CN104867039A - Vehicle member derivative credit evaluation method under influence of many factors - Google Patents

Abstract

The invention discloses a vehicle member derivative credit evaluation method under influence of many factors. The method includes the steps of: dividing numerous factors influencing the credit of vehicle members into sequential layers associated with one another, and establishing a credit evaluation feedback mechanism; and expanding the quantity and quality of users participating into credit evaluation based on trust transfer and big data analysis, establishing a direct trust circle and a derivative trust circle of a goods owner member, and then obtaining the derivative trust reference grades before carriage transaction with respect to the vehicle members to be selected made by the goods owner member. The credit evaluation feedback mechanism can better process the feedback information and output to serve as the credit grade of the vehicle member about the carriage transaction, and the derivative trust reference grades can effectively reduce false evaluation and credit speculation of the vehicle members in the platform, so that the goods owner members can reasonably judge the comprehensive credit conditions of the vehicle members to be selected and make selection according with own carriage requirements, and thereby reducing carriage credit risks and improving carriage efficiency.

Description

Vehicle member under a kind of multifactor impact derives credit assessment method

Technical field

The vehicle member that the present invention relates under a kind of multifactor impact derives credit assessment method, to be applicable in the business platform in logistics transportation the Quantitatively Selecting in multidimensional situation, objective, science being carried out to vehicle member, comprehensive, static and dynamic Status combines, to belong to large data message analysis technical field.

Background technology

The development of infotech, promote ecommerce to be combined with the degree of depth of logistics transportation industry, from providing information to concluding the business, logistics transportation transaction business platform referent and the content provided are more and more huger with complexity, continue operation reliably and be unable to do without sound credit security mechanism, particularly to the composite factor quantitative estimation method of vehicle member.Existing logistics transportation transaction platform indiscriminately imitates the credit quantitative estimation method of commodity electron-like business platform, although simply easy to operate, but applicability is weak, intuitively cannot reflect the real haulage level of carrier fully, to such an extent as to other users of logistics transportation e-commerce platform cannot obtain true and reliable carrier's integrated status, seriously constrain rationality and the science of its transport.Therefore, current logistics transportation industry needs one to be conducive to user's objective reasonably selection vehicle member, thus improves effective vehicle member credit assessment method of conevying efficiency.

Summary of the invention

Goal of the invention: for Problems existing in logistics transportation transaction platform quantitative evaluation system in prior art with not enough, taking into full account the multinomial key factor affecting vehicle member credit, according to information feed back and derivative trusting relationship, provide a kind of and derive credit assessment method based on the vehicle member under the multifactor impact of Fuzzy Analysis Method.

Technical scheme: the vehicle member under a kind of multifactor impact derives credit assessment method, Fuzzy Analysis Method and analytical hierarchy process is used the acknowledgement of consignment power of vehicle member to be quantized, the transmission of utilization information expands evaluation of effectively concluding the business, and the business platform being applicable to logistics transportation transaction carries out comprehensively vehicle member, the selection of science.Specifically comprise the steps:

(1) extract platform data library information, data analysis index for selection, sets up the recursive hierarchy structure of index

Selective extraction and carrier's credit appraisal relevant information from database, with reference to the influence factor that this platform of industry selecting index needs, according to the mutual relationship between factor index and between each level index, set up the recursive hierarchy structure of assessment indicator system.Destination layer: setting decision objective is vehicle member credit scoring.Rule layer: the credit scoring of vehicle member basic condition, the credit scoring of vehicle member dynamic transaction situation and the credit scoring of vehicle membership service situation.Solution layer: choose the vehicle member driving age, guarantee service that vehicle member car age, vehicle member affiliated unit scale, vehicle member participate in, vehicle member reaching on the time, vehicle member dispatch a car speed, vehicle membership service attitude, single acknowledgement of consignment dealing money, the financial status of owner of cargo member self, business number occurs vehicle member, damage rate of goods appears in vehicle member and vehicle member meets with complaining time tens of two evaluation indexes as solution layer.

