CN107220833A - A kind of online credit methods and system towards electric business - Google Patents
A kind of online credit methods and system towards electric business Download PDFInfo
- Publication number
- CN107220833A CN107220833A CN201710373998.3A CN201710373998A CN107220833A CN 107220833 A CN107220833 A CN 107220833A CN 201710373998 A CN201710373998 A CN 201710373998A CN 107220833 A CN107220833 A CN 107220833A
- Authority
- CN
- China
- Prior art keywords
- loan
- sales
- mrow
- msub
- debtor
- 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
- G06Q30/00—Commerce
- G06Q30/018—Certifying business or products
-
- 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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
Abstract
The invention provides a kind of online credit methods and system towards electric business, comprise the following steps S1:Balance system receives the loan application from client, and loan application carries identity information, term of loan and and the expectation loan limit of debtor;S2:Identity information of the balance system in loan application obtains the corresponding debtor of the loan application store information in all shops and historical sales information under one's name from each electric business platform;S3:Balance system carries out returned money risk assessment according to store information and historical sales information to loan application, obtains evaluation result, and is determined whether according to evaluation result to make loans, in this way, such as no into step S4, exits;S4:According to evaluation result, the loan limit that can be made loans loan application is calculated;S5:Loan limit is fed back into client, loan operation is carried out after the confirmation instruction waiting for receiving client.The system and method have light assets, without mortgage, efficiency high, automatic business processing the characteristics of.
Description
Technical field
The present invention relates to credit financing technical field, more particularly to a kind of online credit methods and system towards electric business.
Background technology
In recent years, the fast development of Electronic Commerce in China achieves the achievement attracted people's attention, remains the rapid growth impetus,
Numerous medium-sized and small enterprises are exploited market channel, enterprise sales volume using electronic business mode one after another.China electronics business in 2014
Service enterprise's professionals be engaged in more than 2,500,000 people.The employment volume driven indirectly by ecommerce, more than 20,000,000
People.2,650,000 people are reached to E-business service enterprise professionals scale in 2015.E-commerce industry is increasingly becoming drawing
The consumption demand of dynamic China, promotion traditional industry upgrading, the important engine of Modern Service Industry.
For comparing traditional industries, because e-commerce platform has the longer account phase, to vast electric business industry of being engaged in
Medium-sized and small enterprises cause larger financial pressure, and fund turns into the primary problem that the enterprise development of puzzlement electric business is grown.For a long time,
Bank of China tradition character loan is using mortgaging, assuring, pledging isotype, for the electric business of light assets, solid due to lacking
It is difficult successfully to be provided a loan from bank to determine assets to pledge.Secondly, the credit evaluation of electric business enterprise and amount determine to be always puzzlement credit
One problem of industry.In addition, electric business debt-credit has the characteristics of frequency is high, capital turnover is fast, and bank loan is mostly that single is awarded
Letter, single are used, and majority is not recycled, and formality is complicated, examination & approval cycle upper and lower money speed is slow.
Analyzed based on more than, it can be seen that the need for traditional credit model of bank can not meet electric business operation.
In this case, many electric business turn to personalized lending, and on the one hand its legitimacy has considered, and risk is high, another
Aspect, its interest rate is too high.
The content of the invention
It is an object of the invention to provide a kind of online credit methods and system towards electric business, to solve existing credit
Technology can not meet the problem of needs, risk are high, efficiency is low.
To achieve the above object, the invention provides a kind of online credit methods towards electric business, comprise the following steps:
S1:The loan application from client is received, the loan application carries the identity information of debtor, debt-credit phase
Limit and expectation loan limit;
S2:Identity information in loan application obtains the corresponding debt-credit of the loan application from each electric business platform
The store information in all shops and historical sales information under name;
S3:Returned money risk assessment is carried out to the loan application according to the store information and historical sales information, obtained
Evaluation result, and determine whether to make loans according to the evaluation result, it is in this way, such as no into step S4, exit;
S4:According to the evaluation result, the loan limit that can be made loans the loan application is calculated;
S5:The loan limit is fed back into client, loan operation is carried out after the confirmation instruction waiting for receiving client.
It is preferred that in the step S3, carrying out returned money risk assessment and specifically including:
S31:Opening time T is determined according to formula:T=max { t1,t2,……,tN, opening in the store information
The shop time proceeds as follows:Work as T<Tth1, then the evaluation result that refusal is made loans is returned, otherwise, step S32 is performed, wherein, tn
For the opening time in n-th of shop, n=1,2 ..., N, N is the shop sum of debtor under one's name, T under all electric business platformsth1For
First preset time threshold;
S32:The sales growth rate in n shop is determined, including:
S321:Whether judge each shop in n shop is effective references object;
S322:Sales growth rate is used as according to the monthly growth rate of historical sales Information Statistics of all effective references object
S323:JudgeWhether set up, wherein,For default growth rate threshold value, in this way, return to refusal and make loans
Evaluation result, it is such as no, perform step S33;
S33:The sales volume sum for counting all effective references object obtains accumulated sales revenue:
If the accumulated sales revenue is less than default accumulated sales revenue threshold value, the evaluation result that refusal is made loans is returned;
Otherwise, step S34 is performed;
S34:The gross sales amount in predetermined amount of time is calculated as recent gross sales amount, if the recent gross sales amount is less than
Default recent sales volume threshold value, then return to the evaluation result that refusal is made loans, and otherwise, returns to the evaluation result for agreeing to make loans.
