corresponding sequence of differences of benchmark price sequence of the benchmark price sequence and commodity j of commodity i, the sequence of differences
Take absolute value to obtain price differential sequence;
Appoint and take the benchmark price sequence of commodity i or the benchmark price sequence of commodity j to calculate institute as benchmark price sequence
State the sequence of ratio values of price differential sequence and benchmark price sequence;
Count the price differential quantity for being no more than default price differential threshold value in the sequence of ratio values;
By the total quantity of element in the price differential quantity divided by price differential sequence, the price for obtaining commodity i with commodity j associates
Rate.
Optionally, the step of each risk kind of the estimation respectively corresponding price risk includes:
For each risk kind, the weight for the various risks opening that the risk kind includes is calculated;Wherein, risk kind
The weight of contained any sort risk exposure is the summation of the weight of the type risk exposure of each commodity in the risk kind;
For each risk kind, according to the benchmark price sequence of commodity contained by the risk kind, the risk kind is determined
Benchmark price sequence;
The weight of various risks opening and the benchmark price sequence of the risk kind in risk kind, calculating should
The various risks opening valuation of risk kind.
Optionally, the step of each risk kind of the estimation respectively corresponding price risk further includes:
According to the weight of each risk exposure of risk kind and the benchmark price sequence of the risk kind, the wind is calculated respectively
The Time-varying Copula of dangerous each risk exposure of kind.
Optionally, the benchmark price sequence for determining the risk kind includes:
Benchmark price sequence using the benchmark price sequence of any commodity in risk kind as the risk kind;Alternatively,
The weighted average of each commodity of the risk kind in the benchmark price of different time points is calculated respectively, will be counted
Benchmark price sequence of the sequence of weighted average as the risk kind;Wherein, for every kind of commodity, the benchmark price of commodity
The weight of sequence is the ratio of the commodity weight of itself and the gross weight of commodity contained by the affiliated risk kind of the commodity.
On the other hand, present invention also provides a kind of staple commodities price risk estimating system, including:
Risk kind division module, for determining the relevance of each commodity price fluctuation, the relevance of price fluctuation is surpassed
The commodity for crossing default correlation threshold divide a risk kind into;Wherein, a kind of commodity are only capable of one risk kind of cut-in;
Price risk estimation block, for the division according to the risk kind division module, estimation is each described respectively
The corresponding price risk of risk kind.
Optionally, the risk kind division module is additionally operable to, and determines the pass of the first commodity and the fluctuation of the second commodity price
Connection property;Judge whether the relevance of the price fluctuation is more than default correlation threshold, if so, then by the first commodity and the second business
Product divide a risk kind into;Otherwise, the first commodity are divided into a risk kind, divides the second commodity into another risk product
Kind;
For any commodity outside the first commodity and the second commodity, then from risky kind each take a commodity,
The relevance for taking each commodity to be fluctuated with the commodity price is determined respectively, and whether the peak of relevance exceedes determined by judgement
Default correlation threshold, if so, then incorporating the commodity in the corresponding risk kind of the highest commodity of relevance into;If it is not, then will
The commodity divide a new risk kind into.
Optionally, the risk kind division module is additionally operable to, and determines the pass of the first commodity and the fluctuation of the second commodity price
Connection property;Judge whether the relevance of the price fluctuation is more than default correlation threshold, if so, then by the first commodity and the second business
Product divide a risk kind into;Otherwise, the first commodity are divided into a risk kind, divides the second commodity into another risk product
Kind;
For each risk kind, the weighted average sequence of the benchmark price sequence of each commodity in the risk kind is sought
And as the corresponding benchmark price sequence of the risk kind;Wherein, for every kind of commodity, the weight of the benchmark price sequence of commodity
For the ratio of the gross weight of commodity contained by the commodity weight of itself and the affiliated risk kind of the commodity;
For any commodity outside the first commodity and the second commodity, the benchmark price sequence based on risk kind determines each
Whether risk kind and the relevance of commodity price fluctuation, the peak of relevance determined by judgement exceed default association threshold
Value, if so, then incorporating the commodity in the corresponding risk kind of the highest commodity of relevance into;If it is not, then the commodity are divided into
One new risk kind.
Optionally, the corresponding benchmark price sequence of the risk kind is calculated by equation below:
P=(P1*W1+P2*W2+ ...+Pn*Wn)/(W1+W2+ ...+Wn);Wherein, 1,2 ... n is in same risk kind
Comprising n kind commodity;P1 is the benchmark price sequence of commodity 1;P2 is the benchmark price sequence of commodity 2;Pn is the benchmark of commodity n
Price series;W1 is the weight of commodity 1;W2 is the weight of commodity 2;Wn is the weight of commodity n;P for commodity 1,2 ... the affiliated wind of n
The benchmark price sequence of dangerous kind.
Optionally, the system also includes the cycle to repartition module, for every the default cycle, controlling the risk
Kind division module redefines the relevance of commodity price fluctuation using the benchmark price sequence of commodity at that time, and according to again
The relevance of definite commodity price fluctuation repartitions the affiliated risk kind of each commodity.
Optionally, the risk kind division module is additionally operable to, when increasing commodity newly,
Each takes a commodity from risky kind, determines to take each commodity to fluctuate with newly-increased commodity price respectively
Relevance;
Whether the peak of relevance determined by judgement exceedes default correlation threshold, is drawn if so, then increasing this newly commodity
Return in the corresponding risk kind of the highest commodity of relevance;If it is not, then increasing commodity newly divides a newly-increased risk kind into;
Alternatively,
For each risk kind, the weighted average sequence of the benchmark price sequence of each commodity in the risk kind is sought
As the corresponding benchmark price sequence of the risk kind;Wherein, it is for every kind of commodity, the weight of the benchmark price sequence of commodity
The ratio of the commodity weight of itself and the gross weight of commodity contained by the affiliated risk kind of the commodity;
Benchmark price sequence based on risk kind determines that each risk kind is associated with what the newly-increased commodity price fluctuated
Property, whether the peak of relevance determined by judgement exceedes default correlation threshold, if so, then increasing this newly commodity incorporates association into
In the corresponding risk kind of the highest commodity of property;If it is not, then increasing this newly commodity divides a new risk kind into.
Optionally, the relevance of the commodity price fluctuation is represented with commodity price correlation coefficient value;
Correspondingly, the correlation threshold is represented with commodity correlation coefficient value, value range 0.5-1.
Optionally, the relevance of the commodity price fluctuation is represented with the corresponding price association rate score of intercommodity spread;
Correspondingly, the correlation threshold is represented with the corresponding price association rate score of intercommodity spread, value range 0.5-
1;
The computational methods of the corresponding price association rate score of the intercommodity spread include:
The corresponding benchmark price sequences of commodity i and commodity j are obtained respectively;
Calculate the corresponding sequence of differences of benchmark price sequence of the benchmark price sequence and commodity j of commodity i, the sequence of differences
Take absolute value to obtain price differential sequence;
Appoint and take the benchmark price sequence of commodity i or the benchmark price sequence of commodity j to calculate institute as benchmark price sequence
State the sequence of ratio values of price differential sequence and benchmark price sequence;
Count the price differential quantity for being no more than default price differential threshold value in the sequence of ratio values;
By the total quantity of element in the price differential quantity divided by price differential sequence, the price for obtaining commodity i with commodity j associates
Rate.
