CN106570631A - Method and system of facing P2P platform operation risk estimation - Google Patents
Method and system of facing P2P platform operation risk estimation Download PDFInfo
- Publication number
- CN106570631A CN106570631A CN201610960560.0A CN201610960560A CN106570631A CN 106570631 A CN106570631 A CN 106570631A CN 201610960560 A CN201610960560 A CN 201610960560A CN 106570631 A CN106570631 A CN 106570631A
- Authority
- CN
- China
- Prior art keywords
- platform
- alpha
- data
- network loan
- time window
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Educational Administration (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The present invention discloses a method and system of facing P2P platform operation risk estimation. The method comprises the steps of 1) obtaining the data of a P2P network lending platform; 2) pre-processing the data, and cleaning the irrelevant platform data; 3) selecting the appropriate time windows, and dividing the operation cycle of the P2P network lending platform in a fine grain manner; 4) for the P2P network lending platform, providing some discretized data to group and quantify, for example, the age distribution of the borrowers on a grouping platform; 5) extracting the characteristics of the lager information gain via an information gain calculation method; 6) establishing an equation set between the characteristic coefficients and the corresponding weight coefficients, and solving to obtain the weight coefficient of each corresponding attributes; 7) solving the operation risk indexes of the lending platform in each time window, and observing the change situation of the risk indexes of the platform with a period of time. The method and the system of the present invention can prompt the platform operators effectively, adjust the management measures, and have the wide technological and market application values.
Description
Technical field
The present invention relates to a kind of method and system towards P2P platform operation risk assessment, belongs to information security technology neck
Domain.
Background technology
With developing rapidly for Internet technology, especially e-commerce field there occurs huge change to financial circles.Closely
In a little years, as a kind of new debt-credit mode occurs, i.e. P2P network loans change traditional debt-credit flow process so that borrow money and borrow
Money is more easy and convenient.During network loan, data and fund, contract, formality etc. are borrowed all by real-time performance
Money people arranges loan payment standard, and then investor is provided a loan by competitive bids behavior to borrower.It is checked in P2P platforms
Afterwards, borrower can issue some detailed information, for example educate, working condition, mode of satisfaction, interest rate, and the one of fund
A little specific purposes, investor can decide whether investment according to these information.But, so also can there are problems that, example
Such as the prestige problem of borrower, problem, the supervision of network loan platform and information asymmetry equivalent risk problem are cleared.Due in
The disappearance of the special circumstances of state, such as system and the shortage of supervision, P2P network loan platforms have certain operation wind
Danger.The operations risks of P2P network loan platforms are primarily referred to as the quality of P2P platform management states, and breaking occurs in this platform
The risk of the situation of product.
It is traditional for the analysis of P2P platforms is primarily directed to the analysis of the credit risk of borrower, this is to a certain degree
On can be to evade certain loss；Next to that the judge to P2P platforms, i.e., judge that some platform is by some data
Or bad (being primarily referred to as the situation for whether occurring running away), these analyses are mainly assessed the credit risk of borrower and are led to
These platforms are divided into several classes by the method for crossing classification.But, the development of anything has a change procedure, traditional analysis
Have ignored the situation of change of P2P network loan platform operations risks.The change of risk index can reflect the fortune of a P2P platform
Battalion's situation.And the present invention can be solved the problems, such as well above.
The content of the invention
Present invention aim at being directed to above-mentioned the deficiencies in the prior art, there is provided one kind is commented towards P2P platform operation risks
The method and system estimated, the situation that the method passes through analysis P2P network loan platform operations risks, provides P2P in a period of time
The assessment of platform operation risk situation and operations risks are assessed, and give administration person's platform operation shape of investor and platform
The information of condition.