It is preferred that in the step S3, carrying out returned money risk assessment and specifically including:
A. the returned money factor is calculated according to the opening time obtained by the store information, sales growth rate and accumulated sales revenue
ε:
Wherein, T is opening time, Tth1For the first preset time threshold,For sales growth rate,For sales growth rate
Threshold value, V is accumulated sales revenue, VthFor accumulated sales revenue threshold value, S is the gross sales amount in predetermined amount of time, SthFor the scheduled time
Gross sales amount threshold value in section;
B. determined whether to make loans according to the value of the returned money factor ε:
If ε < εth, then the evaluation result that refusal is made loans is returned;
Otherwise, the evaluation result that can be made loans, ε are returnedthFor returned money factor threshold.
It is preferred that in the step S4, the method for calculating loan limit specifically includes following steps:
S41:Obtain the Withdrawal Amount P of debtor1And the available balance P of each electric business account of the debtor2;
S42:The order detail that debtor is handling order is obtained, and according to the transaction of all orders of order detail calculating
Volume total value P3;
S43:Predict sales volume P of the debtor within the term of loan4;
S44:Loan limit P is calculated according to equation below:
Wherein, ωkFor PkCorresponding weight, k=1,2,3,4, specifically:ω1、ω2、ω3、ω4Respectively P1、P2、P3With
P4Weight.
It is preferred that in the step S4, the method for calculating loan limit specifically includes following steps:
S41:Obtain the Withdrawal Amount P of debtor1And the available balance P of each electric business account of the debtor2;
S42:The order detail that debtor is handling order is obtained, and according to the transaction of all orders of order detail calculating
Volume total value P3;
S43:Predict sales volume P of the debtor within the term of loan4;
S44:Loan limit P is calculated according to equation below:
Wherein, φ is returned money factor ε regularization result, ωkFor PkCorresponding weight, k=1,2,3,4, specifically:
ω1、ω2、ω3、ω4Respectively P1、P2、P3And P4Weight.
It is preferred that calculating the turnover total value P3Method comprise the following steps:
S421:It is determined that the corresponding type of merchandize of the order for being presently processing order, the species commodity are directed to according to buyer
Return of goods rate calculate the return of goods rate of current order;
S422:Turnover total value P is calculated according to the return of goods rate of each order3:
Wherein, αiFor return of goods rate of the buyer for i-th of order, βjFor the return of goods rate of the affiliated merchandise classifications of commodity j, ScjFor
Commodity j unit price,For the commodity j of i-th of order number of transaction.
It is preferred that predicting the sales volume P4Method comprise the following steps:
S431:Obtain Marking Budget of the debtor within the term of loan;
S432:The historical sales information is handled by stages according to the term of loan, and existed according to the debtor
Historical sales information before loan determines repurchase rate;
S433:According to the result by stages of the historical sales information, enter for the historical sales information in each phase
Row is counted by stages, the sales volume and the sales volume of preceding s phases of the l same periods before respectively obtaining, wherein, l, s are respectively default just whole
Number;
S434:Form to be measured based on the Marking Budget, repurchase rate, the sales volume of the preceding l same periods and the sales volume of preceding s phases
Sample, the sample to be tested is inputted into the forecast model built in advance, obtains the pin being output as in the term of loan
Sell volume P4。
It is preferred that the repurchase rate successfully bought before being the term of loan twice and the above number of users with it is all
The ratio for the total number of users amount that success is bought.
It is preferred that the construction method of the forecast model is:
The historical sales information formation training set and test set are obtained, each sample includes the battalion in the term of loan
Sell budget and repurchase rate, the sales volume of the preceding l same periods, the sales volume of preceding s phases;
The sample of the training set is divided into input vector and output variable, wherein, the precision setting needed according to prediction
The number of training set;
Using the input vector as input, the output variable is output, trains BP neural network;
And the neutral net is tested using the test set, it regard the BP neural network after test passes as institute
State forecast model.
Present invention also offers a kind of online credit system towards electric business, including:Information exchange and control unit, are performed
The loan application from client is received, and obtains the identity information of debtor entrained in the loan application, debt-credit phase
Limit and expectation loan limit, and the loan limit calculated to client feedback;
Data acquisition unit, execution obtains the debtor according to the identity information of the debtor from each electric business platform
The store information in all shops and historical sales information under one's name;
Returned money risk assessment unit, performs and the loan application is carried out according to the store information and historical sales information
Returned money risk assessment, obtains evaluation result, and is determined whether according to evaluation result to make loans;
Loan limit computing unit, performs according to the evaluation result, calculates the loan that can be made loans the loan application
Amount.
The invention has the advantages that:
1) a kind of online balance system towards electric business and debt-credit pattern are provided, light assets, without mortgage, application is simple,
Speed of making loans money;And whole flow process on-line automaticization can be handled completely, without manual intervention;
2) returned money risk assessment is carried out only according to historic sales data (historical sales information), it is not necessary to submit other to believe
Breath, compared to traditional lending pattern of bank, enormously simplify debt-credit flow, while returned money risk also can be effectively controlled,
It ensure that the interests for the side of making loans;
3) it can be calculated from different dimensions and obtain loan limit, consider remittance risk control and the debtor of the side of making loans
Apply for the relation of amount of money.
Brief description of the drawings
Fig. 1 is the inventive method overall flow figure;
Fig. 2 is the returned money risk assessment flow chart of embodiment one;
Fig. 3 is the method flow diagram of the calculating loan limit of preferred embodiment;
Fig. 4 divides schematic diagram for the time limit in the processing by stages of preferred embodiment;
Fig. 5 is the BP neural network model schematic of preferred embodiment;
Fig. 6 is that present system constitutes structural representation.