(2) determine that credit index is marked according to grade field (the five-grade marking system)

1. the credit index scoring of vehicle member basic condition

The guarantee quantity of service that vehicle member driving age, vehicle member car age, vehicle member affiliated unit capital scale, vehicle member participate in is four the credit indexs determining vehicle member basic condition, their scoring is determined according to grade field, such as the score v of index vehicle member driving age ₁grade field determine as shown in the table:

The grade field of other indexs is determined and index vehicle member driving age score v ₁grade field determine similar.

2. the credit index scoring of vehicle member dynamic transaction situation

The dynamic credit evaluating system index of vehicle member is: the credit standing that vehicle member reaching on the time starts shipment the ground time, vehicle member dispatches a car speed (weighing with reaching destination time of receiving on time), vehicle membership service attitude, single carry dealing money, owner of cargo member self.In order to the financial status of vehicle member objectively can be shown, prevent maliciously poor commenting, be necessary that owner of cargo member self credit standing considering to evaluate singly carries dealing money with this.The score of each index is determined according to grade field.

3. the credit index scoring of vehicle membership service situation

The credit scoring model of platform to vehicle membership service situation is: business number occurs vehicle member, damage rate of goods appears in vehicle member, vehicle member meets with complaining number of times.Their scoring is determined according to grade field.

(3) Judgement Matricies

Judgment matrix refers to and compares between two same level index, provides the judgment value of their relative importances, and whole index, after judging between two, just can form a multilevel iudge matrix.For determining the concrete numerical value in judgment matrix, between conventional scale general 1 to 5.Wherein 1 is two factor no less importants; 3 is that two factors are compared, previous than rear one important a little; 5 is that two factors are compared, previous than rear one obvious important; 2,4 significance levels between 3, between 5.If evaluation index e _iwith evaluation index e _jimportance is in a ratio of b _ij, then e _iwith e _jthe ratio of importance be b _ij.

(4) the weight coefficient method of index under single criterion condition is calculated

According to gained judgment matrix, calculate Maximum characteristic root and proper vector.Main calculation procedure is as follows:

1. calculate the product of each row element of judgment matrix, formula is

$M_i=\underset{j=1}{\overset{n}{\Π}}{a}_{ij},i=1,2,......,n$

2. each row M is calculated _in power root formula be

${\stackrel{\‾}{W}}_i=\sqrt[n]{M_i}$

3. to vector carry out normalization process, namely

$W_i=\frac{\stackrel{\‾}{W_i}}{\underset{j=1}{\overset{n}{\Σ}}\stackrel{\‾}{W_i}}$

W _ibe the weight coefficient value of required index.

(5) calculate judgment matrix Maximum characteristic root and proper vector, carry out the consistency check of two-level index

As the exponent number n=1 of judgment matrix, when 2, matrix always has crash consistency; As the exponent number n>2 of judgment matrix, random Consistency Ratio CR is adopted to check its consistance.Main calculation procedure is as follows:

1. the Maximum characteristic root λ of judgment matrix is asked _maxformula is

${\mathrm{\λ}}_{max}=\underset{i=1}{\overset{n}{\Σ}}\frac{W_i}{{\mathrm{nW}}_i}$

2. calculate coincident indicator CI, formula is

n is judgment matrix exponent number

3. calculate Consistency Ratio CR, formula is

wherein RI is random index, and its value sees the following form:

The value table of Aver-age Random Consistency Index RI

Exponent number

3

4

5

6

7

8

9

10

RI

0.58

0.90

1.12

1.24

1.32

1.41

1.45

1.49

As CR<0.10, namely think that judgment matrix has satisfied consistance.If do not meet consistance, then re-construct judgment matrix before must returning.

(6) calculate the final weight of output, obtain the credit scoring of owner of cargo member k to vehicle member C

W _irepresent solution layer i-th (i=1,2 ..., 12) individual evaluation index to the weight of criterion straton target, in like manner can obtain the weights W of rule layer sub-goal to general objective _j(j=1,2,3).