The present invention solves its technical problem and is adopted the technical scheme that：It is a kind of towards P2P platform operation risk assessment
Method, the method is comprised the following steps：
Step 1：Data acquisition, by web crawlers, or P2P network loan platforms provide etc. mode obtain P2P networks
The operation data of loan platform；
Step 2：Data prediction, washes some and P2P network loan platform irrelevant informations, or the mistake collected
False information；
Step 3：Time window is divided.According to P2P platform risk assessment demand dynamic setting time window function, platform is carried
For data carry out dynamic cutting by window function.It is for example n fine granularity time window by the data cutting in certain platform T time section
Data { t1, t2..., tn}
Step 4：Data after cleaning are preserved, for some discrete data can be adopted in each time window t
The mode of group quantization is taken, more detailed P2P network loan platforms information, the such as educational situation of borrower is obtained with this,
Age situation, or the distribution situation of affiliated area, by way of discrete packets are classified, that is, count each ages, teach
Educate the number distribution situation of level；
Step 5：Feature Selection：In training set, for multiple features of P2P network loan platforms, increased using the information of calculating
The mode of benefit chooses maximally related feature；If set S represents all of transaction record of P2P network loan platforms, there are s bars to record
{S1, S2..., Ss}；Set C={ C1, C2For P2P network loan platforms classification, C1Represent the good platform class of operation situation
Not, C2The P2P network loan platforms that expression runs away, siExpression classification is CiSample number, then have comentropy to calculate public
Formula：
Wherein Pi=si/s.
Assume that characteristic attribute A includes k independent characteristic attribute { a1, a2, a3..., ak}；sjRepresent in A attribute conditions
Under, it is characterized as ajNumber of samples；PijFor SjBelong to classification CiProbability,Then there is comentropy for attribute A
Computing formula：
Wherein
Information gain for attribute A is：
Gain (A)=I (s1j, s2j)-E(A)
Thus, calculating the information gain of each feature, we choose the corresponding feature of larger information gain, as
Analysis object；
Step 6：To each time window t, there is feature { x1x2..., xnN feature is had, if the risk index of platform is
R, { α1, α2..., αnFor the weight coefficient of platform each attribute, then equation can be set up：
R=α1x1+α1x2+…+αnxn
We assume that the peak of platform risk is max (R)=1, ε to be used for weighing the maximum value-at-risk of deviation, then R can
To be expressed as：R=1- ε, ε ∈ (0,1), and the value for finding optimal ε is traveled through to ε step-lengths step=h；
Hypothesis has t time window, and setting up polynary once linear equation group is：
The eigenvalue of the attribute in t-th time window is represented, one group of { α thus can be obtained1,
α2..., αn}.
For different ε, corresponding different weight coefficient solution can be obtained, be provided with ε1, ε2..., εm, it is corresponding each
Individual ε, it can be deduced that one group corresponding to go for coefficient solution in you, i.e.,：
So, the weight coefficient of the platform is：
Step 7：According to the weight coefficient that above-mentioned steps 6 are tried to achieve, the value-at-risk in each time window can be calculated, at certain
In individual time window t, the operations risks index of the P2P platforms is：
Wherein t refers to t-th time window, by calculating, can obtain the operations risks in a period of time window, and risk
Variation tendency.
Further, data of the present invention refer to the operation data of P2P network loan platforms, mainly including cash flow,
Borrower and the essential information of investor that platform is included；
Further, time window is divided and mainly divides the suitable time period for analytical cycle in step 3 of the present invention,
For example with one month, the data in a week are used as object of study；
Further, quantitative packet, mainly by some discrete packets, such as the age, is received an education in the step 3
The distribution situation of degree；
Further, step 4 of the present invention selected characteristic by way of information gain calculating, investigates feature to entirety
Contribution, mainly finance including platform, the granting of loan and the relevant information of borrower.
The present invention also provides a kind of system towards the assessment of P2P network loan platforms operations risks, and the system includes data
Acquisition module, data preprocessing module, characteristic extracting module and model building module.
Data acquisition module is the related operation data for obtaining P2P network loan platforms；
Data preprocessing module is the P2P network loan platform data for processing acquired, cleans incoherent data,
While group quantization discrete data；
Characteristic extracting module is the maximally related feature for extracting with P2P network loan platforms, main every by calculating
The information gain of individual feature is determining；
Model building module is the related weight coefficient for calculating P2P network loan platforms, every such that it is able to calculate
The operations risks value of network loan platform in the individual time.