Embodiment
Below with reference to the accompanying drawing of the present invention, clear, complete description is carried out to the technical scheme in the embodiment of the present invention
And discussion, it is clear that as described herein is only a part of example of the present invention, is not whole examples, based on the present invention
In embodiment, the every other implementation that those of ordinary skill in the art are obtained on the premise of creative work is not made
Example, belongs to protection scope of the present invention.
For the ease of the understanding to the embodiment of the present invention, make further by taking specific embodiment as an example below in conjunction with accompanying drawing
Illustrate, and each embodiment does not constitute the restriction to the embodiment of the present invention.
Embodiment one
Present embodiments provide a kind of online credit methods towards electric business, the online credit methods be particularly suitable for use in towards
Small amount, short term loan, amount is within 1,000,000, loan application of the term of loan within half a year.Credit is then carried out using this method
During application processing, as shown in figure 1, specifically including following steps:
S1:The loan application from client is received, the loan application carries the identity information of debtor, debt-credit phase
Limit and expectation loan limit;
S2:Identity information in loan application obtains the corresponding debt-credit of the loan application from each electric business platform
The store information in all shops and historical sales information under name;
S3:Returned money risk assessment is carried out to the loan application according to the store information and historical sales information, obtained
Evaluation result, and determined whether according to evaluation result to make loans, it is in this way, such as no into step S4, exit;
S4:According to the evaluation result, the loan limit that can be made loans the loan application is calculated;
S5:The loan limit is fed back into client, loan operation is carried out after the confirmation instruction waiting for receiving client.
During practical application:When the evaluation result of returned money risk assessment is made loans for refusal, then borrowed by client feedback
Borrow people's refusal lending information;And after balance system calculating obtains loan limit, also give loan limit by client feedback
User, debtor can adjust final loan limit according to the loan limit, and feed back to balance system, and be basis by debt-credit
Feedback system continues with and completes to make loans.
It is shown in Figure 2, in above-mentioned step S3, in the present embodiment, follow-up opening time, sales growth rate and sale
Volume carries out returned money risk assessment, specifically includes following steps:
S31:Opening time T is determined according to formula first:T=max { t1,t2,……,tN, then further according to store information
In opening time proceed as follows:Judge T<Tth1Whether set up, the evaluation result that refusal is made loans then is returned in this way, otherwise,
Step S32 is performed, wherein, tnFor the opening time in n-th of shop, n=1,2 ..., N, N is debtor under all electric business platforms
Shop sum under one's name, Tth1It is those skilled in the art's default time threshold according to actual needs for the first preset time threshold
Value;
S32:The sales growth rate in n shop is determined, this step is specifically included:
S321:Whether be effective references object, be specially, to i-th of shop, to judge if judging each shop in n shop
ti≤Tth2Whether set up, then i-th of shop is inactive reference object in this way, such as otherwise i-th of shop is effective references object,
S322 is performed again after judging to finish to n shop, wherein, T hereth2It is art technology for the second preset time threshold
Personnel's default time threshold according to actual needs;
S322:Sales growth rate θ is used as according to the monthly growth rate of historical sales Information Statistics of all effective references object:
The growth rate of every month, the moon growth rate θ of r-th month are calculated firstr:
Wherein, MrFor the sales volume sum of this month (i.e. the r months) all effective references object, Mr-1For all effective ginsengs last month
Examine the sales volume sum of object;
Then to all months growth rate θrAverage and can obtain monthly growth rate;
S323:JudgeWhether set up, wherein,For default sales growth rate threshold value, in this way, refusal is returned to
The evaluation result of lending, it is such as no, perform step S33;
S33:The sales volume sum for counting all effective references object obtains accumulated sales revenue:
If accumulated sales revenue is less than default accumulated sales revenue threshold value, the evaluation result that refusal is made loans is returned;
Otherwise, step S34 is performed;
S34:The gross sales amount in predetermined amount of time is calculated as recent gross sales amount, if the recent gross sales amount is less than
Default recent sales volume threshold value, then return to the evaluation result that refusal is made loans, and otherwise, returns to the evaluation result for agreeing to make loans.
The corresponding threshold value of above-mentioned each intermediate parameters (including the first preset time threshold, the second preset time threshold, sale
Growth rate threshold value, accumulated sales revenue threshold value, recent sales volume threshold value etc.) set previously according to application demand, in practical application mistake
Cheng Zhong, can be adjusted according to application demand.
Referring again to shown in Fig. 3, the method that loan limit is calculated in above-mentioned step S4 specifically includes following steps:
S41:Obtain the Withdrawal Amount P of debtor1And the available balance P of each electric business account of the debtor2;
Withdrawal Amount P1With available balance P2It can be provided by debtor.Opened in Third-party payment platform or electric business platform
During authority, directly it can also be obtained from Third-party payment platform or electric business platform, to ensure the authenticity and reliability of data.
S42:The order detail that debtor is handling order is obtained, and according to the transaction of all orders of order detail calculating
Volume total value P3;Wherein, order detail includes type of merchandize, the dealing money of order, Bidder Information and vendor information;
S43:Predict sales volume P of the debtor within the term of loan4;
S44:Utilize above-mentioned Withdrawal Amount P1, available balance P2, turnover total value P3And the sales volume in the term of loan
P4, calculating loan limit P according to equation below is:
Wherein, ωkFor PkCorresponding weight, k=1,2,3,4, specifically:ω1、ω2、ω3、ω4Respectively P1、P2、P3With
P4Weight, in the present embodiment, ω1=1, ω2=1, ω3=1, ω4=0.9.During practical application, ω1、ω2、ω3、ω4Take
Value can be adjusted according to application demand.