Each credit scoring model score that integrating step (2) obtains, can draw:

The credit scoring of vehicle member basic condition:

The credit scoring of vehicle member dynamic transaction situation:

The credit scoring of vehicle membership service situation:

Vehicle member credit comprehensive grading:

(7) the accumulated weights credit scoring of vehicle member C is calculated

After every single acknowledgement of consignment transaction completes, vehicle member C all can obtain owner of cargo member k (k=1,2,3 ...) and feedback credit appraisal S _kC, along with the carrying out of transaction, feedback credit appraisal number can get more and more, and other members inconvenient knowing the credit situation of vehicle member C, therefore, has the accumulated weights credit scoring of vehicle member C as the feedback credit scoring of vehicle member C, it is the mark CREDIT SCORE of vehicle member C. as the objective credit situation reference of owner of cargo member to vehicle C, not by the impact of people around.

(8) owner of cargo member A information extraction, excavates and had the direct circles of trust of concluding the business with vehicle member C

Step (1)-(7) have calculated the cumulative review credit scoring of vehicle member according to the credit appraisal feedback information of owner of cargo member a large amount of after transaction, reduce the credit risk of network trading to a certain extent, but cannot solve malice evaluate and credit propagandize the false evaluation behavior brought, another characteristic of the present invention utilizes information transmission technique to expand effective credit scoring exactly, reduce false evaluation, allow vehicle member (for convenience of description hereafter with the vehicle member C designate) credit standing of owner of cargo member's (for convenience of description hereafter with owner of cargo member A designate) self-demand of more being fitted.

The log-on message of owner of cargo member A is extracted from platform database, Transaction Information and circle of friends information etc. are correlated with basic interactive information, excavate the direct circles of trust of owner of cargo member A about vehicle member C, comprise the circle of friends of the owner of cargo member A that trading activity occurred with vehicle member C, the large V owner of cargo old credit grade of qualifications and record of service of trading activity occurring high with vehicle member C (comprises the large enterprises that platform volume of freight is large and stable, the large member owner of cargo such as senior member) two classes, this two classes owner of cargo member and owner of cargo member A have direct trusting relationship, their evaluation information is the credit information of owner of cargo member A most reference value.

Owner of cargo member A is about the direct circles of trust L of vehicle member C _aC=m|m ∈ R, m=1,2 ..., M}

Wherein, m is the owner of cargo member having direct trusting relationship with owner of cargo member A.

(9) calculate direct degree of belief and directly trust coefficient, obtaining one-level and derive credit with reference to scoring

In the direct circles of trust of owner of cargo member A, owner of cargo member A and they have direct trusting relationship, use P _amrepresent owner of cargo member A and the direct degree of belief of directly trusting owner of cargo member m, wherein 1≤P _am≤ 5, the method according to grade field is determined;

C _amrepresent the direct trust coefficient of owner of cargo member A and owner of cargo member m,

Then the one-level of owner of cargo member A derives credit with reference to scoring for:

${\tilde{S}}_{A1C}=\underset{m=1}{\overset{M}{\&Sigma;}}{C}_{Am}{S}_{mC}=\underset{m=1}{\overset{M}{\&Sigma;}}\frac{P_{Am}}{\underset{m=1}{\overset{M}{\&Sigma;}}{P}_{Am}}{S}_{mC}=\frac{\underset{m=1}{\overset{M}{\&Sigma;}}{P}_{Am}{S}_{mC}}{\underset{m=1}{\overset{M}{\&Sigma;}}{P}_{Am}}$

Wherein S _mCfor owner of cargo member m (is the S in step 6 to credit appraisal after the acknowledgement of consignment transaction of vehicle member C _kC, the feedback credit appraisal for vehicle after the every single cross of the owner of cargo easily), be the true direct dealing evaluation of owner of cargo member m to vehicle member C, if owner of cargo member m did not occur directly to carry transaction with vehicle member C, then S _mC=0.

The one-level of owner of cargo member A derives credit with reference to scoring the i.e. reference credit score that obtains according to the credit appraisal of " friend " in direct circles of trust to vehicle member C of owner of cargo member A, this reference credit score has the owner of cargo of direct trusting relationship to obtain according to owner of cargo member A, be compared to stranger, their evaluation more directly affects owner of cargo member A to a great extent to credit view before the transaction of vehicle member C, so this reference credit score compared to the accumulated weights credit scoring of owner of cargo member C reference value is had more, because it decreases the impact maliciously evaluated and bring to a great extent concerning owner of cargo member A.