Optionally, the price risk estimation block includes:Open weight computing module, for for each risk product
Kind, calculates the weight for the various risks opening that the risk kind includes;Wherein, the weight of any sort risk exposure contained by risk kind
Measure as the summation of the weight of the type risk exposure of each commodity in the risk kind;
Benchmark price computing module, for for each risk kind, the standard price according to commodity contained by the risk kind
Lattice sequence, determines the benchmark price sequence of the risk kind;
Risk exposure estimator module, weight and the risk kind for the various risks opening in risk kind
Benchmark price sequence, calculate the various risks opening valuation of the risk kind.
Optionally, the price risk estimation block further includes:
Time-varying Copula computing module, for the weight of each risk exposure according to risk kind and the benchmark of the risk kind
Price series, calculate the Time-varying Copula of each risk exposure of risk kind respectively.
Optionally, the step of benchmark price sequence that risk kind is determined in the benchmark price computing module, includes:
Benchmark price sequence using the benchmark price sequence of any commodity in risk kind as the risk kind;Alternatively,
The weighted average of each commodity of the risk kind in the benchmark price of different time points is calculated respectively, will be counted
Benchmark price sequence of the sequence of weighted average as the risk kind;Wherein, for every kind of commodity, the benchmark price of commodity
The weight of sequence is the ratio of the commodity weight of itself and the gross weight of commodity contained by the affiliated risk kind of the commodity.
From the above it can be seen that staple commodities price risk evaluation method provided by the invention and system, have as follows
Advantage:
1st, the high commodity of the relevance of price fluctuation are incorporated into for a kind of risk kind, and using risk kind as price risk
The granularity of monitoring, in this way, the workload of price risk monitoring is greatly reduced, saves price risk monitoring institute's cost source.
2nd, the correspondence of timed maintenance commodity and risk kind, avoid commodity with the price fluctuation of time relevance with
Time change, causes the relevance of the price fluctuation of each commodity contained by risk kind itself no longer high, influences price risk monitoring
Accuracy.
Brief description of the drawings
Fig. 1 is the flow chart of one embodiment of staple commodities price risk evaluation method provided by the invention;
Fig. 2 is the flow chart of one embodiment that definite commodity price provided by the invention fluctuates relevance;
Fig. 3 is the flow chart for another embodiment that definite commodity price provided by the invention fluctuates relevance;
Fig. 4 is the algorithm flow chart provided by the invention that relevance is represented with price association rate score;
Fig. 5 is the algorithm flow chart of the corresponding price risk of estimation risk kind provided by the invention;
Fig. 6 is the structure chart of one embodiment of staple commodities price risk estimating system provided by the invention.
Embodiment
For the object, technical solutions and advantages of the present invention are more clearly understood, below in conjunction with specific embodiment, and reference
Attached drawing, the present invention is described in more detail.
It should be noted that all statements for using " first " and " second " are for differentiation two in the embodiment of the present invention
The non-equal entity of a same names or non-equal parameter, it is seen that " first " " second " should not only for the convenience of statement
The restriction to the embodiment of the present invention is interpreted as, following embodiment no longer illustrates this one by one.
A kind of improved estimation is proposed for currently for problem present in the estimation of staple commodities price risk, the application
Method, is the flow chart of one embodiment of staple commodities price risk evaluation method provided by the invention with reference to shown in Fig. 1.
As shown in Figure 1, herein described staple commodities price risk evaluation method includes:
Step 101, determine the relevance of each commodity price fluctuation, the relevance of price fluctuation is exceeded into default correlation threshold
Commodity divide a risk kind into;Wherein, a kind of commodity are only capable of one risk kind of cut-in;Based on the estimation to price risk
The influence of price fluctuation is essentially consisted in, and for the complicated commodity of species, association of the application according to price fluctuation between commodity
The height of property and then judge the degree of closeness of the price risk of different commodity, and then the approximate commodity of price risk are included into system
In one risk kind, the number of objects of commodity price risk estimation can be substantially reduced, improves the efficiency of estimation.It is appreciated that
It is that the default correlation threshold can be according to the different corresponding adjusted designs of relevance demand.In addition, the application determines to associate
Property algorithm include algorithm based on related coefficient or based on price differential, will specifically illustrate in following embodiment.Certainly, also may be used
To determine the relevance of commodity price fluctuation using other algorithms, the application does not limit this.
Step 102, the corresponding price risk of each risk kind is estimated respectively.That is, according to the wind in step 101
After dangerous kind division, the estimation of price risk can be directly carried out to each risk kind, directly obtains high-volume commodity correspondence
Price risk.It should be noted that the estimation process in step 102 was either one manually triggered estimated
Journey or according to certain mechanism timing or the estimation process of passive trigger-type.It is specific how to estimate can according to
The demand at family and set, the application is not construed as limiting this.
It is described to determine each commodity valency in step 101 with reference to shown in Fig. 2 in the application some optional embodiments
The step of relevance that lattice wave moves, specifically includes:
Step 201, the relevance of the first commodity and the fluctuation of the second commodity price is determined;Namely for staple commodities situation,
At random or can choose two commodity therein according to certain rule and first carry out correlation analysis, then gradually by the 3rd,
4th grade subsequent article and the commodity analyzed or being associated property of risk kind are analyzed, and then all commodity are gradually included in
Into different risk kinds.
Step 202, judge whether the relevance of the price fluctuation is more than default correlation threshold;In order to judge different business
The high and low level of product relevance is, it is necessary to which the demand estimated according to price risk presets the reference mark of a relevance height
Standard, namely correlation threshold, and then the judgement relevance that can quantify is high or low.
Step 203, if so, then dividing the first commodity and the second commodity into a risk kind;If the pass of price fluctuation
Connection property is higher than default correlation threshold, then represents that the relevance of two commodity is high, thus can be included into same risk product
In kind.
Step 204, otherwise, divide the first commodity into a risk kind, divide the second commodity into another risk kind;
If the relevance of price fluctuation is equal to or less than default correlation threshold, then it represents that the relevance of two commodity is not high, because
This cannot be included into same risk kind.
Step 205, for any commodity outside the first commodity and the second commodity, then from risky kind each take one
A commodity, determine the relevance for taking each commodity to be fluctuated with the commodity price respectively;After categorized partial risks kind,
Need by unclassified commodity compared with risk kind, the application provides one kind and randomly selects any commodity in risk kind
As the object compared, analyzed with unclassified being associated property of commodity, in this way, each risk kind and the commodity chosen
To obtain a relevance result.
Step 206, whether the peak of relevance determined by judgement exceedes default correlation threshold;Select relevance highest
End value and compared with default correlation threshold, what can so be selected does not sort out commodity and a certain risk kind
Relevance highest, and then can determine whether relevance is sufficiently high, to determine whether to be included into same risk product
In kind.
Step 207, if so, then incorporating the commodity in the corresponding risk kind of the highest commodity of relevance into;
Step 208, if it is not, then dividing the commodity into a new risk kind.
In this way, realizing definite and risk kind the division of relevance by the above process, while cause in enterprise
All commodity can divide to obtain according to correlation degree to have in the risk kind of close price risk, finally can not only
The efficiency and accuracy that commodity price risk is estimated enough are improved, and the operation for being conducive to related personnel is realized.