Wherein, turnover total value P is calculated in above-mentioned step S423Method further comprise the following steps:
S421:It is determined that the corresponding type of merchandize of the order for being presently processing order, according to buyer's moving back for the commodity
Goods rate calculates the return of goods rate of current order;
S422:Turnover total value P is calculated according to the return of goods rate of each order3:
Wherein, αiFor return of goods rate of the buyer for i-th of order, βjFor the return of goods rate of the affiliated merchandise classifications of commodity j, ScjFor
Commodity j unit price,For the commodity j of i-th of order number of transaction.
And in above-mentioned step S43, it is being predicted sales volume P4When, the one step process further comprises the steps:
S431:Obtain Marking Budget of the debtor within the term of loan;
S432:The historical sales information is handled by stages according to the term of loan, and existed according to the debtor
Historical transaction record (including historical transaction record in historical sales information) before loan determines repurchase rate;
S433:According to the result by stages of the historical sales information, enter for the historical sales information in each phase
Row is counted by stages, respectively obtains the sales volume and the sales volume of preceding 4 phase of the first two years same period;
S434:Formed based on above-mentioned Marking Budget, repurchase rate, the sales volume of the first two years same period and the sales volume of preceding 4 phase
Sample to be tested, sample to be tested is inputted into the forecast model built in advance, obtains being output as the sales volume in the term of loan
P4。
In the present embodiment, repurchase rate in step S432 successfully bought before being the term of loan twice and the above number of users
The ratio for the total number of users amount that amount is bought with all successes.
And the processing by stages in step S432 is mainly:According to the term of loan, all historical datas are carried out according to the time
Classification, is individually counted for the sales volume in each time zone.During one time zone is called a phase, the present embodiment
One phase referred to a term of loan, according to month, was carried out by stages with sliding window.If for example, the term of loan is 3 months
(being respectively in August, 2017, September And October), then be used as a phase using 3 months.It is as shown in Figure 4 that time limit divides schematic diagram.Then step
Preceding 2 annual sales amount obtained in S433 is expressed as Yk1、Yk2.Wherein, Yk1Represent in August, 2015, the sale of September And October
Volume, Yk2Represent in August, 2015, the sales volume of September And October.And the preceding 4 phase sales volume obtained in step S433 is expressed as
Xk-4, Xk-3, Xk-2, Xk-1.Wherein, Xk-1The 1st phase before the term of loan is represented, corresponding to three months terms of loan the 1st:2017
May in year, June and July;Xk-2The 2nd phase before the term of loan is represented, corresponding to three months terms of loan the 2nd:In April, 2017,5
The moon and June;Xk-3The 3rd phase before the term of loan is represented, corresponding to three months terms of loan the 3rd:In March, 2017, April and 5
Month;Xk-4The 4th phase before the term of loan is represented, corresponding to three months terms of loan the 4th:2 months 2017, March and April.
As described above, it can be seen that the sample to be tested in the present embodiment includes the Marking Budget M in the term of loanadk
And repurchase rate ηk, the sales volume Y of the first two years same periodk1、Yk2, the sales volume X of preceding 4 phasek-4, Xk-3, Xk-2, Xk-1.In the form of vectors
It is expressed as:{Madk, ηk, Yk1, Yk2, Xk-4, Xk-3, Xk-2, Xk-1}。
The forecast model built in advance in the present embodiment is obtained according to the historic sales data of historical sales information.This implementation
The forecast model used in example is obtained, the construction method of the forecast model is for BP neural network model by training:
(1) historical sales information formation training set and test set are obtained, each sample includes the battalion in the term of loan
Sell budget and repurchase rate, the sales volume of the first two years same period, the sales volume of preceding 4 phase;
(2) sample of training set is divided into input vector and output variable, be expressed as follows:Input vector formal mode is to be measured
Sample is identical, { M specific as followsadk, ηk, Xk-4, Xk-3, Xk-2, Xk-1, output variable is Xk.Using the above-mentioned term of loan as 2017 8
Illustrated exemplified by the moon, September And October, MadkFor the Marking Budget in 8~October, ηkFor the history repurchase before in August, 2017 part
Rate, Yk1, Yk2The sales volume in 8~October of respectively 2015 and 2016, Xk-4, Xk-3, Xk-2, Xk-1, XkThe respectively corresponding time limit
Interior sales volume.Wherein, the number of the precision setting training set needed according to prediction, usually 25~100;
(3) using above-mentioned input vector as input, output variable is output, trains BP neural network;
(4) and using above-mentioned test set BP neural network is tested, the BP neural network after test passes is made
For forecast model.
It should be noted that further to improve accuracy rate, in the case where data volume is enough, can also increase as follows
The sales volume of the 5th phase before input item, such as term of loan, the sales volume of the 6th phase before the term of loan, the before the term of loan the 3rd
At least one of in the same period sales volume in year etc..
On the contrary, the shop do not grown for opening time, because historic sales data is not enough, input can also be reduced accordingly
, the same period sales volume of the 2nd year before such as term of loan, now, input vector are { Madk, ηk, Yk1, Xk-4, Xk-3, Xk-2,
Xk-1}.Based on above-mentioned example, Yk2For 7~September sales volume of 2016.
It should be noted that when the sample in training set and test set increases or decreases input item, it is meant that make
Node quantity for input layer in the neutral net of forecast model is accordingly increased or reduced;Accordingly, when predicting P4,
It is also required to increase or decrease corresponding item of information in sample to be tested.
Then using the input vector in each above-mentioned training sample as input, using output variable as output, BP is trained
Neutral net, the obtained BP neural network trained as forecast model.
As shown in figure 5, the BP neural network include input layer, output layer and hidden layer, with 5 input nodes, 1 it is defeated
The action function gone out between node and 6 hidden nodes, each layer node is:Type function.