(10) expand derivative circles of trust, obtain the derivative trust of n level with reference to scoring

Have a kind of situation to be derivative credit situation before owner of cargo member A wants to know the transaction of vehicle member C, but inside his direct circles of trust, nobody and vehicle member C occurred to carry transaction, and one-level cannot be obtained and derive credit with reference to scoring.But in platform large database concept, all owner of cargo members have connected into a complicated pass net, we are owner of cargo member m (m=1 in the direct circles of trust of owner of cargo member A, 2, ..., M) one-level that direct circles of trust becomes owner of cargo member A derives circles of trust, if the one-level of owner of cargo member A derives in circles of trust people b (b ∈ L _mC=b|b ∈ R, b=1,2 ..., B}) occurred to carry transaction with vehicle member C, then can obtain the secondary derivative trust of owner of cargo member A about vehicle member C with reference to scoring for:

${\tilde{S}}_{A2C}=\underset{b=1}{\overset{B}{\&Sigma;}}\underset{m=1}{\overset{M}{\&Sigma;}}{C}_{Am}{C}_{mb}{S}_{bC}$

Wherein S _bCfor owner of cargo member b is to credit appraisal after the acknowledgement of consignment transaction of vehicle member C, if owner of cargo member b did not occur directly to carry transaction with vehicle member C, then S _bC=0.

Utilize large data mining technology in like manner the derivative circles of trust of owner of cargo member A can be expanded, the n level derivative trust of owner of cargo member A about vehicle member C can be obtained with reference to scoring for:

${\tilde{S}}_{AnC}=\underset{b=1}{\overset{B}{\&Sigma;}}...\underset{m=1}{\overset{M}{\&Sigma;}}{C}_{Am}\mathrm{...}{C}_{mb}{S}_{bC}.$

Beneficial effect: compared with prior art, the present invention has two major features, first is to affect the many factors of vehicle member credit by being divided into the orderly level connected each other, set up feedback credit appraisal mechanism, export owner of cargo member to the credit scoring of this vehicle member according to the feedback information of owner of cargo member after acknowledgement of consignment transaction; Second point is based on large data mining, sets up the direct circles of trust of owner of cargo member and derivative circles of trust, obtains owner of cargo member and trusts with reference to scoring about derivative before the acknowledgement of consignment transaction of vehicle member to be selected.According to accumulated weights credit scoring and the derivative trust reference scoring of vehicle member, platform owner of cargo member can know the comprehensive credit situation of vehicle member objectively, solve the false credit appraisal problem of platform vehicle member to a great extent, make the owner of cargo or other members in countless vehicle member, find satisfied vehicle member fast, objectively and make the selection meeting oneself demand.

Accompanying drawing explanation

Fig. 1 is method flow diagram of the present invention;

Fig. 2 is the hierarchical structure model of the embodiment of the present invention;

Fig. 3 is the circles of trust model of embodiment of the present invention owner of cargo member A.

Embodiment

Below in conjunction with specific embodiment, illustrate the present invention further, these embodiments should be understood only be not used in for illustration of the present invention and limit the scope of the invention, after having read the present invention, the amendment of those skilled in the art to the various equivalent form of value of the present invention has all fallen within the application's claims limited range.

(1) extract platform data library information, data analysis index for selection, sets up the recursive hierarchy structure of index

Selective extraction and carrier's credit appraisal relevant information from database, with reference to the influence factor that this platform of industry selecting index needs, according to the mutual relationship between factor index and between each level index, set up the recursive hierarchy structure of assessment indicator system as accompanying drawing 2.Destination layer: setting decision objective is vehicle member credit scoring.Rule layer: the credit scoring of vehicle member basic condition, the credit scoring of vehicle member dynamic transaction situation and the credit scoring of vehicle membership service situation.Solution layer: choose the vehicle member driving age, guarantee service that vehicle member car age, vehicle member affiliated unit scale, vehicle member participate in, vehicle member reaching on the time, vehicle member dispatch a car speed, vehicle membership service attitude, single acknowledgement of consignment dealing money, the financial status of owner of cargo member self, business number occurs vehicle member, damage rate of goods appears in vehicle member and vehicle member meets with complaining time tens of two evaluation indexes as solution layer.