It is described to determine each commodity in step 101 with reference to shown in Fig. 3 in the application other optional embodiments
The step of relevance of price fluctuation, can also specifically include:
Step 301, the relevance of the first commodity and the fluctuation of the second commodity price is determined;
Step 302, judge whether the relevance of the price fluctuation is more than default correlation threshold;
Step 303, if so, then dividing the first commodity and the second commodity into a risk kind;
Step 304, otherwise, divide the first commodity into a risk kind, divide the second commodity into another risk kind;
Step 305, for each risk kind, the weighting of the benchmark price sequence of each commodity in the risk kind is asked
Mean sequence is simultaneously used as the corresponding benchmark price sequence of the risk kind;Wherein, for every kind of commodity, the benchmark price sequence of commodity
The weight of row is the ratio of the commodity weight of itself and the gross weight of commodity contained by the affiliated risk kind of the commodity;
Optionally, the corresponding benchmark price sequence of the risk kind is calculated by equation below:
P=(P1*W1+P2*W2+ ...+Pn*Wn)/(W1+W2+ ...+Wn);Wherein, 1,2 ... n is in same risk kind
Comprising n kind commodity;P1 is the benchmark price sequence of commodity 1;P2 is the benchmark price sequence of commodity 2;Pn is the benchmark of commodity n
Price series;W1 is the weight of commodity 1;W2 is the weight of commodity 2;Wn is the weight of commodity n;P for commodity 1,2 ... the affiliated wind of n
The benchmark price sequence of dangerous kind.
Step 306, for any commodity outside the first commodity and the second commodity, the benchmark price sequence based on risk kind
Determine each risk kind and the relevance of commodity price fluctuation;
Step 307, whether the peak of relevance determined by judgement exceedes default correlation threshold;
Step 308, if so, then incorporating the commodity in the corresponding risk kind of the highest commodity of relevance into;
Step 309, if it is not, then dividing the commodity into a new risk kind.
From above-described embodiment, the difference of embodiment illustrated in fig. 3 and embodiment illustrated in fig. 2 essentially consists in:Calculation risk
The mode of the corresponding benchmark price sequence of kind is different, used in embodiment illustrated in fig. 2 in the commodity that risk kind includes with
Machine chooses the benchmark price sequence of a commodity as the corresponding benchmark price sequence of risk kind, and embodiment illustrated in fig. 3 is then
The corresponding benchmark of risk kind is used as by the weighted average sequence of the benchmark price sequence of each commodity in calculation risk kind
Price series.Both respectively have advantage, the commodity valency that is particularly suitable in risk kind simply easy to implement for former approach
Lattice wave moves the very strong situation of relevance, namely when default correlation threshold chooses higher value, can use former approach, then
A kind of method then calculates more accurate, it is not easy to the difference of result randomly selected of analysis difference due to to(for) relevance compared with
Greatly, kind division is more accurately analyzed because this latter approach can be realized.
It is continually changing with the time based on commodity price fluctuation in the application some optional embodiments, so needing
Every the default cycle, the relevance of commodity price fluctuation, and foundation are redefined using commodity benchmark price sequence at that time
The relevance of the commodity price fluctuation redefined repartitions the affiliated risk kind of each commodity.This way it is possible to avoid analysis product
The division of kind cannot match with the real-time fluctuations of commodity price, and then can further optimize staple commodities price risk and estimate
Accuracy and reliability.It should be noted that the default cycle can according to the demand that different risks is estimated phase
The design adjustment answered, such as:The default cycle was used as using one month, a season, half a year, 1 year etc..
In the application some optional embodiments, when there are newly-increased commodity, it is thus necessary to determine that the wind described in newly-increased commodity
Dangerous kind repartitions a risk kind.It is identical with the division of the risk kind described in the above embodiments of the present application,
Determined for the risk kind volume for increasing commodity newly, it is as follows including at least two ways:
First way, each takes a commodity from risky kind, determines what is taken each commodity and increase newly respectively
The relevance of commodity price fluctuation;
Whether the peak of relevance determined by judgement exceedes default correlation threshold, is drawn if so, then increasing this newly commodity
Return in the corresponding risk kind of the highest commodity of relevance;If it is not, then increasing commodity newly divides a newly-increased risk kind into.
That is, it is used as comparison other by arbitrarily choosing a commodity in risky kind, then respectively with increasing newly
Being associated property of commodity is analyzed, and is relatively sentenced with default correlation threshold according to that highest analysis result of relevance accordingly
It is disconnected whether to be included into risky kind, or, it is necessary to newly a risk kind is increased to newly-increased commodity.
The second way, for each risk kind, seeks the benchmark price sequence of each commodity in the risk kind
Weighted average sequence is as the corresponding benchmark price sequence of the risk kind;Wherein, for every kind of commodity, the benchmark price of commodity
The weight of sequence is the ratio of the commodity weight of itself and the gross weight of commodity contained by the affiliated risk kind of the commodity;
Benchmark price sequence based on risk kind determines that each risk kind is associated with what the newly-increased commodity price fluctuated
Property, whether the peak of relevance determined by judgement exceedes default correlation threshold, if so, then increasing this newly commodity incorporates association into
In the corresponding risk kind of the highest commodity of property;If it is not, then increasing this newly commodity divides a new risk kind into.
That is, the weighted average sequence conduct of the benchmark price sequence of each commodity in each risk kind is obtained by calculation
The corresponding benchmark price sequence of the risk kind, then by the obtained corresponding benchmark price sequence of each risk kind respectively with
Newly-increased being associated property of commodity analysis, and then determine whether newly-increased commodity can be included into risky kind, or it is, it is necessary to right
Newly-increased commodity increase a risk kind newly.It should be noted that the algorithmic formula of weighted average sequence is calculated in the second way
It is identical with corresponding algorithmic formula in embodiment illustrated in fig. 3.
In the application some optional embodiments, the relevance of the commodity price fluctuation is with commodity price related coefficient
Value represents;The commodity price correlation coefficient value is calculated by equation below:
R (i, j)=(E (XY)-E (X) E (Y))/sqrt (E (XX) E (YY));
Wherein, X is the benchmark price sequence of commodity i;Y is the benchmark price sequence of commodity j;E (X) is the benchmark of commodity i
The corresponding desired value of price series;E (Y) is the corresponding desired value of benchmark price sequence of commodity j;E (XY) is the XY corresponding phases
Prestige value;E (XX) is the corresponding desired values of XX;E (YY) is the corresponding desired values of YY;R (i, j) is the commodity valency of commodity i and commodity j
Lattice related coefficient;
Correspondingly, the correlation threshold is represented with commodity price correlation coefficient value, value range 0.5-1.
In this way, the benchmark price sequence by obtaining two commodity, it is possible to it is related that corresponding commodity price is calculated
Coefficient, then compared with correlation threshold, can determine the high and low level of two commodity covariances.It should be noted that
The value range of correlation threshold shown in the embodiment can also be 0.6,0.7,0.8,0.9 etc., can be according to actual need
Ask corresponding design adjustment.Usually, the value of correlation threshold is bigger, then the commodity covariance in sorted risk kind
It is higher, so that commodity price risk is estimated more accurately, but it can equally cause the number of risk kind to increase, Ye Jizeng
Calculation amount is added.
In the application other optional embodiments, the relevance of the commodity price fluctuation can also be with intercommodity spread
Corresponding price association rate score represents;Correspondingly, the correlation threshold can also be with the corresponding price association rate of intercommodity spread
Numerical value expression, value range 0.5-1;
Specifically, with reference to shown in Fig. 4, for the algorithm flow provided by the invention that relevance is represented with price association rate score
Figure.The computational methods of the corresponding price association rate score of the intercommodity spread include:
Step 401, the corresponding benchmark price sequences of commodity i and commodity j are obtained respectively;For example, the price series of commodity i are
The price series of X=(x1, x2 ..., xm), commodity j are Y=(y1, y2 ..., ym);
Step 402, the sequence of differences of the benchmark price sequence of commodity i and the benchmark price sequence of commodity j, the difference are calculated
Sequence takes absolute value to obtain price differential sequence;For example, sequence of differences is (x1-y1, x2-y2 ..., xm-ym);Price differential sequence for (|
X1-y1 |, | x2-y2 | ..., | xm-ym |)
Step 403, the benchmark price sequence for taking commodity i or the benchmark price sequence of commodity j are appointed as benchmark price sequence
Row, calculate the sequence of ratio values of the price differential sequence and benchmark price sequence;Such as:Sequence of ratio values=(| (x1-y1)/x1 |, |
(x2-y2)/x2 | ..., | (xm-ym)/xm |);
Step 404, the quantity for the price differential for being no more than default price differential threshold value in the sequence of ratio values is counted;Optionally, it is described
Price differential threshold value value range for (0,0.3], be preferably 0.15, the price differential threshold value be used for weigh two commodity price differences whether surpass
Certain boundary line have been crossed, if the price differential threshold value is smaller, has represented that the granularity of measurement is thinner, risk estimation is more accurate, but together
When can also make it that resource occupation is bigger, therefore the price differential threshold value to the demand of accuracy and can be capable of providing according to enterprise
Resource respective design determines.