Each neuron realizes full connection between levels, and each node of each node of lower floor and upper strata is realized to be connected entirely
Connect, and it is connectionless between every layer of each node.
In addition, in above-mentioned step S433, when being counted by stages, the year of obtained sales volume is not limited to the first two years,
Can also be first 3 years, the same period sales volume of the several years such as first 4 years (year is represented with l), similarly, issue is also not necessarily limited to preceding 4 phase,
If can also be set to the sales volume of the dry spells (representing year with s) such as preceding 5 phase, preceding 6 phase as needed, those skilled in the art can basis
Setting l, s value is needed, wherein, l, s are respectively default positive integer.Correspondingly, when being subsequently predicted the structure of model, adopt
Model foundation is carried out with sales volume corresponding with l, s value.
Embodiment two
The present embodiment is in addition to herein below and embodiment one are otherwise varied, content of the remainder content with embodiment one
Identical, same section content is repeated no more, and the difference to the present embodiment elaborates below, specific as follows:
In the present embodiment, the method that the method and above preferred embodiment of returned money risk assessment are carried out in above-mentioned step S3
Difference, the process of the returned money risk assessment of the present embodiment specifically includes following two steps:
A. according to the opening time, sales growth rate and accumulated sales revenue that are obtained by above-mentioned store information calculate returned money because
Sub- ε:
Wherein, T is opening time, Tth1For the first preset time threshold,For sales growth rate,For sales growth rate
Threshold value, V is accumulated sales revenue, VthFor accumulated sales revenue threshold value, S is recent (predetermined amount of time) gross sales amount, SthTo be recent
(predetermined amount of time) gross sales amount threshold value;
B. determined whether to make loans according to the value of the returned money factor ε:
If ε < εth, then the evaluation result that refusal is made loans is returned;
Otherwise, the evaluation result that can be made loans is returned, wherein, εthFor returned money factor threshold.
Then in above-mentioned S44, above-mentioned Withdrawal Amount P is utilized1, available balance P2, turnover total value P3And in the term of loan
Sales volume P4, calculating loan limit P according to equation below is:
Wherein, φ is returned money factor ε regularization result.Specifically, in the present embodiment, according to equation below to returned money because
Sub- ε carries out regularization:
Wherein, [εmin,εmax] be ε value distributed area, εmaxFor returned money factor ε maximum, εminFor returned money factor ε
Minimum value, [εm′in,εm′ax] it is to the expectation value distributed area after ε regularizations.
Here ε value distributed area [εmin,εmax] can be obtained using statistical method, mass data is counted
Obtain.
And to the expectation value distributed area [ε after ε regularizationsm′in,εm′ax] preset, can be according to practical situations
It is adjusted.
In the embodiment of another deformation, when the calculating of loan limit is carried out in embodiment two, such as embodiment can be also used
Step S41~S44 shown in a kind of carries out the calculating of loan limit, that is, carrying out the method for returned money risk assessment in step S3
For by the way of the returned money factor, and when calculating loan limit, it is not necessary to the returned money factor is utilized, directly by formulaMeter
Calculation is obtained.Remainder is identical with the embodiment of embodiment one.
Those skilled in the art can select the method for any one above-mentioned returned money risk assessment as needed, and corresponding
Loan limit calculation.
As shown in fig. 6, corresponding to above-mentioned method, the present embodiment additionally provides a kind of online credit system towards electric business
620, the system 620 includes:
Information exchange and control unit 621, perform the operation for receiving the loan application from client, and obtain the loan
The identity information of entrained debtor, term of loan and expectation loan limit in application, and borrowed in the calculating of system 620
After amount of money degree, the loan limit that system 620 is calculated feeds back to the client that have sent loan application, so as to user feedback Shen
Please result;
Data acquisition unit 622, is performed according to the identity information of debtor from each electric business platform in electric business platform 630
Place obtains the debtor store information in all shops and historical sales information under one's name;
Returned money risk assessment unit 623, performs the loan to borrower according to above-mentioned store information and historical sales information
Money application carries out returned money risk assessment, obtains evaluation result, and is determined whether according to evaluation result to make loans;
Loan limit computing unit 624, performs according to above-mentioned evaluation result, calculates the loan that can be made loans loan application
Amount.
With reference to Fig. 6, when user (namely debtor) is borrowed or lent money using the system 620, user is inputted by client 610
Loan application, and the loan application is transmitted to system 620 by client, system 620 receives the debt-credit from client 610
After application, returned money risk assessment is carried out in the store information of each electric business platform according to debtor, and according to risk evaluation result
Loan limit is calculated, and feeds back to client 610.Wherein, client can be set to multiple as needed and (3 visitors only be shown in Fig. 6
Family end is respectively client 611~613), and loaning bill system 620 carries out data interaction with electric business platform 630, and electric business platform 630 is wrapped
Include m electric business platform, respectively 1~m of electric business platform.
This method and system provide online debt-credit towards electric business, are borrowed by being embedded in the online of the present invention in electric business payment platform
Loan system, electric business can very easily propose loan application online.And for the side of making loans, can be according to trade company's (electric business)
Historic sales data is estimated to returned money risk, and the sales data prediction based on trade company shop in following a period of time and
Circulating fund of the trade company in e-commerce platform determines amount of making loans, on the one hand directly by electric business platform and payment platform pair
The examination & verification and monitoring of merchant identification information and no longer individually carry out identity examination & verification, it is often more important that, can quickly basis from electric business
The merchant information rapid evaluation returned money risk that platform is obtained, calculating loan limit and can transfer loan, and whole debt-credit is treated
Cheng Jun does not need manual intervention, substantially reduces the time of making loans, and saves manpower examination & verification assessed cost.