Beneficial effect：
1st, the present invention is not only able to provide the operation state of corresponding P2P network loan platforms, moreover it is possible to be given at a timing
The situation of change of interior operations risks, investor can pass through the situation of change of observation risk, thus it is speculated that the wind for running away occurs in platform
Danger, so as to decide whether investment；Platform management person can timely adjust management strategy so that platform can normally run.
2nd, the method for the present invention can be good at the situation of change of the operations risks for assessing some loan platform, while energy
Enough reflect development trend of the platform in prolonged stage inner platform, provide reference to investor, it is also possible to platform
Network operator some effective promptings, strengthen the supervision to P2P platforms, reduce the operations risks of P2P platforms.
3rd, using the method for the present invention and system, it can be estimated that the situation of change of the operations risks of some loan platform,
Simultaneously development and operation trend of the network platform in prolonged stage inner platform can be reflected, to investor ginseng is provided
Examine, it is also possible to give the network operator of platform some effective promptings, adjust control measures, with extensive technology and market valency is applied
Value.
Description of the drawings
Fig. 1 is method of the present invention flow chart.
Fig. 2 is the system structure diagram of the present invention.
Specific embodiment
With reference to Figure of description the invention is described in further detail by specific embodiment.Should manage
Solution, the example that is embodied as described herein is merely illustrative and explains the present invention, is not intended to limit the present invention.
As shown in figure 1, the invention provides a kind of method and system towards P2P platform operation risk assessment, the method
Comprise the steps：
(1) data acquisition, by web crawlers, or P2P network loan platforms provide etc. mode obtain P2P network loans
The operation data of platform；
(2) data prediction, washes some and P2P network loan platform irrelevant informations, or the mistake collected
Information；
(3) time window is divided, and being chosen by fine-grained time window acquired in us can reflect P2P network loans
The change of traffic-operating period.For example, there are the data of n month length, time window t can be divided1, t2..., tn, n time
Window, same we can also divide time window with the shorter time；
(4) data after cleaning are preserved, for some discrete data can be taken point in each time window t
The mode that group quantifies, with this more detailed P2P network loan platforms information, the such as educational situation of borrower, age are obtained
Situation, or the distribution situation of affiliated area, by way of discrete packets are classified, that is, count each ages, educate layer
Secondary number distribution situation；
(5) Feature Selection：In training set, for multiple features of P2P network loan platforms, using calculating information gain
Mode chooses maximally related feature；If set S represents all of transaction record of P2P network loan platforms, there are s bars to record；Collection
Close C={ C1, C2For P2P network loan platforms classification, C1Represent the good platform classification of operation situation, C2Expression is run
The P2P network loan platforms on road, siExpression classification is CiSample number, then have comentropy computing formula：
Wherein Pi=si/s.
Assume that characteristic attribute A includes k independent characteristic attribute, a1, a2, a3..., ak；sjRepresent under A attribute conditions,
It is characterized as ajNumber of samples；PijFor SjBelong to classification CiProbability,Then there is comentropy to calculate for attribute A
Formula：
Wherein
Information gain for attribute A is：
Gain (A)=I (s1j, s2j)-E(A)
Thus, calculating the information gain of each feature, we choose the corresponding feature of larger information gain, as
Analysis object；
(6) to each time window t, there is feature { x1, x2..., xnN feature is had, if the risk index of platform is R,
{α1, α2..., αnFor the weight coefficient of platform each attribute, then equation can be set up：
R=α1x1+α1x2+…+αnxn
We assume that the peak of platform risk is max (R)=1, ε to be used for weighing the maximum value-at-risk of deviation, then R can
To be expressed as：R=1- ε, ε ∈ (0,1), and the value for finding optimal ε is traveled through to ε step-lengths step=h.
Hypothesis has t time window, and setting up polynary once linear equation group is：
The eigenvalue of the attribute in t-th time window is represented, one group of { α thus can be obtained1,
α2..., αn}.