Step 405, by the total quantity of element in the price differential quantity divided by price differential sequence, the valency of commodity i and commodity j are obtained
Lattice association rate.
Above-mentioned two embodiment each provides the mode of different calculating commodity price fluctuation relevances, and one kind is using related
Coefficient value represents commodity price relevance, and another kind represents commodity price association using the corresponding price association rate score of price differential
Property.Actual implementation process can choose suitable algorithm accordingly or other efficient algorithms can also be used to represent as needed
Commodity price relevance.
In the application some optional embodiments, for how determining each risk kind of estimation in step 102
The process of corresponding price risk, gives specific implementation steps, is estimation risk provided by the invention with reference to shown in Fig. 5
The algorithm flow chart of the corresponding price risk of kind.The step for estimating the corresponding price risk of each risk kind respectively
Suddenly include:
Step 1021, for each risk kind, the weight for the various risks opening that the risk kind includes is calculated;Its
In, the weight of any sort risk exposure contained by risk kind is the weight of the type risk exposure of each commodity in the risk kind
Summation;Optionally, the type of the risk exposure includes:The definite promise that forecasted transaction is open, not yet confirms is open, true
The different risk exposure types such as the definite promise opening recognized, asset-liabilities opening;Therefore, it is necessary to pin in each risk kind
Its open weight is calculated each risk exposure type respectively accordingly;It is understood that actually described risk exposure
Type will have other kinds of risk exposure due to the difference of type of merchandize or the difference in market, and the application is simultaneously unlimited
The type of fixed specific risk exposure.
Step 1022, for each risk kind, according to the benchmark price sequence of commodity contained by the risk kind, determining should
The benchmark price sequence of risk kind;
Optionally, the method for the benchmark price sequence for determining the risk kind is as follows including at least two kinds:
First method, the benchmark price using the benchmark price sequence of any commodity in risk kind as the risk kind
Sequence;
Second method, calculates the weighted average of each commodity of the risk kind in the benchmark price of different time points respectively
Value, the benchmark price sequence using the sequence of counted weighted average as the risk kind;Wherein, for every kind of commodity, business
The weight of the benchmark price sequence of product is the commodity weight of itself and the gross weight of commodity contained by the affiliated risk kind of the commodity
Ratio.Specifically, the algorithm of the sequence of the weighted average can algorithm corresponding with embodiment illustrated in fig. 3 it is identical.
Further alternative, risk kind is calculated in the benchmark price sometime put by equation below:
Prv_i=p1_i*w1+p2_i*w2+p3_i*w3+ ...+pn_i*wn;
Wherein, pn_i is price of the n commodity in time point i;Wn is that the weight of n commodity accounts for the ratio of gross weight
Example;Prv_i is benchmark prices of the risk kind rv in time point i.By calculating respectively a series of time point, you can with
To the benchmark price sequence of risk kind.
Step 1023, the weight of various risks opening and the benchmark price sequence of the risk kind in risk kind
Row, calculate the various risks opening valuation of the risk kind.
Optionally, the risk exposure valuation is calculated by equation below:
Vrv_i=qrv*prv_i;
Wherein, qrv is the weight of a kind of risk exposure of risk kind rv;Prv_i is risk kind rv time point i's
Benchmark price;Vrv_i is such risk exposure valuation of risk kind rv in time point i.In this way, risk kind pair can be obtained
The different risk exposure valuations answered, and then a degree of estimate can be carried out to the price risk of staple commodities.
Further, above-mentioned calculating is merely able to the open progress valuation of various risks for single time point, it is difficult to risk
Kind has the estimation of a globality, therefore, described to estimate the corresponding valency of each risk kind respectively with reference to shown in Fig. 5
The step of lattice risk, further includes:
Step 1024, according to the weight of each risk exposure of risk kind and the benchmark price sequence of the risk kind, divide
The Time-varying Copula of each risk exposure of risk kind is not calculated.
Optionally, the Time-varying Copula for calculating each risk exposure includes at least two ways, as follows:
First way, the default Time-varying Copula algorithm use the parametric method of normal distribution;And pass through equation below
Calculate:
VaR=q* α * s*sqrt (h);Wherein, q is the weight of risk kind;Standard normal is used as using default confidence level b
The aggregate-value of distribution, α are the maximum deviation degree obtained with standardized normal distribution aggregation function;S is the appraisal sequence of risk kind
Corresponding standard deviation;H holds the time limit for setting;VaR is the Time-varying Copula of risk kind.
The second way, the default Time-varying Copula algorithm use historical method;And include the following steps:
Corresponding yield volatility is calculated according to the appraisal sequence of each risk kind;Earning rate passes through equation below
Calculate:
G_i=(L_i-L_i-1)/L_i-1;Wherein, L_i is the corresponding prices of time point i;L_i-1 is i-1 pairs of time point
The price answered;G_i is the corresponding earning rates of time point i;The earning rate is ranked up according to predefined procedure, obtains earning rate
Sequence G;
According to the confidence level b of setting and the corresponding sample total V of the yield volatility, in the yield volatility G
The earning rate value g_k nearest from b*V sequence numbers is found out, it is v=sqrt (h) * g_k that maximum loss ratio, which is calculated,;Wherein, sample
Total amount V represents the total quantity of earning rate in the yield volatility G;Such as 286 price points can obtain 285 earning rates
Point, sample total V are exactly 285.Further, if confidence level is 95%, then b*V=0.95*285=270.75, rounds up,
It is g_k to take the 271st earning rate after sequence.
Calculated according to the benchmark price that the maximum loss ratio, open weight and the risk kind of risk kind are current
Obtain Time-varying Copula;
The Time-varying Copula is calculated by equation below:
VaR=v*q*p;
Wherein, v is maximum loss ratio;Q is the open weight of risk kind;P is the current benchmark price of risk kind.
Wherein, the Time-varying Copula is represented to the worst expected loss in a holding period for determining confidential interval.For example, holding period is
1 day, confidence level 95%, VaR was 1,000,000 yuan, then it represents that possibility of the expected loss more than 1,000,000 yuan is not over 5%.
From above-described embodiment, the price fluctuation of commodity is mostly derived from based on commodity price risk, to commodity price wind
The monitoring of danger is monitoring to commodity price risk relevant parameter with the change of price fluctuation, the correlation of the price fluctuation of commodity
Property is higher, then the price risk relevant parameter of commodity is more close with the change of price fluctuation, or even tends to be identical, thus, this hair
The high commodity of the correlation of price fluctuation are classified as a risk kind by bright embodiment, and then the correlation of price fluctuation is high
A variety of commodity, i.e. a risk kind regard entirety as to monitor its price risk, can reach price risk monitoring demand
Accuracy, turn avoid the high workload amount for monitoring commodity price risk one by one, save price risk monitoring institute's cost source.
It is staple commodities price risk estimating system provided by the invention with reference to shown in Fig. 6 in the another aspect of the application
One embodiment flow chart.The staple commodities price risk estimating system includes:
Risk kind division module 501, for determining the relevance of each commodity price fluctuation, by the relevance of price fluctuation
Commodity more than default correlation threshold divide a risk kind into;Wherein, a kind of commodity are only capable of one risk kind of cut-in;
Price risk estimation block 502, for the division according to the risk kind division module, estimates each institute respectively
State the corresponding price risk of risk kind.
In the application some optional embodiments, the risk kind division module 501 is additionally operable to, and determines the first commodity
With the relevance of the second commodity price fluctuation;Judge whether the relevance of the price fluctuation is more than default correlation threshold, if
It is then to divide the first commodity and the second commodity into a risk kind;Otherwise, the first commodity are divided into a risk kind, will
Second commodity divide another risk kind into;
For any commodity outside the first commodity and the second commodity, then from risky kind each take a commodity,
The relevance for taking each commodity to be fluctuated with the commodity price is determined respectively, and whether the peak of relevance exceedes determined by judgement
Default correlation threshold, if so, then incorporating the commodity in the corresponding risk kind of the highest commodity of relevance into;If it is not, then will
The commodity divide a new risk kind into.
In the application some optional embodiments, the risk kind division module 501 is additionally operable to, and determines the first commodity
With the relevance of the second commodity price fluctuation;Judge whether the relevance of the price fluctuation is more than default correlation threshold, if
It is then to divide the first commodity and the second commodity into a risk kind;Otherwise, the first commodity are divided into a risk kind, will
Second commodity divide another risk kind into;
For each risk kind, the weighted average sequence of the benchmark price sequence of each commodity in the risk kind is sought
And as the corresponding benchmark price sequence of the risk kind;Wherein, for every kind of commodity, the weight of the benchmark price sequence of commodity
For the ratio of the gross weight of commodity contained by the commodity weight of itself and the affiliated risk kind of the commodity;
For any commodity outside the first commodity and the second commodity, the benchmark price sequence based on risk kind determines each
Whether risk kind and the relevance of commodity price fluctuation, the peak of relevance determined by judgement exceed default association threshold
Value, if so, then incorporating the commodity in the corresponding risk kind of the highest commodity of relevance into;If it is not, then the commodity are divided into
One new risk kind.
In the application some optional embodiments, the corresponding benchmark price sequence of the risk kind passes through equation below
Calculate:
P=(P1*W1+P2*W2+ ...+Pn*Wn)/(W1+W2+ ...+Wn);Wherein, 1,2 ... n is in same risk kind
Comprising n kind commodity;P1 is the benchmark price sequence of commodity 1;P2 is the benchmark price sequence of commodity 2;Pn is the benchmark of commodity n
Price series;W1 is the weight of commodity 1;W2 is the weight of commodity 2;Wn is the weight of commodity n;P for commodity 1,2 ... the affiliated wind of n
The benchmark price sequence of dangerous kind.
In the application some optional embodiments, the system also includes the cycle to repartition module 503, for every
In the default cycle, control the risk kind division module 501 to redefine commodity using the benchmark price sequence of commodity at that time
The relevance of price fluctuation, and repartition the affiliated risk product of each commodity according to the relevance of the commodity price fluctuation redefined
Kind.
In the application some optional embodiments, the risk kind division module 501 is additionally operable to, when increasing commodity newly,
Each takes a commodity from risky kind, determines to take each commodity to fluctuate with newly-increased commodity price respectively
Relevance;
Whether the peak of relevance determined by judgement exceedes default correlation threshold, is drawn if so, then increasing this newly commodity
Return in the corresponding risk kind of the highest commodity of relevance;If it is not, then increasing commodity newly divides a newly-increased risk kind into;
Alternatively,
For each risk kind, the weighted average sequence of the benchmark price sequence of each commodity in the risk kind is sought
As the corresponding benchmark price sequence of the risk kind;Wherein, it is for every kind of commodity, the weight of the benchmark price sequence of commodity
The ratio of the commodity weight of itself and the gross weight of commodity contained by the affiliated risk kind of the commodity;
Benchmark price sequence based on risk kind determines that each risk kind is associated with what the newly-increased commodity price fluctuated
Property, whether the peak of relevance determined by judgement exceedes default correlation threshold, if so, then increasing this newly commodity incorporates association into
In the corresponding risk kind of the highest commodity of property;If it is not, then increasing this newly commodity divides a new risk kind into.
In the application some optional embodiments, the relevance of the commodity price fluctuation is with commodity price related coefficient
Value represents;The commodity price correlation coefficient value is calculated by equation below:
R (i, j)=(E (XY)-E (X) E (Y))/sqrt (E (XX) E (YY));
Wherein, X is the benchmark price sequence of commodity i;Y is the benchmark price sequence of commodity j;E (X) is the benchmark of commodity i
The corresponding desired value of price series;E (Y) is the corresponding desired value of benchmark price sequence of commodity j;E (XY) is the XY corresponding phases
Prestige value;E (XX) is the corresponding desired values of XX;E (YY) is the corresponding desired values of YY;R (i, j) is the commodity valency of commodity i and commodity j
Lattice related coefficient;
Correspondingly, the correlation threshold is represented with commodity correlation coefficient value, value range 0.5-1.
In the application some optional embodiments, the relevance of the commodity price fluctuation is with the corresponding valency of intercommodity spread
Lattice association rate score represents;
Correspondingly, the correlation threshold is represented with the corresponding price association rate score of intercommodity spread, value range 0.5-
1;
The computational methods of the corresponding price association rate score of the intercommodity spread include:
The corresponding benchmark price sequences of commodity i and commodity j are obtained respectively;
Calculate the corresponding sequence of differences of benchmark price sequence of the benchmark price sequence and commodity j of commodity i, the sequence of differences
Take absolute value to obtain price differential sequence;
Appoint and take the benchmark price sequence of commodity i or the benchmark price sequence of commodity j to calculate institute as benchmark price sequence
State the sequence of ratio values of price differential sequence and benchmark price sequence;
Count the price differential quantity for being no more than default price differential threshold value in the sequence of ratio values;
By the total quantity of element in the price differential quantity divided by price differential sequence, the price for obtaining commodity i with commodity j associates
Rate.
In the application some optional embodiments, the price risk estimation block 502 includes:
Open weight computing module 5021, for for each risk kind, calculating all kinds of wind that the risk kind includes
The open weight in danger;Wherein, the weight of any sort risk exposure contained by risk kind be the risk kind in each commodity such
The summation of the weight of type risk exposure;
Benchmark price computing module 5022, for for each risk kind, the base according to commodity contained by the risk kind
Quasi- price series, determine the benchmark price sequence of the risk kind;
In the application some optional embodiments, the standard price of risk kind is determined in the benchmark price computing module
The step of lattice sequence, includes:
Benchmark price sequence using the benchmark price sequence of any commodity in risk kind as the risk kind;Alternatively,
The weighted average of each commodity of the risk kind in the benchmark price of different time points is calculated respectively, by counted weighted average
Benchmark price sequence of the sequence of value as the risk kind;Wherein, for every kind of commodity, the power of the benchmark price sequence of commodity
Weight is the ratio of the commodity weight of itself and the gross weight of commodity contained by the affiliated risk kind of the commodity.
Risk exposure estimator module 5023, weight and the risk for the various risks opening in risk kind
The benchmark price sequence of kind, calculates the various risks opening valuation of the risk kind.