The foregoing is only a specific embodiment of the invention, but protection scope of the present invention is not limited thereto, any
Those skilled in the art the invention discloses technical scope in, to the present invention deformation or replacement done, should all cover
Within protection scope of the present invention.Therefore, protection scope of the present invention should be defined by described scope of the claims.
Claims (10)
1. a kind of online credit methods towards electric business, it is characterised in that comprise the following steps:
S1:Receive the loan application from client, the loan application carry the identity information of debtor, the term of loan and
Expect loan limit;
S2:Identity information in loan application obtains the corresponding debt-credit name of the loan application from each electric business platform
Under all shops store information and historical sales information;
S3:Returned money risk assessment is carried out to the loan application according to the store information and historical sales information, evaluated
As a result, and according to the evaluation result determine whether to make loans, it is in this way, such as no into step S4, exit;
S4:According to the evaluation result, the loan limit that can be made loans the loan application is calculated;
S5:The loan limit is fed back into client, loan operation is carried out after the confirmation instruction waiting for receiving client.
2. the online credit methods according to claim 1 towards electric business, it is characterised in that in the step S3, are carried out
Returned money risk assessment is specifically included:
S31:Opening time T is determined according to formula:T=max { t1,t2,......,tN, running a shop in the store information
Time proceeds as follows:Work as T<Tth1, then the evaluation result that refusal is made loans is returned, otherwise, step S32 is performed, wherein, tnFor
The opening time in n-th of shop, n=1,2 ..., N, N is the shop sum of debtor under one's name, T under all electric business platformsth1For
One preset time threshold;
S32:The sales growth rate in n shop is determined, including:
S321:Whether judge each shop in n shop is effective references object;
S322:Sales growth rate is used as according to the monthly growth rate of historical sales Information Statistics of all effective references object
S323:JudgeWhether set up, wherein,For default growth rate threshold value, in this way, commenting for refusal lending is returned to
Valency result, it is such as no, perform step S33;
S33:The sales volume sum for counting all effective references object obtains accumulated sales revenue:
If the accumulated sales revenue is less than default accumulated sales revenue threshold value, the evaluation result that refusal is made loans is returned;
Otherwise, step S34 is performed;
S34:The gross sales amount in predetermined amount of time is calculated as recent gross sales amount, is preset if the recent gross sales amount is less than
Recent sales volume threshold value, then return to the evaluation result that refusal is made loans, otherwise, return and agree to the evaluation result made loans.
3. the online credit methods according to claim 1 towards electric business, it is characterised in that in the step S3, are carried out
Returned money risk assessment is specifically included:
A. returned money factor ε is calculated according to the opening time obtained by the store information, sales growth rate and accumulated sales revenue:
<mrow>
<mi>&epsiv;</mi>
<mo>=</mo>
<mfrac>
<mi>T</mi>
<msub>
<mi>T</mi>
<mrow>
<mi>t</mi>
<mi>h</mi>
<mn>1</mn>
</mrow>
</msub>
</mfrac>
<mo>&times;</mo>
<mfrac>
<mover>
<mi>&theta;</mi>
<mo>&OverBar;</mo>
</mover>
<msub>
<mover>
<mi>&theta;</mi>
<mo>&OverBar;</mo>
</mover>
<mrow>
<mi>t</mi>
<mi>h</mi>
</mrow>
</msub>
</mfrac>
<mo>&times;</mo>
<mfrac>
<mi>V</mi>
<msub>
<mi>V</mi>
<mrow>
<mi>t</mi>
<mi>h</mi>
</mrow>
</msub>
</mfrac>
<mo>&times;</mo>
<mfrac>
<mi>S</mi>
<msub>
<mi>S</mi>
<mrow>
<mi>t</mi>
<mi>h</mi>
</mrow>
</msub>
</mfrac>
<mo>,</mo>
</mrow>
Wherein, T is opening time, Tth1For the first preset time threshold,For sales growth rate,For sales growth rate threshold value, V
For accumulated sales revenue, VthFor accumulated sales revenue threshold value, S is the gross sales amount in predetermined amount of time, SthFor in predetermined amount of time
Gross sales amount threshold value;
B. determined whether to make loans according to the value of the returned money factor ε:
If ε < εth, then the evaluation result that refusal is made loans is returned;
Otherwise, the evaluation result that can be made loans, ε are returnedthFor returned money factor threshold.
4. the online credit methods according to claim 2 towards electric business, it is characterised in that in the step S4, are calculated
The method of loan limit specifically includes following steps:
S41:Obtain the Withdrawal Amount P of debtor1And the available balance P of each electric business account of the debtor2;
S42:The order detail that debtor is handling order is obtained, and the turnover for calculating all orders according to order detail is total
Volume P3;
S43:Predict sales volume P of the debtor within the term of loan4;
S44:Loan limit P is calculated according to equation below:
<mrow>
<mi>P</mi>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>k</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mn>4</mn>
</munderover>
<msub>
<mi>&omega;</mi>
<mi>k</mi>
</msub>
<mo>&times;</mo>
<msub>
<mi>P</mi>
<mi>k</mi>
</msub>
<mo>,</mo>
</mrow>
Wherein, ωkFor PkCorresponding weight, k=1,2,3,4, specifically:ω1、ω2、ω3、ω4Respectively P1、P2、P3And P4's
Weight.