For different ε, corresponding different weight coefficient solution can be obtained, be provided with ε1, ε2..., εm, it is corresponding each
Individual ε, it can be deduced that one group corresponding to go for coefficient solution in you, i.e.,：
So, the weight coefficient of the platform is：
(7) weight coefficient tried to achieve according to above-mentioned steps (6), can calculate the value-at-risk in each time window, at certain
In individual time window t, the operations risks index of the P2P platforms is：
T refers to t-th time window, by calculating, can obtain the operations risks in a period of time window, and the change of risk
Change trend.
Such as Fig. 2, the invention provides one kind is towards P2P network loan platform operations risks assessment systems, the system includes
Data acquisition module, data preprocessing module, characteristic extracting module and model building module.
Data acquisition module, for obtaining the related operation data of P2P network loan platforms；
Data preprocessing module, for processing acquired P2P network loan platform data, cleans incoherent data,
While group quantization discrete data；
Characteristic extracting module, it is main by calculating each for extracting the maximally related feature with P2P network loan platforms
The information gain of feature is determining；
Model building module, for calculating the related weight coefficient of P2P network loan platforms, such that it is able to calculate each
The operations risks value of network loan platform in time.
It should be appreciated that the above-mentioned description for preferred embodiment is more detailed, therefore can not be considered to this
The restriction of invention patent protection scope, one of ordinary skill in the art is weighing under the enlightenment of the present invention without departing from the present invention
Under the protected ambit of profit requirement, replacement can also be made or deformed, be each fallen within protection scope of the present invention, this
It is bright scope is claimed to be defined by claims.
Claims (6)
1. one kind is towards P2P network loan platform operations risks appraisal procedures, it is characterised in that include：
Step 1：Data acquisition, obtains P2P network loans and puts down by way of web crawlers or P2P network loan platforms are provided
The operation data of platform；
Step 2：Data prediction, washes some and P2P network loan platform irrelevant informations, or the mistake letter collected
Breath；
Step 3：Time window is divided, being chosen by fine-grained time window for acquisition, reflects the change of P2P network loan traffic-operating periods
Change；
Step 4：Data after cleaning are preserved, for some discrete data take amount of packets in each time window t
The mode of change, with this P2P network loan platform information is obtained；
Step 5：Feature Selection：In training set, for multiple features of P2P network loan platforms, using calculating information gain
Mode chooses maximally related feature；If set S represents all of transaction record of P2P network loan platforms, there are s bars to record { S1,
S2,…,Ss}；Set C={ C1, C2For P2P network loan platforms classification, C1Represent the good platform classification of operation situation, C2
The P2P network loan platforms that expression runs away, siExpression classification is CiSample number, then have comentropy computing formula：
Wherein Pi=si/s；
Step 6：To each time window t, there is feature (x1, x2..., xnN feature is had, if the risk index of platform is R,
{α1, α2..., αnFor the weight coefficient of platform each attribute, then setting up equation is：
R=α1x1+α1x2+…+αnxn
Step 7：According to the weight coefficient that above-mentioned steps 6 are tried to achieve, the value-at-risk in each time window is calculated, in certain time window
In t, the operations risks index of the P2P platforms is：
Wherein t refers to t-th time window, by calculating, obtains the operations risks in a period of time window, and the change of risk becomes
Gesture.
2. one kind according to claim 1 is towards P2P network loan platform operations risks appraisal procedures, it is characterised in that
Time window described in step 3 is divided to be included：There are the data of n month length, divide time window t1, t2..., tn, n time
Window.
3. one kind according to claim 1 is towards P2P network loan platform operations risks appraisal procedures, it is characterised in that
P2P network loan platform information described in step 4 includes：The educational situation of borrower, age situation, or affiliated area
Distribution situation, by way of discrete packets are classified, that is, counts each ages, the number distribution situation of education levels.
4. one kind according to claim 1 is towards P2P network loan platform operations risks appraisal procedures, it is characterised in that
Step 5 includes：Assume that characteristic attribute A includes k independent characteristic attribute, α1, α2, α3..., αk；sjRepresent in A attribute conditions
Under, it is characterized as αjNumber of samples；PijFor SjBelong to classification CiProbability,Then there is comentropy meter for attribute A
Calculating formula is：
Wherein
Information gain for attribute A is：
Gain (A)=I (s1j, s2j)-E(A)
Calculate the information gain of each feature, choose the corresponding feature of larger information gain, as analysis object.