Optionally, the risk exposure valuation is calculated by equation below:
Vrv_i=qrv*prv_i;
Wherein, qrv is the weight of a kind of risk exposure of risk kind rv;Prv_i is risk kind rv time point i's
Benchmark price;Vrv_i is such risk exposure valuation of risk kind rv in time point i.In this way, risk kind pair can be obtained
The different risk exposure valuations answered, and then a degree of estimate can be carried out to the price risk of staple commodities.
In the application some optional embodiments, the price risk estimation block 502 further includes:
Time-varying Copula computing module 5024, weight and the risk kind for each risk exposure according to risk kind
Benchmark price sequence, calculates the Time-varying Copula of each risk exposure of risk kind respectively.
Optionally, the Time-varying Copula for calculating each risk exposure includes at least two ways, as follows:
First way, the default Time-varying Copula algorithm use the parametric method of normal distribution;And pass through equation below
Calculate:
VaR=q* α * s*sqrt (h);Wherein, q is the weight of risk kind;Standard normal is used as using default confidence level b
The aggregate-value of distribution, α are the maximum deviation degree obtained with standardized normal distribution aggregation function;S is the appraisal sequence of risk kind
Corresponding standard deviation;H holds the time limit for setting;VaR is the Time-varying Copula of risk kind.
The second way, the default Time-varying Copula algorithm use historical method;And include the following steps:
Corresponding yield volatility is calculated according to the appraisal sequence of each risk kind;Earning rate passes through equation below
Calculate:
G_i=(L_i-L_i-1)/L_i-1;Wherein, L_i is the corresponding prices of time point i;L_i-1 is i-1 pairs of time point
The price answered;G_i is the corresponding earning rates of time point i;The earning rate is ranked up according to predefined procedure, obtains earning rate
Sequence G;
According to the confidence level b of setting and the corresponding sample total V of the yield volatility, in the yield volatility G
The earning rate value g_k nearest from b*V sequence numbers is found out, it is v=sqrt (h) * g_k that maximum loss ratio, which is calculated,;Wherein, sample
Total amount V represents the total quantity of earning rate in the yield volatility G;Such as 286 price points can obtain 285 earning rates
Point, sample total V are exactly 285.Further, if confidence level is 95%, then b*V=0.95*285=270.75, rounds up,
It is g_k to take the 271st earning rate after sequence.
Calculated according to the benchmark price that the maximum loss ratio, open weight and the risk kind of risk kind are current
Obtain Time-varying Copula;
The Time-varying Copula is calculated by equation below:
VaR=v*q*p;
Wherein, v is maximum loss ratio;Q is the open weight of risk kind;P is the current benchmark price of risk kind.
Wherein, the Time-varying Copula is represented to the worst expected loss in a holding period for determining confidential interval.For example, holding period is
1 day, confidence level 95%, VaR was 1,000,000 yuan, then it represents that possibility of the expected loss more than 1,000,000 yuan is not over 5%.
From above-described embodiment, staple commodities price risk estimating system described herein has and staple commodities valency
The identical or equivalent technical characteristic of lattice risk estimation methods, thus with the corresponding identical technique effect of method, herein not
Repeat and repeat.
Those of ordinary skills in the art should understand that:The discussion of any of the above embodiment is exemplary only, not
It is intended to imply that the scope of the present disclosure (including claim) is limited to these examples;Under the thinking of the present invention, above example
Or can also be combined between the technical characteristic in different embodiments, step can be realized with random order, and be existed such as
Many other changes of the upper different aspect of the invention, for simplicity, they are not provided in details.
In addition, to simplify explanation and discussing, and in order not to obscure the invention, can in the attached drawing provided
To show or can not show that the known power ground with integrated circuit (IC) chip and other components is connected.Furthermore, it is possible to
Device is shown in block diagram form, to avoid obscuring the invention, and this have also contemplated that following facts, i.e., on this
The details of the embodiment of a little block diagram arrangements be the platform that height depends on implementing the present invention (that is, these details should
It is completely in the range of the understanding of those skilled in the art).Elaborating detail (for example, circuit) with the description present invention's
In the case of exemplary embodiment, it will be apparent to those skilled in the art that can be in these no details
In the case of or implement the present invention in the case that these details change.Therefore, these descriptions are considered as illustrating
It is property rather than restricted.
Although having been incorporated with specific embodiment of the invention, invention has been described, according to retouching above
State, many replacements of these embodiments, modifications and variations will be apparent for those of ordinary skills.Example
Such as, other memory architectures (for example, dynamic ram (DRAM)) can use discussed embodiment.
The embodiment of the present invention be intended to fall within the broad range of appended claims it is all it is such replace,
Modifications and variations.Therefore, within the spirit and principles of the invention, any omission, modification, equivalent substitution, the improvement made
Deng should all be included in the protection scope of the present invention.
Claims (22)
- A kind of 1. staple commodities price risk evaluation method, it is characterised in that including:Determine the relevance of each commodity price fluctuation, the commodity that the relevance of price fluctuation is exceeded to default correlation threshold divide one into A risk kind;Wherein, a kind of commodity are only capable of one risk kind of cut-in;The corresponding price risk of each risk kind is estimated respectively.
- 2. according to the method described in claim 1, it is characterized in that, described the step of determining the relevance that each commodity price fluctuates Including:Determine the relevance of the first commodity and the fluctuation of the second commodity price;Judge whether the relevance of the price fluctuation is more than in advance If correlation threshold, if so, then dividing the first commodity and the second commodity into a risk kind;Otherwise, the first commodity are divided into One risk kind, divides the second commodity into another risk kind;For any commodity outside the first commodity and the second commodity, then from risky kind each take a commodity, respectively Definite taken each commodity and the relevance of commodity price fluctuation, it is default whether the peak of relevance determined by judgement exceedes Correlation threshold, if so, then incorporating the commodity in the corresponding risk kind of the highest commodity of relevance into;If it is not, then by the business Product divide a new risk kind into.
- 3. according to the method described in claim 1, it is characterized in that, described the step of determining the relevance that each commodity price fluctuates Including:Determine the relevance of the first commodity and the fluctuation of the second commodity price;Judge whether the relevance of the price fluctuation is more than in advance If correlation threshold, if so, then dividing the first commodity and the second commodity into a risk kind;Otherwise, the first commodity are divided into One risk kind, divides the second commodity into another risk kind;For each risk kind, seek the weighted average sequence of the benchmark price sequence of each commodity in the risk kind and make For the corresponding benchmark price sequence of the risk kind;Wherein, for every kind of commodity, the weight of the benchmark price sequence of commodity is should The ratio of the weight of commodity itself and the gross weight of commodity contained by the affiliated risk kind of the commodity;For any commodity outside the first commodity and the second commodity, the benchmark price sequence based on risk kind determines each risk Whether kind and the relevance of commodity price fluctuation, the peak of relevance determined by judgement exceed default correlation threshold, If so, then the commodity are incorporated into the corresponding risk kind of the highest commodity of relevance;If it is not, then divide the commodity into one New risk kind.
- 4. according to the method described in claim 3, it is characterized in that, the corresponding benchmark price sequence of the risk kind passes through such as Lower formula calculates:P=(P1*W1+P2*W2+ ...+Pn*Wn)/(W1+W2+ ...+Wn);Wherein, 1,2 ... n is to be included in same risk kind N kind commodity;P1 is the benchmark price sequence of commodity 1;P2 is the benchmark price sequence of commodity 2;Pn is the benchmark price of commodity n Sequence;W1 is the weight of commodity 1;W2 is the weight of commodity 2;Wn is the weight of commodity n;P for commodity 1,2 ... the affiliated risk product of n The benchmark price sequence of kind.
- 5. according to the method described in claim 1, it is characterized in that, every the default cycle, using commodity benchmark price at that time Sequence redefines the relevance of commodity price fluctuation, and is repartitioned according to the relevance of the commodity price fluctuation redefined Each affiliated risk kind of commodity.
- 6. according to the method described in claim 1, it is characterized in that, when increasing commodity newly, this method further includes:Each takes a commodity from risky kind, determines to take each commodity and the pass of newly-increased commodity price fluctuation respectively Connection property;Whether the peak of relevance determined by judgement exceedes default correlation threshold, if so, then increasing this newly commodity incorporates pass into In the corresponding risk kind of the highest commodity of connection property;If it is not, then increasing commodity newly divides a newly-increased risk kind into;Alternatively,For each risk kind, the weighted average sequence conduct of the benchmark price sequence of each commodity in the risk kind is asked The corresponding benchmark price sequence of the risk kind;Wherein, for every kind of commodity, the weight of the benchmark price sequence of commodity is the business The ratio of the weight of product itself and the gross weight of commodity contained by the affiliated risk kind of the commodity;Benchmark price sequence based on risk kind determines each risk kind and the relevance of the newly-increased commodity price fluctuation, sentences Whether the peak of relevance determined by disconnected exceedes default correlation threshold, if so, then increasing this newly commodity incorporates relevance into most In the corresponding risk kind of high commodity;If it is not, then increasing this newly commodity divides a new risk kind into.
- 7. method according to any one of claim 1 to 6, it is characterised in that the relevance of the commodity price fluctuation Represented with commodity price correlation coefficient value;Correspondingly, the correlation threshold is represented with commodity price correlation coefficient value, value range 0.5-1.
- 8. method according to any one of claim 1 to 6, it is characterised in that the relevance of the commodity price fluctuation Represented with the corresponding price association rate score of intercommodity spread;Correspondingly, the correlation threshold is represented with the corresponding price association rate score of intercommodity spread, value range 0.5-1;The computational methods of the corresponding price association rate score of the intercommodity spread include:The corresponding benchmark price sequences of commodity i and commodity j are obtained respectively;The corresponding sequence of differences of benchmark price sequence of the benchmark price sequence and commodity j of commodity i is calculated, which takes absolutely To being worth to price differential sequence;Appointing takes the benchmark price sequence of commodity i or the benchmark price sequence of commodity j to calculate the valency as benchmark price sequence Difference sequence and the sequence of ratio values of benchmark price sequence;Count the price differential quantity for being no more than default price differential threshold value in the sequence of ratio values;By the total quantity of element in the price differential quantity divided by price differential sequence, the price association rate of commodity i and commodity j is obtained.
- 9. according to the method described in claim 1, it is characterized in that, described estimate the corresponding valency of each risk kind respectively The step of lattice risk, includes:For each risk kind, the weight for the various risks opening that the risk kind includes is calculated;Wherein, contained by risk kind The weight of any sort risk exposure is the summation of the weight of the type risk exposure of each commodity in the risk kind;For each risk kind, according to the benchmark price sequence of commodity contained by the risk kind, the base of the risk kind is determined Quasi- price series;The weight of various risks opening and the benchmark price sequence of the risk kind in risk kind, calculate the risk The various risks opening valuation of kind.
- 10. according to the method described in claim 9, it is characterized in that, described estimate that each risk kind is corresponding respectively The step of price risk, further includes:According to the weight of each risk exposure of risk kind and the benchmark price sequence of the risk kind, the risk product are calculated respectively The Time-varying Copula of each risk exposure of kind.
- 11. the method according to claim 9 or 10, it is characterised in that the benchmark price sequence for determining the risk kind Row include:Benchmark price sequence using the benchmark price sequence of any commodity in risk kind as the risk kind;Alternatively,The weighted average of each commodity of the risk kind in the benchmark price of different time points is calculated respectively, by counted weighting Benchmark price sequence of the sequence of average value as the risk kind;Wherein, for every kind of commodity, the benchmark price sequence of commodity Weight gross weight of commodity contained by the commodity weight of itself and the affiliated risk kind of the commodity ratio.
- A kind of 12. staple commodities price risk estimating system, it is characterised in that including:Risk kind division module, for determining the relevance of each commodity price fluctuation, the relevance of price fluctuation is exceeded pre- If the commodity of correlation threshold divide a risk kind into;Wherein, a kind of commodity are only capable of one risk kind of cut-in;Price risk estimation block, for the division according to the risk kind division module, estimates each risk respectively The corresponding price risk of kind.
- 13. system according to claim 12, it is characterised in that the risk kind division module is additionally operable to, and determines One commodity and the relevance of the second commodity price fluctuation;Judge whether the relevance of the price fluctuation is more than default association threshold Value, if so, then dividing the first commodity and the second commodity into a risk kind;Otherwise, the first commodity are divided into a risk product Kind, divide the second commodity into another risk kind;For any commodity outside the first commodity and the second commodity, then from risky kind each take a commodity, respectively Definite taken each commodity and the relevance of commodity price fluctuation, it is default whether the peak of relevance determined by judgement exceedes Correlation threshold, if so, then incorporating the commodity in the corresponding risk kind of the highest commodity of relevance into;If it is not, then by the business Product divide a new risk kind into.
- 14. system according to claim 12, it is characterised in that the risk kind division module is additionally operable to, and determines One commodity and the relevance of the second commodity price fluctuation;Judge whether the relevance of the price fluctuation is more than default association threshold Value, if so, then dividing the first commodity and the second commodity into a risk kind;Otherwise, the first commodity are divided into a risk product Kind, divide the second commodity into another risk kind;For each risk kind, seek the weighted average sequence of the benchmark price sequence of each commodity in the risk kind and make For the corresponding benchmark price sequence of the risk kind;Wherein, for every kind of commodity, the weight of the benchmark price sequence of commodity is should The ratio of the weight of commodity itself and the gross weight of commodity contained by the affiliated risk kind of the commodity;For any commodity outside the first commodity and the second commodity, the benchmark price sequence based on risk kind determines each risk Whether kind and the relevance of commodity price fluctuation, the peak of relevance determined by judgement exceed default correlation threshold, If so, then the commodity are incorporated into the corresponding risk kind of the highest commodity of relevance;If it is not, then divide the commodity into one New risk kind.
- 15. system according to claim 14, it is characterised in that the corresponding benchmark price sequence of the risk kind passes through Equation below calculates:P=(P1*W1+P2*W2+ ...+Pn*Wn)/(W1+W2+ ...+Wn);Wherein, 1,2 ... n is to be included in same risk kind N kind commodity;P1 is the benchmark price sequence of commodity 1;P2 is the benchmark price sequence of commodity 2;Pn is the benchmark price of commodity n Sequence;W1 is the weight of commodity 1;W2 is the weight of commodity 2;Wn is the weight of commodity n;P for commodity 1,2 ... the affiliated risk product of n The benchmark price sequence of kind.
- 16. system according to claim 12, it is characterised in that the system also includes the cycle to repartition module, uses In every the default cycle, the risk kind division module is controlled to redefine business using the benchmark price sequence of commodity at that time The relevance of product price fluctuation, and repartition the affiliated risk of each commodity according to the relevance of the commodity price fluctuation redefined Kind.