5. the online credit methods according to claim 3 towards electric business, it is characterised in that in the step S4, are calculated
The method of loan limit specifically includes following steps:
S41:Obtain the Withdrawal Amount P of debtor1And the available balance P of each electric business account of the debtor2;
S42:The order detail that debtor is handling order is obtained, and the turnover for calculating all orders according to order detail is total
Volume P3;
S43:Predict sales volume P of the debtor within the term of loan4;
S44:Loan limit P is calculated according to equation below:
<mrow>
<mi>P</mi>
<mo>=</mo>
<mi>&phi;</mi>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>k</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mn>4</mn>
</munderover>
<msub>
<mi>&omega;</mi>
<mi>k</mi>
</msub>
<mo>&times;</mo>
<msub>
<mi>P</mi>
<mi>k</mi>
</msub>
<mo>,</mo>
</mrow>
Wherein, φ is returned money factor ε regularization result, ωkFor PkCorresponding weight, k=1,2,3,4, specifically:ω1、ω2、
ω3、ω4Respectively P1、P2、P3And P4Weight.
6. the online credit methods towards electric business according to claim 4 or 5, it is characterised in that calculate the turnover
Total value P3Method comprise the following steps:
S421:It is determined that the corresponding type of merchandize of the order for being presently processing order, according to buyer's moving back for the species commodity
Goods rate calculates the return of goods rate of current order;
S422:Turnover total value P is calculated according to the return of goods rate of each order3:
<mrow>
<msub>
<mi>P</mi>
<mn>3</mn>
</msub>
<mo>=</mo>
<munder>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
<mo>,</mo>
<mi>j</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
</munder>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>-</mo>
<msub>
<mi>&alpha;</mi>
<mi>i</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>&times;</mo>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>-</mo>
<msub>
<mi>&beta;</mi>
<mi>j</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>&times;</mo>
<msub>
<mi>Sc</mi>
<mi>j</mi>
</msub>
<mo>&times;</mo>
<msubsup>
<mi>L</mi>
<mi>i</mi>
<mi>j</mi>
</msubsup>
<mo>,</mo>
</mrow>
Wherein, αiFor return of goods rate of the buyer for i-th of order, βjFor the return of goods rate of the affiliated merchandise classifications of commodity j, ScjFor commodity
J unit price,For the commodity j of i-th of order number of transaction.
7. the online credit methods towards electric business according to claim 4 or 5, it is characterised in that the prediction sales volume P4
Method comprise the following steps:
S431:Obtain Marking Budget of the debtor within the term of loan;
S432:The historical sales information is handled by stages according to the term of loan, and according to the debtor in loan
Historical sales information before determines repurchase rate;
S433:According to the result by stages of the historical sales information, divided for the historical sales information in each phase
Phase counts, the sales volume and the sales volume of preceding s phases of the l same periods before respectively obtaining, wherein, l, s are respectively default positive integer;
S434:Test sample is treated based on the formation of the Marking Budget, repurchase rate, the sales volume of the preceding l same periods and the sales volume of preceding s phases
This, the sample to be tested is inputted into the forecast model built in advance, the sale being output as in the term of loan is obtained
Volume P4。
8. the online credit methods according to claim 7 towards electric business, it is characterised in that the repurchase rate is borrowed to be described
Borrow the time limit before successfully buy twice and the above number of users with it is all success buy total number of users amounts ratio.
9. the online credit methods according to claim 7 towards electric business, it is characterised in that the structure of the forecast model
Method is:
Obtaining each sample in the historical sales information formation training set and test set, the training set and test set includes institute
State the Marking Budget and repurchase rate in the term of loan, the sales volume of the preceding l same periods, the sales volume of preceding s phases;
The sample of the training set is divided into input vector and output variable, wherein, trained according to the precision setting that prediction needs
The number of collection;
Using the input vector as input, the output variable is output, trains BP neural network;
And the neutral net is tested using the test set, using the BP neural network after test passes as described pre-
Survey model.
10. a kind of online credit system towards electric business, it is characterised in that including:
Information exchange and control unit, perform and receive the loan application from client, and obtain and taken in the loan application
Identity information, term of loan and the expectation loan limit of the debtor of band, and the loan limit calculated to client feedback;
Data acquisition unit, execution obtains the debtor under one's name according to the identity information of the debtor from each electric business platform
The store information and historical sales information in all shops;
Returned money risk assessment unit, performs and carries out returned money to the loan application according to the store information and historical sales information
Risk assessment, obtains evaluation result, and is determined whether according to evaluation result to make loans;
Loan limit computing unit, performs according to the evaluation result, calculates the loan limit that can be made loans the loan application.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710373998.3A CN107220833A (en) | 2017-05-24 | 2017-05-24 | A kind of online credit methods and system towards electric business |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710373998.3A CN107220833A (en) | 2017-05-24 | 2017-05-24 | A kind of online credit methods and system towards electric business |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107220833A true CN107220833A (en) | 2017-09-29 |
Family
ID=59944524
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710373998.3A Pending CN107220833A (en) | 2017-05-24 | 2017-05-24 | A kind of online credit methods and system towards electric business |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107220833A (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107833130A (en) * | 2017-10-25 | 2018-03-23 | 中国银行股份有限公司 | A kind of credit card amount lends method and system |
CN108416666A (en) * | 2018-02-28 | 2018-08-17 | 四川新网银行股份有限公司 | A kind of consumptive credit solution based on open platform technologies |
CN108765137A (en) * | 2018-05-30 | 2018-11-06 | 中智诚征信有限公司 | A kind of credit demand prediction technique and system, storage medium |
CN109727113A (en) * | 2018-02-12 | 2019-05-07 | 平安普惠企业管理有限公司 | Adding management method, device, equipment and the computer storage medium of fund pool |
CN109886799A (en) * | 2019-01-22 | 2019-06-14 | 上海上湖信息技术有限公司 | A kind of real-time method and system predicted and show loaning bill success rate |
CN110189218A (en) * | 2019-04-25 | 2019-08-30 | 北京互金新融科技有限公司 | The management method and device of loan limit |
CN110728458A (en) * | 2019-10-18 | 2020-01-24 | 支付宝(杭州)信息技术有限公司 | Target object risk monitoring method and device and electronic equipment |
CN112232949A (en) * | 2020-12-07 | 2021-01-15 | 国网电子商务有限公司 | Block chain-based loan risk prediction method and device |
CN112508694A (en) * | 2021-02-05 | 2021-03-16 | 北京淇瑀信息科技有限公司 | Resource limit application processing method and device and electronic equipment |
CN116883084A (en) * | 2023-09-08 | 2023-10-13 | 青岛巨商汇网络科技有限公司 | Sales evaluation-based data intelligent monitoring and early warning method and system |
-
2017
- 2017-05-24 CN CN201710373998.3A patent/CN107220833A/en active Pending
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107833130A (en) * | 2017-10-25 | 2018-03-23 | 中国银行股份有限公司 | A kind of credit card amount lends method and system |
CN109727113B (en) * | 2018-02-12 | 2024-02-13 | 重庆柯利弗文化传媒有限公司 | Method, device, equipment and computer storage medium for recharging management of fund pool |
CN109727113A (en) * | 2018-02-12 | 2019-05-07 | 平安普惠企业管理有限公司 | Adding management method, device, equipment and the computer storage medium of fund pool |
CN108416666A (en) * | 2018-02-28 | 2018-08-17 | 四川新网银行股份有限公司 | A kind of consumptive credit solution based on open platform technologies |
CN108765137A (en) * | 2018-05-30 | 2018-11-06 | 中智诚征信有限公司 | A kind of credit demand prediction technique and system, storage medium |
CN109886799A (en) * | 2019-01-22 | 2019-06-14 | 上海上湖信息技术有限公司 | A kind of real-time method and system predicted and show loaning bill success rate |
CN110189218A (en) * | 2019-04-25 | 2019-08-30 | 北京互金新融科技有限公司 | The management method and device of loan limit |
CN110728458A (en) * | 2019-10-18 | 2020-01-24 | 支付宝(杭州)信息技术有限公司 | Target object risk monitoring method and device and electronic equipment |
CN110728458B (en) * | 2019-10-18 | 2022-07-29 | 支付宝(杭州)信息技术有限公司 | Target object risk monitoring method and device and electronic equipment |
CN112232949B (en) * | 2020-12-07 | 2021-03-09 | 国网电子商务有限公司 | Block chain-based loan risk prediction method and device |
CN112232949A (en) * | 2020-12-07 | 2021-01-15 | 国网电子商务有限公司 | Block chain-based loan risk prediction method and device |
CN112508694A (en) * | 2021-02-05 | 2021-03-16 | 北京淇瑀信息科技有限公司 | Resource limit application processing method and device and electronic equipment |
CN112508694B (en) * | 2021-02-05 | 2021-07-02 | 北京淇瑀信息科技有限公司 | Method and device for processing resource limit application by server and electronic equipment |
CN116883084A (en) * | 2023-09-08 | 2023-10-13 | 青岛巨商汇网络科技有限公司 | Sales evaluation-based data intelligent monitoring and early warning method and system |
CN116883084B (en) * | 2023-09-08 | 2023-11-28 | 青岛巨商汇网络科技有限公司 | Sales evaluation-based data intelligent monitoring and early warning method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107220833A (en) | A kind of online credit methods and system towards electric business | |
Rocheteau et al. | Corporate finance and monetary policy | |
JP2002163449A (en) | Method and system for financing and evaluating method for technology-secured credit | |
Rezaei et al. | Ranking the banks through performance evaluation by integrating fuzzy AHP and TOPSIS methods: A study of Iranian private banks | |
Guchhait et al. | Inventory policy of a deteriorating item with variable demand under trade credit period | |
US8027894B2 (en) | Modeling responsible consumer debt consolidation behavior | |
Markose et al. | Network Effects On Cash‐Card Substitution In Transactions And Low Interest Rate Regimes | |
Afaha | Electronic payment systems (E-payments) and Nigeria economic growth | |
Shirov et al. | RIM interindustry macroeconomic model: Development of instruments under current economic conditions | |
CN1971610A (en) | System and method for evaluating bank lending risks | |
Cachanosky | Austrian economics, market process, and the EVA® framework | |
CN109886800A (en) | Electronic device, nonstandard creditor's assets estimation method and computer readable storage medium | |
Kang et al. | Macroeconomic dynamics in korea during and after the global financial crisis: a bayesian DSGE approach | |
Karambut et al. | The intention in online submission of micro credit | |
CN115660803A (en) | Supply chain financial risk management method under internet background | |
Song et al. | Smart supply chain finance | |
Chen et al. | House price, mortgage premium, and business fluctuations | |
Wang et al. | Bank Customer Default Risk Based on Multimedia in the Background of Internet Digital Finance | |
Lotfi et al. | Multi-component efficiency with shared resources in commercial banks | |
RU190382U1 (en) | Automated device for evaluating the effectiveness of the conversion of industrial areas | |
Osipenko | Investigation into methods of predicting income from credit card holders using panel data | |
Walwyn et al. | How to manage risk better | |
Ma | Estimating a dynamic discrete choice model with partial observability for household mortgage default and prepayment behaviors | |
CN101359387A (en) | Mutually type house loan method and system | |
Jia et al. | The Research of Customer Lifetime Value Related to Risk Factors in the Internet Business: Exampled by Online Car-hailing Industry |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170929 |
|
RJ01 | Rejection of invention patent application after publication |