5. one kind according to claim 1 is towards P2P network loan platform operations risks appraisal procedures, it is characterised in that
Step 6 includes：The peak for assuming platform risk is that max (R)=1, ε is used for weighing the maximum value-at-risk of deviation, then R is represented
For:R=1- ε, ε ∈ (0,1), and the value for finding optimal ε is traveled through to ε step-lengths step=h；
Hypothesis has t time window, and setting up polynary once linear equation group is：
The eigenvalue of the attribute in t-th time window is represented, one group of { α thus can be obtained1, α2..., αn}.
For different ε, corresponding different weight coefficient solution is obtained, be provided with ε1, ε2..., εm, each ε is corresponded to, draw
One group corresponding to go for coefficient solution in you, i.e.,：
So, the weight coefficient of the platform is：
6. one kind is towards P2P network loan platform risk evaluating systems, it is characterised in that：The system includes data acquisition mould
Block, data preprocessing module, characteristic extracting module and model building module；
Data acquisition module is the operation data for obtaining P2P network loan platforms；
Data preprocessing module is the P2P network loan platform data for processing acquired, cleans incoherent data, while
Group quantization discrete data；
Characteristic extracting module is the maximally related feature for extracting with P2P network loan platforms, by calculating each feature
Information gain is determining；
Model building module is the related weight coefficient for calculating P2P network loan platforms, so as to calculate in each time
The operations risks value of network loan platform.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610960560.0A CN106570631B (en) | 2016-10-28 | 2016-10-28 | P2P platform-oriented operation risk assessment method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610960560.0A CN106570631B (en) | 2016-10-28 | 2016-10-28 | P2P platform-oriented operation risk assessment method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106570631A true CN106570631A (en) | 2017-04-19 |
| CN106570631B CN106570631B (en) | 2021-01-01 |
Family
ID=58535801
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610960560.0A Active CN106570631B (en) | 2016-10-28 | 2016-10-28 | P2P platform-oriented operation risk assessment method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106570631B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107423878A (en) * | 2017-05-31 | 2017-12-01 | 南京邮电大学 | A kind of method and system towards P2P platform operation risk assessment |
| CN107992978A (en) * | 2017-12-21 | 2018-05-04 | 连连银通电子支付有限公司 | It is a kind of to net the method for prewarning risk and relevant apparatus for borrowing platform |
| CN108199866A (en) * | 2017-12-14 | 2018-06-22 | 上海交通大学 | Social network system with strong secret protection |
| WO2020015140A1 (en) * | 2018-07-18 | 2020-01-23 | 平安科技（深圳）有限公司 | Passenger rating model generation method and apparatus, and computer device and storage medium |
| CN110866696A (en) * | 2019-11-15 | 2020-03-06 | 成都数联铭品科技有限公司 | Method and device for training shop falling risk assessment model |
| CN113344692A (en) * | 2021-04-24 | 2021-09-03 | 大连理工大学 | Method for establishing network loan credit risk assessment model with multi-information-source fusion |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060100957A1 (en) * | 2002-05-08 | 2006-05-11 | Accenture Global Services Gmbh | Electronic data processing system and method of using an electronic data processing system for automatically determining a risk indicator value |
| CN105069683A (en) * | 2015-07-24 | 2015-11-18 | 广州时韵信息科技有限公司 | Tax risk assessment system |
| CN105427171A (en) * | 2015-11-30 | 2016-03-23 | 北京口袋财富信息科技有限公司 | Data processing method of Internet lending platform rating |
| CN105844424A (en) * | 2016-05-30 | 2016-08-10 | 中国计量学院 | Product quality problem discovery and risk assessment method based on network comments |
-
2016
- 2016-10-28 CN CN201610960560.0A patent/CN106570631B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060100957A1 (en) * | 2002-05-08 | 2006-05-11 | Accenture Global Services Gmbh | Electronic data processing system and method of using an electronic data processing system for automatically determining a risk indicator value |