(2) determine that credit index is marked according to grade field (the five-grade marking system)

According to the feedback information of the present embodiment vehicle member basic condition, dynamic transaction situation and vehicle membership service situation, use Fuzzy Analysis Method to carry out criterion and quantity and grade field, the credit index scoring determined is as shown in table 1 below:

Table 1 embodiment vehicle member credit index is marked

Sequence number	Embodiment vehicle member index	Acknowledgement of consignment Transaction Information	Score v i
				1	The vehicle member driving age	8 years	3 points
2	Vehicle member car age	8 years	3 points
				3	Vehicle member affiliated unit scale	50-100 ten thousand Renminbi	2 points
4	The guarantee service that vehicle member participates in	All	5 points
				5	Vehicle member reaching on the time	< 10 minutes	5 points
6	Vehicle member dispatches a car speed	< 10 minutes	5 points
				7	Vehicle membership service attitude	Better	4 points
8	Single acknowledgement of consignment dealing money	150000	3 points
				9	The credit standing of owner of cargo member self	4 points	4 points
10	There is business number in vehicle member	12 is single	2 points
				11	There is damage rate of goods in vehicle member	0	5 points
12	Vehicle member meets with complaining number of times	1	4 points

(3) Judgement Matricies

Affect the solution layer index judgment matrix A of vehicle member basic condition credit scoring ₁for:

$A_1=\left[\begin{array}{cccc}1& 2& 1/3& 1/2\\ 1/2& 1& 1/3& 1/4\\ 3& 3& 1& 1/2\\ 2& 4& 2& 1\end{array}\right]$

Affect the solution layer index judgment matrix A of vehicle member dynamic transaction situation credit scoring ₂for:

$A_2=\left[\begin{array}{ccccc}1& 1/2& 4& 2& 4\\ 2& 1& 4& 3& 5\\ 1/4& 1/4& 1& 1/2& 2\\ 1/2& 1/3& 2& 1& 2\\ 1/4& 1/5& 1/2& 1/2& 1\end{array}\right]$

Affect the solution layer index judgment matrix A of vehicle membership service situation credit scoring ₃for:

$A_3=\left[\begin{array}{ccc}1& 1/3& 1/5\\ 3& 1& 1/2\\ 5& 2& 1\end{array}\right]$

The rule layer index judgment matrix B affecting destination layer vehicle meeting credit scoring is:

$B=\left[\begin{array}{ccc}1& 1/3& 1/5\\ 3& 1& 1/2\\ 5& 2& 1\end{array}\right]$

(4) difference compute matrix Maximum characteristic root and vector matrix, and carry out consistency check

According to gained judgment matrix, calculate Maximum characteristic root and proper vector.Main calculation procedure is as follows:

Matrix A ₁characteristic vector W _a1=(0.163,0.097,0.312,0.428) ^t, λ _max=4.117141, coincident indicator random index RI=0.90, Consistency Ratio $\mathrm{CR}=\frac{\mathrm{CI}}{\mathrm{RI}}=0.042286<0.1,$ Meet consistance.

Matrix A ₂characteristic vector W _a2=(0.092,0.062,0.282,0.175,0.389) ^t, λ _max=5, coincident indicator random index RI=1.12, Consistency Ratio meet consistance.

Matrix A ₃characteristic vector W _a3=(0.109,0.309,0.582) ^t, λ _max=3.00695, coincident indicator random index RI=0.58, consistency check coefficient $CR=\frac{CI}{RI}=0.006<0.1,$ Therefore, consistance is met.

The characteristic vector W of matrix B _b=(0.109,0.309,0.582) ^t, λ _max=3.00695, coincident indicator random index RI=0.58, consistency check coefficient $CR=\frac{CI}{RI}=0.006<0.1,$ Therefore, consistance is met.

(4) calculate the final weight of output, obtain the credit scoring of owner of cargo member k to vehicle member C

W _i∈ (W _a1, W _a2, W _a3) represent solution layer i-th (i=1,2 ..., 12) individual evaluation index to the weight of criterion straton target, in like manner can obtain the weights W of rule layer sub-goal to general objective _j∈ W _b(j=1,2,3).

Each credit scoring model score that integrating step (2) obtains, can draw:

The credit scoring of vehicle member basic condition: point

The credit scoring of vehicle member dynamic transaction situation: point

The credit scoring of vehicle membership service situation: point

Vehicle member credit comprehensive grading: point

dividing is credit appraisal after the vehicle member C obtained based on the information feed back of owner of cargo k after a single acknowledgement of consignment has been concluded the business once concludes the business, and namely carrying the credit appraisal of transaction owner of cargo member k to vehicle member C for this time is 3.662 points (full marks are 5 points).

(7) the accumulated weights credit scoring of vehicle member C is calculated

After every single acknowledgement of consignment transaction completes, vehicle member C all can obtain owner of cargo member k (k=1,2,3 ...) and feedback credit appraisal S _kC, along with the carrying out of transaction, feedback credit appraisal number can get more and more, and other members inconvenient knowing the credit situation of vehicle member C, therefore, has the accumulated weights credit scoring of vehicle member C as the feedback credit scoring of vehicle member C.The acknowledgement of consignment transaction scoring record of the vehicle member of the present embodiment is as following table 2, and the accumulative credit scoring of every single cross easy rear vehicle member C can change.

The transaction record of table 2 embodiment vehicle member

(8) owner of cargo member A information extraction, excavates and had the direct circles of trust of concluding the business with vehicle member C

The relevant basic interactive information such as the log-on message of owner of cargo member A, Transaction Information and circle of friends information are extracted from platform database, excavate the direct circles of trust of owner of cargo member A about vehicle member C as Fig. 3, comprise there is the owner of cargo member A of trading activity with vehicle member C circle of friends, there is the high large V owner of cargo two class of the old credit grade of qualifications and record of service of trading activity with vehicle member C, this two classes owner of cargo member and owner of cargo member A have direct trusting relationship, and their evaluation information is the credit information of owner of cargo member A most reference value

Owner of cargo member A is about the direct circles of trust L of vehicle member C _aC=m|m ∈ R, m=1,2 ..., M}

Wherein, m is the owner of cargo member having direct trusting relationship with owner of cargo member A.

(9) calculate direct degree of belief and directly trust coefficient, obtaining one-level and derive credit with reference to scoring

In the direct circles of trust of owner of cargo member A, owner of cargo member A and they have direct trusting relationship, use P _amrepresent owner of cargo member A and the direct degree of belief of directly trusting owner of cargo member m, wherein 1≤P _am≤ 5;

C _amrepresent the direct trust coefficient of owner of cargo member A and owner of cargo member m,

Then the one-level of owner of cargo member A derives credit with reference to scoring for:

${\tilde{S}}_{A1C}=\underset{m=1}{\overset{M}{\&Sigma;}}{C}_{Am}{S}_{mC}=\underset{m=1}{\overset{M}{\&Sigma;}}\frac{P_{Am}}{\underset{m=1}{\overset{M}{\&Sigma;}}{P}_{Am}}{S}_{mC}=\frac{\underset{m=1}{\overset{M}{\&Sigma;}}{P}_{Am}{S}_{mC}}{\underset{m=1}{\overset{M}{\&Sigma;}}{P}_{Am}}$

Wherein S _mCfor owner of cargo member m is to credit appraisal after the acknowledgement of consignment transaction of vehicle member C, if owner of cargo member m did not occur directly to carry transaction with vehicle member C, then S _mC=0.

The owner of cargo member a, b, c and vehicle member C is had to have to carry and conclude the business in the direct circles of trust of the present embodiment owner of cargo member A, trading situation in article transaction record of the 1st, 4,5 in table 2, then the direct circles of trust scoring of owner of cargo member A and one-level derivative reference score information as shown in table 3 below:

The direct circles of trust situation of table 3 embodiment owner of cargo member

So concerning owner of cargo member A, the credit standing of vehicle member C has two, and one is the accumulated weights credit scoring of C point, another is that the derivative trust of one-level of C is with reference to scoring point.Accumulated weights credit scoring concerning A be to the one of C the most directly, more objective credit situation knows, be obtain according to the All Activity historical record of C, the demand not by " friend " affects; Derivative trust is with reference to scoring concerning A be basis on further understanding to C credit situation, be " friend " direct dealing contact basis on obtain.The one-level of owner of cargo member A derives credit with reference to scoring the i.e. reference credit score that obtains according to the credit appraisal of " friend " in direct circles of trust to vehicle member C of owner of cargo member A, this reference credit score has the owner of cargo of direct trusting relationship to obtain according to owner of cargo member A, be compared to stranger, their evaluation more directly affects owner of cargo member A to a great extent to credit view before the transaction of vehicle member C, so this reference credit score compared to the accumulated weights credit scoring of owner of cargo member C reference value is had more, because it decreases the impact that false evaluation is brought to a great extent concerning owner of cargo member A.

Claims (1)

1. the vehicle member under multifactor impact derives a credit assessment method, it is characterized in that, specifically comprises the steps:

(1) extract platform data library information, data analysis index for selection, sets up the recursive hierarchy structure of index

Selective extraction and carrier's credit appraisal relevant information from database, with reference to the influence factor that this platform of industry selecting index needs, according to the mutual relationship between factor index and between each level index, set up the recursive hierarchy structure of assessment indicator system; Destination layer: setting decision objective is vehicle member credit scoring; Rule layer: the credit scoring of vehicle member basic condition, the credit scoring of vehicle member dynamic transaction situation and the credit scoring of vehicle membership service situation; Solution layer: choose the vehicle member driving age, guarantee service that vehicle member car age, vehicle member affiliated unit scale, vehicle member participate in, vehicle member reaching on the time, vehicle member dispatch a car speed, vehicle membership service attitude, single acknowledgement of consignment dealing money, the financial status of owner of cargo member self, business number occurs vehicle member, damage rate of goods appears in vehicle member and vehicle member meets with complaining time tens of two evaluation indexes as solution layer;

(2) mark according to grade field determination credit index

1. the credit index scoring of vehicle member basic condition

The guarantee quantity of service that vehicle member driving age, vehicle member car age, vehicle member affiliated unit capital scale, vehicle member participate in is four the credit indexs determining vehicle member basic condition, and their scoring is determined according to grade field;

2. the credit index scoring of vehicle member dynamic transaction situation

The dynamic credit evaluating system index of vehicle member is: the credit standing that vehicle member reaching on the time starts shipment the ground time, vehicle member dispatches a car speed (weighing with reaching destination time of receiving on time), vehicle membership service attitude, single carry dealing money, owner of cargo member self;

3. the credit index scoring of vehicle membership service situation

The credit scoring model of platform to vehicle membership service situation is: business number occurs vehicle member, damage rate of goods appears in vehicle member, vehicle member meets with complaining number of times; Their scoring is determined according to grade field;

(3) Judgement Matricies

Judgment matrix refers to and compares between two same level index, provides the judgment value of their relative importances, and whole index, after judging between two, just can form a multilevel iudge matrix;

(4) the weight coefficient method of index under single criterion condition is calculated;

(5) calculate judgment matrix Maximum characteristic root and proper vector, carry out the consistency check of two-level index;

As CR<0.10, namely think that judgment matrix has satisfied consistance; If do not meet consistance, then re-construct judgment matrix before must returning.

(6) calculate the final weight of output, obtain the credit scoring of owner of cargo member k to vehicle member C

W _irepresent solution layer i-th (i=1,2 ..., 12) individual evaluation index to the weight of criterion straton target, in like manner can obtain the weights W of rule layer sub-goal to general objective _j(j=1,2,3).

Each credit scoring model score that integrating step (2) obtains, can draw:

The credit scoring of vehicle member basic condition:

The credit scoring of vehicle member dynamic transaction situation:

The credit scoring of vehicle membership service situation:

Vehicle member credit comprehensive grading:

(7) the accumulated weights credit scoring of vehicle member C is calculated

After every single acknowledgement of consignment transaction completes, vehicle member C all can obtain owner of cargo member k (k=1,2,3 ...) and feedback credit appraisal S _kC, along with the carrying out of transaction, feedback credit appraisal number can get more and more, and other members inconvenient knowing the credit situation of vehicle member C, therefore, has the accumulated weights credit scoring of vehicle member C as the feedback credit scoring of vehicle member C, it is the mark CREDIT SCORE of vehicle member C; as the objective credit situation reference of owner of cargo member to vehicle C, not by the impact of people around;

(8) owner of cargo member A information extraction, excavates and had the direct circles of trust of concluding the business with vehicle member C

Owner of cargo member A is about the direct circles of trust L of vehicle member C _aC=m|m ∈ R, m=1,2 ..., M}, wherein, m is the owner of cargo member having direct trusting relationship with owner of cargo member A;

(9) calculate direct degree of belief and directly trust coefficient, obtaining one-level and derive credit with reference to scoring

In the direct circles of trust of owner of cargo member A, owner of cargo member A and they have direct trusting relationship, use P _amrepresent owner of cargo member A and the direct degree of belief of directly trusting owner of cargo member m, wherein 1≤P _am≤ 5, the method according to grade field is determined;

C _amrepresent the direct trust coefficient of owner of cargo member A and owner of cargo member m,

Then the one-level of owner of cargo member A derives credit with reference to scoring for:

${\tilde{S}}_{A1C}=\underset{m=1}{\overset{M}{\&Sigma;}}{C}_{Am}{S}_{mC}=\underset{m=1}{\overset{M}{\&Sigma;}}\frac{P_{Am}}{\underset{m=1}{\overset{M}{\&Sigma;}}{P}_{Am}}{S}_{mC}=\frac{\underset{m=1}{\overset{M}{\&Sigma;}}{P}_{Am}{S}_{mC}}{\underset{m=1}{\overset{M}{\&Sigma;}}{P}_{Am}}$

Wherein S _mCfor owner of cargo member m is to credit appraisal after the acknowledgement of consignment transaction of vehicle member C, be the true direct dealing evaluation of owner of cargo member m to vehicle member C, if owner of cargo member m did not occur directly to carry transaction with vehicle member C, then S _mC=0;

(10) expand derivative circles of trust, obtain the derivative trust of n level with reference to scoring

Owner of cargo member m in the direct circles of trust of owner of cargo member A (m=1,2 ..., M) the direct circles of trust one-level that becomes owner of cargo member A derive circles of trust, if the one-level of owner of cargo member A derives in circles of trust people b (b ∈ L _mC=b|b ∈ R, b=1,2 ..., B}) occurred to carry transaction with vehicle member C, then can obtain the secondary derivative trust of owner of cargo member A about vehicle member C with reference to scoring for:

${\tilde{S}}_{A2C}=\underset{b=1}{\overset{B}{\&Sigma;}}\underset{m=1}{\overset{M}{\&Sigma;}}{C}_{Am}{C}_{mb}{S}_{bC}$

Wherein S _bCfor owner of cargo member b is to credit appraisal after the acknowledgement of consignment transaction of vehicle member C, if owner of cargo member b did not occur directly to carry transaction with vehicle member C, then S _bC=0;

Utilize large data mining technology in like manner the derivative circles of trust of owner of cargo member A can be expanded, the n level derivative trust of owner of cargo member A about vehicle member C can be obtained with reference to scoring for:

${\tilde{S}}_{AnC}=\underset{b=1}{\overset{B}{\&Sigma;}}...\underset{m=1}{\overset{M}{\&Sigma;}}{C}_{Am}\mathrm{...}{C}_{mb}{S}_{bC}.$