- 17. system according to claim 12, it is characterised in that the risk kind division module is additionally operable to, and increases business newly During product,Each takes a commodity from risky kind, determines to take each commodity and the pass of newly-increased commodity price fluctuation respectively Connection property;Whether the peak of relevance determined by judgement exceedes default correlation threshold, if so, then increasing this newly commodity incorporates pass into In the corresponding risk kind of the highest commodity of connection property;If it is not, then increasing commodity newly divides a newly-increased risk kind into;Alternatively,For each risk kind, the weighted average sequence conduct of the benchmark price sequence of each commodity in the risk kind is asked The corresponding benchmark price sequence of the risk kind;Wherein, for every kind of commodity, the weight of the benchmark price sequence of commodity is the business The ratio of the weight of product itself and the gross weight of commodity contained by the affiliated risk kind of the commodity;Benchmark price sequence based on risk kind determines each risk kind and the relevance of the newly-increased commodity price fluctuation, sentences Whether the peak of relevance determined by disconnected exceedes default correlation threshold, if so, then increasing this newly commodity incorporates relevance into most In the corresponding risk kind of high commodity;If it is not, then increasing this newly commodity divides a new risk kind into.
- 18. the system according to any one of claim 12 to 17, it is characterised in that the association of the commodity price fluctuation Property is represented with commodity price correlation coefficient value;Correspondingly, the correlation threshold is represented with commodity correlation coefficient value, value range 0.5-1.
- 19. the system according to any one of claim 12 to 17, it is characterised in that the association of the commodity price fluctuation Property represented with intercommodity spread corresponding price association rate score;Correspondingly, the correlation threshold is represented with the corresponding price association rate score of intercommodity spread, value range 0.5-1;The computational methods of the corresponding price association rate score of the intercommodity spread include:The corresponding benchmark price sequences of commodity i and commodity j are obtained respectively;The corresponding sequence of differences of benchmark price sequence of the benchmark price sequence and commodity j of commodity i is calculated, which takes absolutely To being worth to price differential sequence;Appointing takes the benchmark price sequence of commodity i or the benchmark price sequence of commodity j to calculate the valency as benchmark price sequence Difference sequence and the sequence of ratio values of benchmark price sequence;Count the price differential quantity for being no more than default price differential threshold value in the sequence of ratio values;By the total quantity of element in the price differential quantity divided by price differential sequence, the price association rate of commodity i and commodity j is obtained.
- 20. system according to claim 12, it is characterised in that the price risk estimation block includes:Open weight Computing module, for for each risk kind, calculating the weight for the various risks opening that the risk kind includes;Wherein, wind The weight of any sort risk exposure contained by dangerous kind is the total of the weight of the type risk exposure of each commodity in the risk kind With;Benchmark price computing module, for for each risk kind, the benchmark price sequence according to commodity contained by the risk kind Row, determine the benchmark price sequence of the risk kind;Risk exposure estimator module, for the weight of various risks opening and the base of the risk kind in risk kind Quasi- price series, calculate the various risks opening valuation of the risk kind.
- 21. system according to claim 20, it is characterised in that the price risk estimation block further includes:Time-varying Copula computing module, for the weight of each risk exposure according to risk kind and the benchmark price of the risk kind Sequence, calculates the Time-varying Copula of each risk exposure of risk kind respectively.
- 22. the system according to claim 20 or 21, it is characterised in that risk is determined in the benchmark price computing module The step of benchmark price sequence of kind, includes:Benchmark price sequence using the benchmark price sequence of any commodity in risk kind as the risk kind;Alternatively,The weighted average of each commodity of the risk kind in the benchmark price of different time points is calculated respectively, by counted weighting Benchmark price sequence of the sequence of average value as the risk kind;Wherein, for every kind of commodity, the benchmark price sequence of commodity Weight gross weight of commodity contained by the commodity weight of itself and the affiliated risk kind of the commodity ratio.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711098860.3A CN107944673A (en) | 2017-11-09 | 2017-11-09 | A kind of staple commodities price risk evaluation method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711098860.3A CN107944673A (en) | 2017-11-09 | 2017-11-09 | A kind of staple commodities price risk evaluation method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107944673A true CN107944673A (en) | 2018-04-20 |
Family
ID=61933569
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711098860.3A Pending CN107944673A (en) | 2017-11-09 | 2017-11-09 | A kind of staple commodities price risk evaluation method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107944673A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109685303A (en) * | 2018-08-21 | 2019-04-26 | 平安普惠企业管理有限公司 | Financial product risk monitoring and control method, apparatus, equipment and readable storage medium storing program for executing |
CN109783385A (en) * | 2019-01-14 | 2019-05-21 | 中国银行股份有限公司 | A kind of product test method and apparatus |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106355501A (en) * | 2016-11-14 | 2017-01-25 | 洪志令 | Method for recommending stock selection and avoiding risk based on strong correlation analysis of stock |
-
2017
- 2017-11-09 CN CN201711098860.3A patent/CN107944673A/en active Pending
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106355501A (en) * | 2016-11-14 | 2017-01-25 | 洪志令 | Method for recommending stock selection and avoiding risk based on strong correlation analysis of stock |
Non-Patent Citations (1)
Title |
---|
申尊焕: "《资产定价与风险管理》", 31 March 2016 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109685303A (en) * | 2018-08-21 | 2019-04-26 | 平安普惠企业管理有限公司 | Financial product risk monitoring and control method, apparatus, equipment and readable storage medium storing program for executing |
CN109783385A (en) * | 2019-01-14 | 2019-05-21 | 中国银行股份有限公司 | A kind of product test method and apparatus |
CN109783385B (en) * | 2019-01-14 | 2022-05-24 | 中国银行股份有限公司 | Product testing method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Buncic et al. | Forecasting copper prices with dynamic averaging and selection models | |
Huisman et al. | VaR-x: Fat tails in financial risk management | |
Wied et al. | A new fluctuation test for constant variances with applications to finance | |
Fahmy et al. | The Fisher effect: new evidence and implications | |
KR101975448B1 (en) | Evaluation System and Method for Big Data Based Commodity Investment Recommendation Algorithms Using Artificial Intelligence | |
Aye et al. | Long-and short-run relationships between house and stock prices in South Africa: a nonparametric approach | |
CN107944673A (en) | A kind of staple commodities price risk evaluation method and system | |
Lo et al. | Analysis of relationships between hourly electricity price and load in deregulated real-time power markets | |
Mensi et al. | Modeling cross-correlations and efficiency of Islamic and conventional banks from Saudi Arabia: Evidence from MF-DFA and MF-DXA approaches | |
CN104820942A (en) | Electricity market trade evaluation criterion measuring and calculating method based on hierarchical clustering | |
Foley | Statistical equilibrium in a simple labor market | |
Lv et al. | The mean reversion/persistence of financial cycles: Empirical evidence for 24 countries worldwide | |
Sapio | Modeling the distribution of day-ahead electricity returns: a comparison | |
Hsu et al. | How to choose mutual funds that perform well? Evidence from Taiwan | |
Urrutia et al. | Modelling and forecasting the exchange rate of the Philippines: A time series analysis | |
CN110084400A (en) | Information forecasting method, device, computer equipment and storage medium | |
Smolny | Monopolistic price setting and supply rigidities in a disequilibrium framework | |
CN108305171A (en) | A kind of mutual fund earnings analysis method and device | |
CN109903070A (en) | Data digging method, device and computer readable storage medium | |
CN109360041A (en) | Trade company's methods of exhibiting, device, electronic equipment and storage medium | |
KR20090102884A (en) | Method and apparatus for selecting stock item which price is synchronized with the price index of stocks | |
Saman | Asymmetric interaction between stock price index and exchange rates: Empirical evidence for Romania | |
Alvarez-Ramirez et al. | Dynamics of electricity market correlations | |
KR102461056B1 (en) | System for providing information for investment using performance pattern and method thereof | |
Mamipour et al. | Non-linear relationships among oil price, gold price and stock market returns in Iran: A multivariate regime-switching approach |
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 |