| CN105069683A (en) * | 2015-07-24 | 2015-11-18 | 广州时韵信息科技有限公司 | Tax risk assessment system |
| CN105427171A (en) * | 2015-11-30 | 2016-03-23 | 北京口袋财富信息科技有限公司 | Data processing method of Internet lending platform rating |
| CN105844424A (en) * | 2016-05-30 | 2016-08-10 | 中国计量学院 | Product quality problem discovery and risk assessment method based on network comments |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107423878A (en) * | 2017-05-31 | 2017-12-01 | 南京邮电大学 | A kind of method and system towards P2P platform operation risk assessment |
| CN108199866A (en) * | 2017-12-14 | 2018-06-22 | 上海交通大学 | Social network system with strong secret protection |
| CN108199866B (en) * | 2017-12-14 | 2020-06-12 | 上海交通大学 | Social network system with strong privacy protection |
| CN107992978A (en) * | 2017-12-21 | 2018-05-04 | 连连银通电子支付有限公司 | It is a kind of to net the method for prewarning risk and relevant apparatus for borrowing platform |
| WO2020015140A1 (en) * | 2018-07-18 | 2020-01-23 | 平安科技（深圳）有限公司 | Passenger rating model generation method and apparatus, and computer device and storage medium |
| CN110866696A (en) * | 2019-11-15 | 2020-03-06 | 成都数联铭品科技有限公司 | Method and device for training shop falling risk assessment model |
| CN113344692A (en) * | 2021-04-24 | 2021-09-03 | 大连理工大学 | Method for establishing network loan credit risk assessment model with multi-information-source fusion |
| CN113344692B (en) * | 2021-04-24 | 2022-03-11 | 大连理工大学 | Method for establishing network loan credit risk assessment model with multi-information-source fusion |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106570631B (en) | 2021-01-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106570631A (en) | Method and system of facing P2P platform operation risk estimation | |
| Mensah et al. | How are Africa's emerging stock markets related to advanced markets? Evidence from copulas | |
| Chen et al. | Credit risk measurement and early warning of SMEs: An empirical study of listed SMEs in China | |
| CN106372952A (en) | Objective and subjective weight determining multi-model compositional verification-based enterprise credit assessment method and system | |
| Samreen et al. | Design and development of credit scoring model for the commercial banks of Pakistan: Forecasting creditworthiness of individual borrowers | |
| CN104463673A (en) | P2P network credit risk assessment model based on support vector machine | |
| Bulman et al. | Good countries or good projects? Comparing macro and micro correlates of World Bank and Asian Development Bank project performance | |
| CN106780005A (en) | Rating business credit method and rating business credit device | |
| Gallo | Fintech platforms: Lax or careful borrowers’ screening? | |
| Zmami et al. | Oil price and the economic activity in GCC countries: Evidence from quantile regression | |
| Li et al. | Application of XGBoost in P2P default prediction | |
| Amore et al. | Corporate governance and international trade shocks | |
| Dastoori et al. | Credit scoring model for iranian banking customers and forecasting creditworthiness of borrowers | |
| Hui et al. | The model and empirical research of application scoring based on data mining methods | |
| Yuan | Research on credit risk assessment of P2P network platform: based on the logistic regression model of evidence weight | |
| van Greunen et al. | Determining the impact of different forms of stationarity on financial time series analysis | |
| Lopatina et al. | Managing risks of venture entrepreneurship | |
| Ando et al. | Do Japan's Free Trade Agreements (FTAs) Increase Its International Trade? | |
| Pavelková et al. | Measuring a company's performance: The identification of correlation between EVA and selected financial indicators with use of genetic algorithm | |
| Damayanti et al. | Overconfidence of Indonesian millennial investors' behavior during pandemic | |
| CN107423878A (en) | A kind of method and system towards P2P platform operation risk assessment | |
| Najahi et al. | Relationship between structure and performance in the banking industry of Iran | |
| Akpinar | Factors Affecting Bankruptcy Risk: An Application on Borsa Istanbul | |
| Benvenuti et al. | Asymmetric information in loan contracts: New evidence from Italian big data | |
| Park et al. | Assessing Bank Climate Disclosures and Their Relationship to Bank Lending |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |