CN110782339A - Default probability prediction method, system and readable storage medium - Google Patents
Default probability prediction method, system and readable storage medium Download PDFInfo
- Publication number
- CN110782339A CN110782339A CN201911003344.7A CN201911003344A CN110782339A CN 110782339 A CN110782339 A CN 110782339A CN 201911003344 A CN201911003344 A CN 201911003344A CN 110782339 A CN110782339 A CN 110782339A
- Authority
- CN
- China
- Prior art keywords
- client
- financial
- customer
- level
- default probability
- 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
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000003860 storage Methods 0.000 title claims abstract description 17
- 238000012546 transfer Methods 0.000 claims abstract description 44
- 238000013210 evaluation model Methods 0.000 claims description 6
- 230000007306 turnover Effects 0.000 claims description 6
- 239000000523 sample Substances 0.000 description 29
- 238000010801 machine learning Methods 0.000 description 28
- 239000011159 matrix material Substances 0.000 description 16
- 230000007704 transition Effects 0.000 description 14
- 230000000694 effects Effects 0.000 description 10
- 230000008859 change Effects 0.000 description 8
- 238000009826 distribution Methods 0.000 description 8
- 230000002787 reinforcement Effects 0.000 description 8
- 238000007619 statistical method Methods 0.000 description 8
- 230000008901 benefit Effects 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 6
- 238000012549 training Methods 0.000 description 6
- 230000006399 behavior Effects 0.000 description 4
- 230000003993 interaction Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000007621 cluster analysis Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000004941 influx Effects 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000008450 motivation Effects 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000005309 stochastic process Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000013467 fragmentation Methods 0.000 description 1
- 238000006062 fragmentation reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention provides a default probability prediction method, a default probability prediction system and a readable storage medium, wherein the method comprises the following steps: receiving a service request submitted by a client and acquiring basic information of the client; acquiring financial information of the client according to the basic information of the client and by combining a credit investigation center and third-party big data information; predicting the financial life cycle and liability level of the customer based on the financial information of the customer; evaluating the client's debt transfer capacity and level of willingness to save on duty; integrating the liability level, the debt transfer capability and the level of the contractual willingness of the client, and establishing a default probability model based on the financial life cycle; according to the invention, by establishing the default probability model, a financial institution can dynamically predict the default probability of the customer, so that the optimal credit granting period under the acceptable default probability level is selected, and the credit risk of the customer can be monitored; meanwhile, the default probability model is high in prediction accuracy and can be suitable for scenes in different fields.
Description
Technical Field
The present invention relates to the field of data processing and probability prediction, and more particularly, to a default probability prediction method, system and readable storage medium.
Background
The impact of the development of the internet technology on the financial field is getting larger and larger, the light application and fragmentation properties of finance are getting more and more obvious, no trend is reflected from the traditional loan to the P2P platform, and the loan demand of small and micro enterprises is gradually discovered and more paid attention. The characteristics of small fixed asset scale, small mortgage proportion in the asset structure, weak anti-risk capability, unstable business and the like of small and micro enterprises make the small and micro enterprises difficult to apply for mortgage loans and credit loans. To develop this emerging market, people reduce the risk of a default for a credit customer by building a credit customer default model to predict their future default probability.
Currently, mainstream default models (such as KMV default models) focus on studying whether the assets of customers are deteriorated, and the default probability is evaluated by combining historical sample information. However, such a violation model faces the following problems: the method has the advantages that individual differences are ignored, and the accuracy of default probability prediction is low; secondly, the accumulation period of default samples is long, which easily results in low accuracy of default probability prediction. Meanwhile, the existing various default models have obvious industriality and poor applicability in cross-domain scenes.
Disclosure of Invention
In order to solve at least one of the above technical problems, the present invention provides a default probability prediction method, system and readable storage medium.
In order to achieve the above object, a first aspect of the present invention provides a default probability prediction method, including:
receiving a service request submitted by a client and acquiring basic information of the client;
acquiring financial information of the client according to the basic information of the client and by combining a credit investigation center and third-party big data information;
predicting the financial life cycle and liability level of the customer based on the financial information of the customer;
evaluating the client's debt transfer capacity and level of willingness to save on duty;
and integrating the liability level, the debt transfer capability and the level of the contractual willingness of the client to establish a default probability model based on the financial life cycle.
In this scheme, according to the financial information prediction of customer's financial life cycle and liability level, still include:
predicting the financial life cycle of the customer according to the financial information of the customer and by adopting a financial life cycle model; and/or
And predicting the liability level of the client according to the financial information of the client and by adopting a liability level model.
In the scheme, the evaluating the debt transfer capability and the level of the wisdom of the client further comprises the following steps:
analyzing the existing financing channel and financing amount of the customer and evaluating the debt transfer capability under the fund turnover predicament; and/or
And establishing a comprehensive evaluation model according to the overdue records and social information of the clients, and dynamically evaluating the level of the client's willingness to keep in charge.
Preferably, the financing channel is one or more of loan, credit card and private loan.
In this scheme, the default probability prediction method further includes:
receiving a loan service request submitted by a customer, and acquiring basic information of the customer;
acquiring financial information of the client according to the basic information of the client and by combining a credit investigation center and third-party big data information;
predicting the financial life cycle and liability level of the customer based on the financial information of the customer;
evaluating the client's debt transfer capacity and level of willingness to save on duty;
and integrating the loan amount, the loan interest rate, the loan term, the liability level, the debt transfer capability and the agreement willingness level of the client to establish a time-varying agreement default probability model.
In this scheme, after establishing the default probability model based on the financial lifecycle, still include:
selecting a trust period at an acceptable breach probability level; and/or.
The credit risk of the customer is monitored.
The second aspect of the present invention further provides a default probability prediction system, which includes: a memory and a processor, the memory including a default probability prediction method program, the default probability prediction method program when executed by the processor implementing the steps of:
receiving a service request submitted by a client and acquiring basic information of the client;
acquiring financial information of the client according to the basic information of the client and by combining a credit investigation center and third-party big data information;
predicting the financial life cycle and liability level of the customer based on the financial information of the customer;
evaluating the client's debt transfer capacity and level of willingness to save on duty;
and integrating the liability level, the debt transfer capability and the level of the contractual willingness of the client to establish a default probability model based on the financial life cycle.
In this scheme, according to the financial information prediction of customer's financial life cycle and liability level, still include:
predicting the financial life cycle of the customer according to the financial information of the customer and by adopting a financial life cycle model; and/or
And predicting the liability level of the client according to the financial information of the client and by adopting a liability level model.
In the scheme, the evaluating the debt transfer capability and the level of the wisdom of the client further comprises the following steps:
analyzing the existing financing channel and financing amount of the customer and evaluating the debt transfer capability under the fund turnover predicament; and/or
And establishing a comprehensive evaluation model according to the overdue records and social information of the clients, and dynamically evaluating the level of the client's willingness to keep in charge.
The third aspect of the present invention also provides a computer-readable storage medium, which includes a default probability prediction method program, and when the default probability prediction method program is executed by a processor, the computer-readable storage medium implements the steps of the default probability prediction method as described above.
The invention receives the service request submitted by the client and obtains the basic information of the client; acquiring financial information of the client according to the basic information of the client and by combining a credit investigation center and third-party big data information; predicting the financial life cycle and liability level of the customer based on the financial information of the customer; evaluating the client's debt transfer capacity and level of willingness to save on duty; integrating the liability level, the debt transfer capability and the level of the contractual willingness of the client, and establishing a default probability model based on the financial life cycle; the default probability model can realize high-precision prediction of the default probability of the customer, and can be suitable for scenes in different fields. The default probability model of the invention can also make the financial institution dynamically predict the default probability of the customer, and select the optimal credit granting period under the acceptable default probability level, thereby reducing the default risk of the customer; meanwhile, under the condition of low cost, the credit risk of the client can be monitored.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
FIG. 1 is a flow chart illustrating a method of default probability prediction of the present invention;
FIG. 2 is a flow chart illustrating a method for predicting the loan transaction default probability of a credit customer according to the invention;
FIG. 3 illustrates a block diagram of a default probability prediction system of the present invention.
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described herein, and therefore the scope of the present invention is not limited by the specific embodiments disclosed below.
FIG. 1 is a flow chart illustrating a method for default probability prediction in accordance with the present invention.
As shown in fig. 1, a first aspect of the present invention provides a default probability prediction method, including:
s102, receiving a service request submitted by a client and acquiring basic information of the client;
s104, acquiring financial information of the client according to the basic information of the client and by combining a credit investigation center and third-party big data information;
s106, predicting the financial life cycle and liability level of the client according to the financial information of the client;
s108, evaluating the debt transfer capability and the level of the wisdom of conservation of the client;
and S110, integrating the liability level, the debt transfer capability and the contractual willingness level of the client, and establishing a default probability model based on the financial life cycle.
The client may be an individual or an enterprise. The basic information of the client can be one or more of a client name, an identification card, a business license, a contact address and a contact telephone.
After the default probability model is established, the probability of default can be predicted through the model. After customer information is input, big data information of a user is obtained through a background server, the big data information is input into a default probability model, and the default probability model is analyzed and calculated to obtain a probability value of customer default. And if the default probability threshold value is exceeded, performing reminding operation. Preferably, the breach probability threshold is 60%.
Further, predicting the financial life cycle and liability level of the client according to the financial information of the client, further comprising:
predicting the financial life cycle of the customer according to the financial information of the customer and by adopting a financial life cycle model; and/or
And predicting the liability level of the client according to the financial information of the client and by adopting a liability level model.
Further, the step of constructing the financial lifecycle model may be:
establishing a financial sample database;
and establishing a financial life cycle model according to the financial sample database by a machine learning method.
It should be noted that the financial sample database contains financial samples of different credit customers, and each financial sample includes all financial data in the financial lifecycle. It will be appreciated that the greater the number of financial samples in the financial sample database, the greater the accuracy of the financial lifecycle model predictions. However, the increase in the number of financial samples will result in a longer time for machine learning. Therefore, on the basis of meeting the prediction accuracy of the financial life cycle model, the number of financial samples in the financial sample database is properly reduced, and the machine learning efficiency can be improved. Preferably, the financial sample database includes ten thousand financial samples, but is not limited thereto.
It should be noted that machine learning (machine learning) is a multi-domain cross discipline, and relates to multiple disciplines such as probability theory, statistics, algorithm complexity, and the like. It is specialized to study how computers simulate or implement human learning behavior, and it is able to discover and mine the potential value contained in the data. Machine learning has become a branch of artificial intelligence, and potential rules of data are discovered and mined through a self-learning algorithm, so that unknown data are predicted. Machine learning has been widely used in the fields of computer science research, natural language processing, machine vision, speech, games, and the like. The methods of machine learning are mainly divided into three types: supervised learning, unsupervised learning, and reinforcement learning.
The training data in supervised learning is labeled with classes. Supervised learning builds a model by using training data with class targets, and unknown data can be predicted by the trained model. For example, the machine learning algorithm used for handwritten number recognition belongs to supervised learning, and before training a model, a number table represented by the picture needs to be defined so that a computer can extract better feature similarity marks from data. Supervised learning can be divided into classification and regression.
Reinforcement learning is the process of building a system to improve the performance of the system during interaction with the environment. The current state information of the environment may include a feedback signal by which the current system may be evaluated to improve the system. Through interaction with the environment, the system can obtain a series of behaviors through reinforcement learning, and forward feedback is maximized through the design of an incentive system. Reinforcement learning is often used in the field of games, such as go games, where the system determines the next step according to the current game status on the board, and the win or loss at the end of the game is used as the motivation signal.
Unsupervised learning deals with class labels or general trend ambiguity of data, and the unsupervised learning can search for potential regularity in the data without knowing the class labels and outputting scalar quantities and without feedback signals. Unsupervised learning can be divided into clustering and dimensionality reduction.
Further, establishing a financial life cycle model according to the financial sample database by a machine learning method, further comprising:
analyzing the life cycle of each financial sample in the financial sample database, and identifying financial change trends of different life cycles;
checking out the influence factors on the financial life cycle by adopting a statistical method, and quantifying the influence degree;
and integrating the financial life cycles of the samples and the influence factors of the financial life cycles, and constructing a Markov chain transfer matrix with variable time sequence.
Further, after identifying the financial variation trends of different life cycles, the method further comprises the following steps:
the general characteristics of the financial lifecycle are abstracted in conjunction with cluster analysis across sample data.
It should be noted that, before machine learning, it is first determined which features are important, general features of the financial lifecycle can be obtained through analysis, and machine learning finds corresponding patterns, that is, what kind of combinations of features will lead to what kind of results by analyzing general features of the financial lifecycle of each financial sample, thereby constructing a financial lifecycle model.
Further, the influence factors on the financial life cycle are tested by adopting a statistical method, and the method further comprises the following steps:
preselecting demographic information, work information and social information as influence factors of the financial life cycle;
the influence degree of the influence factors on the financial life cycle is checked by adopting a statistical method;
screening out the influence factors with the influence degree higher than the preset value, and taking the influence factors as potential variables of the financial life cycle.
It should be noted that, before machine learning, it is first determined which influencing factors are important through statistical method tests, and then machine learning finds the corresponding mode, that is, what kind of result the combination of features will lead to, by analyzing the influencing factors of the financial life cycle of each financial sample, so as to construct the financial life cycle model.
Further, after constructing the timing variable markov chain transfer matrix, the method further includes:
and displaying the possibility that the preset state point position of any financial life cycle changes to other state point positions in a probability form according to the Markov chain transfer matrix.
It should be noted that a Markov chain (Markov chain), also called a discrete-time Markov chain (discrete-time Markov chain), is a stochastic process in a state space that undergoes a transition from one state to another. This process requires a "memoryless" property: the probability distribution of the next state can only be determined by the current state, independent of events preceding it in the time series. This particular type of "memoryless" is referred to as a Markov property.
At each step of the Markov chain, the system may change from one state to another state, or may maintain the current state, according to a probability distribution. The change of state is called a transition and the probability associated with a different state change is called a transition probability. The probability distribution of state transitions is typically represented as a transition matrix of a markov chain. If the Markov chain has N possible states, then this transition matrix is an N by N matrix such that the element (I, J) represents the probability of transitioning from state I to state J. Furthermore, the state transition matrix must be a random matrix, the sum of its elements in each row must be 1.
Preferably, the specific steps of predicting the liability level of the client by the liability level model may be:
acquiring the net assets of the client through a credit investigation center and third-party big data information;
predicting income level and expenditure level of the customer at each time point of the customer's financial lifecycle;
and obtaining the liability level at each time point according to the net assets and the income level and the expenditure level at each time point.
It should be noted that the net asset is the client owner's equity, which refers to the economic benefit that the owner enjoys in the enterprise asset, and the amount is the balance of the asset minus the liability. Owner equity includes real capital (or equity), equity, earnings, and unallocated profits, among others.
Revenue refers to the total influx of economic benefits that an enterprise generates in daily activities that result in increased owner equity, regardless of the owner's investing in capital. Income is divided into commodity sales income, labor income provision and asset concession right income according to different properties of daily activities carried out by enterprises. The income is divided into main business income and other business income according to the difference of the primary business and the secondary business of the enterprise. The revenue of the main business is the revenue realized by the frequent activities undertaken by the enterprise to accomplish its business objectives. Other business revenue refers to revenue realized by activities associated with recurring activities engaged in by the enterprise to accomplish its business objectives.
An expense is the outflow of an asset that occurs during a production operation by an enterprise to obtain another asset, to liquidate a debt. Such as payment or prepaid money for purchasing materials, office supplies, etc. by enterprises; the outflow of assets that occurs for the repayment of bank debits, accounts payable and payment accounts or the payment of equity; expenses incurred for the purchase of fixed assets, the payment of long-term construction expenses and consumption expenses in life.
According to the embodiment of the invention, the evaluation of the debt transfer capability and the level of the wisdom of the client further comprises the following steps:
analyzing the existing financing channel and financing amount of the customer and evaluating the debt transfer capability under the fund turnover predicament; and/or
And establishing a comprehensive evaluation model according to the overdue records and social information of the clients, and dynamically evaluating the level of the client's willingness to keep in charge.
It should be noted that the financing channel may be one or more of loan, credit card, and private loan.
Fig. 2 is a flow chart illustrating a loan default probability prediction method for a credit customer according to the present invention.
As shown in fig. 2, the default probability prediction method further includes:
s202, receiving a loan service request submitted by a customer, and acquiring basic information of the customer;
s204, acquiring financial information of the client according to the basic information of the client and by combining a credit investigation center and third-party big data information;
s206, predicting the financial life cycle and liability level of the client according to the financial information of the client;
s208, evaluating the debt transfer capability and the level of the wisdom of conservation of the client;
s210, integrating the loan amount, the loan interest rate, the loan duration, the liability level, the debt transfer capability and the agreement willingness level of the client, and establishing a time-varying agreement default probability model.
It should be noted that the default probability model according to the present invention may be a probit model. The probit model is a generalized linear model that follows a normal distribution.
According to the embodiment of the invention, after establishing the default probability model based on the financial life cycle, the method further comprises the following steps:
selecting a trust period at an acceptable breach probability level; and/or.
The credit risk of the customer is monitored.
It can be understood that after the default probability model based on the financial life cycle of the customer is established, the financial institution can dynamically predict the default probability of the customer, and selects the optimal credit granting period under the acceptable default probability level in the financial life cycle according to the prediction result, so that the default risk of the customer is reduced; meanwhile, under the condition of low cost, the credit risk of the client can be monitored.
FIG. 3 illustrates a block diagram of a default probability prediction system of the present invention.
As shown in fig. 3, the second aspect of the present invention also proposes a default probability prediction system 3, wherein the credit customer default probability prediction system 3 comprises: a memory 31 and a processor 32, wherein the memory 31 includes a credit customer default probability prediction method program, and the credit customer default probability prediction method program when executed by the processor 32 implements the following steps:
receiving a service request submitted by a client and acquiring basic information of the client;
acquiring financial information of the client according to the basic information of the client and by combining a credit investigation center and third-party big data information;
predicting the financial life cycle and liability level of the customer based on the financial information of the customer;
evaluating the client's debt transfer capacity and level of willingness to save on duty;
and integrating the liability level, the debt transfer capability and the level of the contractual willingness of the client to establish a default probability model based on the financial life cycle.
The client may be an individual or an enterprise. The basic information of the client can be one or more of a client name, an identification card, a business license, a contact address and a contact telephone.
Further, predicting the financial life cycle and liability level of the client according to the financial information of the client, further comprising:
predicting the financial life cycle of the customer according to the financial information of the customer and by adopting a financial life cycle model; and/or
And predicting the liability level of the client according to the financial information of the client and by adopting a liability level model.
Further, the step of constructing the financial lifecycle model may be:
establishing a financial sample database;
and establishing a financial life cycle model according to the financial sample database by a machine learning method.
It should be noted that the financial sample database contains financial samples of different credit customers, and each financial sample includes all financial data in the financial lifecycle. It will be appreciated that the greater the number of financial samples in the financial sample database, the greater the accuracy of the financial lifecycle model predictions. However, the increase in the number of financial samples will result in a longer time for machine learning. Therefore, on the basis of meeting the prediction accuracy of the financial life cycle model, the number of financial samples in the financial sample database is properly reduced, and the machine learning efficiency can be improved. Preferably, the financial sample database includes ten thousand financial samples, but is not limited thereto.
It should be noted that machine learning (machine learning) is a multi-domain cross discipline, and relates to multiple disciplines such as probability theory, statistics, algorithm complexity, and the like. It is specialized to study how computers simulate or implement human learning behavior, and it is able to discover and mine the potential value contained in the data. Machine learning has become a branch of artificial intelligence, and potential rules of data are discovered and mined through a self-learning algorithm, so that unknown data are predicted. Machine learning has been widely used in the fields of computer science research, natural language processing, machine vision, speech, games, and the like. The methods of machine learning are mainly divided into three types: supervised learning, unsupervised learning, and reinforcement learning.
The training data in supervised learning is labeled with classes. Supervised learning builds a model by using training data with class targets, and unknown data can be predicted by the trained model. For example, the machine learning algorithm used for handwritten number recognition belongs to supervised learning, and before training a model, a number table represented by the picture needs to be defined so that a computer can extract better feature similarity marks from data. Supervised learning can be divided into classification and regression.
Reinforcement learning is the process of building a system to improve the performance of the system during interaction with the environment. The current state information of the environment may include a feedback signal by which the current system may be evaluated to improve the system. Through interaction with the environment, the system can obtain a series of behaviors through reinforcement learning, and forward feedback is maximized through the design of an incentive system. Reinforcement learning is often used in the field of games, such as go games, where the system determines the next step according to the current game status on the board, and the win or loss at the end of the game is used as the motivation signal.
Unsupervised learning deals with class labels or general trend ambiguity of data, and the unsupervised learning can search for potential regularity in the data without knowing the class labels and outputting scalar quantities and without feedback signals. Unsupervised learning can be divided into clustering and dimensionality reduction.
Further, establishing a financial life cycle model according to the financial sample database by a machine learning method, further comprising:
analyzing the life cycle of each financial sample in the financial sample database, and identifying financial change trends of different life cycles;
checking out the influence factors on the financial life cycle by adopting a statistical method, and quantifying the influence degree;
and integrating the financial life cycles of the samples and the influence factors of the financial life cycles, and constructing a Markov chain transfer matrix with variable time sequence.
Further, after identifying the financial variation trends of different life cycles, the method further comprises the following steps:
the general characteristics of the financial lifecycle are abstracted in conjunction with cluster analysis across sample data.
It should be noted that, before machine learning, it is first determined which features are important, general features of the financial lifecycle can be obtained through analysis, and machine learning finds corresponding patterns, that is, what kind of combinations of features will lead to what kind of results by analyzing general features of the financial lifecycle of each financial sample, thereby constructing a financial lifecycle model.
Further, the influence factors on the financial life cycle are tested by adopting a statistical method, and the method further comprises the following steps:
preselecting demographic information, work information and social information as influence factors of the financial life cycle;
the influence degree of the influence factors on the financial life cycle is checked by adopting a statistical method;
screening out the influence factors with the influence degree higher than the preset value, and taking the influence factors as potential variables of the financial life cycle.
It should be noted that, before machine learning, it is first determined which influencing factors are important through statistical method tests, and then machine learning finds the corresponding mode, that is, what kind of result the combination of features will lead to, by analyzing the influencing factors of the financial life cycle of each financial sample, so as to construct the financial life cycle model.
Further, after constructing the timing variable markov chain transfer matrix, the method further includes:
and displaying the possibility that the preset state point position of any financial life cycle changes to other state point positions in a probability form according to the Markov chain transfer matrix.
Markov chains (Markov chains), also known as discrete-time Markov chains (discrete-time Markovchain), are stochastic processes in state space that undergo transitions from one state to another. This process requires a "memoryless" property: the probability distribution of the next state can only be determined by the current state, independent of events preceding it in the time series. This particular type of "memoryless" is referred to as a Markov property.
At each step of the Markov chain, the system may change from one state to another state, or may maintain the current state, according to a probability distribution. The change of state is called a transition and the probability associated with a different state change is called a transition probability. The probability distribution of state transitions is typically represented as a transition matrix of a markov chain. If the Markov chain has N possible states, then this transition matrix is an N by N matrix such that the element (I, J) represents the probability of transitioning from state I to state J. Furthermore, the state transition matrix must be a random matrix, the sum of its elements in each row must be 1.
Preferably, the specific steps of predicting the liability level of the client by the liability level model may be:
acquiring the net assets of the client through a credit investigation center and third-party big data information;
predicting income level and expenditure level of the customer at each time point of the customer's financial lifecycle;
and obtaining the liability level at each time point according to the net assets and the income level and the expenditure level at each time point.
It should be noted that the net asset is the client owner's equity, which refers to the economic benefit that the owner enjoys in the enterprise asset, and the amount is the balance of the asset minus the liability. Owner equity includes real capital (or equity), equity, earnings, and unallocated profits, among others.
Revenue refers to the total influx of economic benefits that an enterprise generates in daily activities that result in increased owner equity, regardless of the owner's investing in capital. Income is divided into commodity sales income, labor income provision and asset concession right income according to different properties of daily activities carried out by enterprises. The income is divided into main business income and other business income according to the difference of the primary business and the secondary business of the enterprise. The revenue of the main business is the revenue realized by the frequent activities undertaken by the enterprise to accomplish its business objectives. Other business revenue refers to revenue realized by activities associated with recurring activities engaged in by the enterprise to accomplish its business objectives.
An expense is the outflow of an asset that occurs during a production operation by an enterprise to obtain another asset, to liquidate a debt. Such as payment or prepaid money for purchasing materials, office supplies, etc. by enterprises; the outflow of assets that occurs for the repayment of bank debits, accounts payable and payment accounts or the payment of equity; expenses incurred for the purchase of fixed assets, the payment of long-term construction expenses and consumption expenses in life.
According to the embodiment of the invention, the evaluation of the debt transfer capability and the level of the wisdom of the client further comprises the following steps:
analyzing the existing financing channel and financing amount of the customer and evaluating the debt transfer capability under the fund turnover predicament; and/or
And establishing a comprehensive evaluation model according to the overdue records and social information of the clients, and dynamically evaluating the level of the client's willingness to keep in charge.
It should be noted that the financing channel may be one or more of loan, credit card, and private loan.
The credit customer default probability prediction method program when executed by the processor further implements the steps of:
receiving a loan service request submitted by a customer, and acquiring basic information of the customer;
acquiring financial information of the client according to the basic information of the client and by combining a credit investigation center and third-party big data information;
predicting the financial life cycle and liability level of the customer based on the financial information of the customer;
evaluating the client's debt transfer capacity and level of willingness to save on duty;
and integrating the loan amount, the loan interest rate, the loan term, the liability level, the debt transfer capability and the agreement willingness level of the client to establish a time-varying agreement default probability model.
It should be noted that the default probability model according to the present invention may be a probit model. The probit model is a generalized linear model that follows a normal distribution.
According to the embodiment of the invention, after establishing the default probability model based on the financial life cycle, the method further comprises the following steps:
selecting a trust period at an acceptable breach probability level; and/or.
The credit risk of the customer is monitored.
It can be understood that after the default probability model based on the financial life cycle of the customer is established, the financial institution can dynamically predict the default probability of the customer, and selects the optimal credit granting period under the acceptable default probability level in the financial life cycle according to the prediction result, so that the default risk of the customer is reduced; meanwhile, under the condition of low cost, the credit risk of the client can be monitored.
The third aspect of the present invention also proposes a computer-readable storage medium, which includes a program of a credit customer default probability prediction method, which when executed by a processor implements the steps of a credit customer default probability prediction method as described above.
The invention receives the service request submitted by the client and obtains the basic information of the client; acquiring financial information of the client according to the basic information of the client and by combining a credit investigation center and third-party big data information; predicting the financial life cycle and liability level of the customer based on the financial information of the customer; evaluating the client's debt transfer capacity and level of willingness to save on duty; integrating the liability level, the debt transfer capability and the level of the contractual willingness of the client, and establishing a default probability model based on the financial life cycle; the default probability model can realize high-precision prediction of the default probability of the customer, and can be suitable for scenes in different fields. The default probability model of the invention can also make the financial institution dynamically predict the default probability of the customer, and select the optimal credit granting period under the acceptable default probability level, thereby reducing the default risk of the customer; meanwhile, under the condition of low cost, the credit risk of the client can be monitored.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described device embodiments are merely illustrative, for example, the division of the unit is only a logical functional division, and there may be other division ways in actual implementation, such as: multiple units or components may be combined, or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the coupling, direct coupling or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or units may be electrical, mechanical or other forms.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units; can be located in one place or distributed on a plurality of network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, all the functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately regarded as one unit, or two or more units may be integrated into one unit; the integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
Those of ordinary skill in the art will understand that: all or part of the steps for realizing the method embodiments can be completed by hardware related to program instructions, the program can be stored in a computer readable storage medium, and the program executes the steps comprising the method embodiments when executed; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Alternatively, the integrated unit of the present invention may be stored in a computer-readable storage medium if it is implemented in the form of a software functional module and sold or used as a separate product. Based on such understanding, the technical solutions of the embodiments of the present invention may be essentially implemented or a part contributing to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, a ROM, a RAM, a magnetic or optical disk, or various other media that can store program code.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (10)
1. A method for predicting a probability of breach, comprising:
receiving a service request submitted by a client and acquiring basic information of the client;
acquiring financial information of the client according to the basic information of the client and by combining a credit investigation center and third-party big data information;
predicting the financial life cycle and liability level of the customer based on the financial information of the customer;
evaluating the client's debt transfer capacity and level of willingness to save on duty;
and integrating the liability level, the debt transfer capability and the level of the contractual willingness of the client to establish a default probability model based on the financial life cycle.
2. The method of claim 1, wherein predicting the financial lifecycle and liability level of the customer based on the financial information of the customer, further comprises:
predicting the financial life cycle of the customer according to the financial information of the customer and by adopting a financial life cycle model; and/or
And predicting the liability level of the client according to the financial information of the client and by adopting a liability level model.
3. The method of claim 1, wherein the evaluating the debt transfer ability and the level of willingness to guard of the client further comprises:
analyzing the existing financing channel and financing amount of the customer and evaluating the debt transfer capability under the fund turnover predicament; and/or
And establishing a comprehensive evaluation model according to the overdue records and social information of the clients, and dynamically evaluating the level of the client's willingness to keep in charge.
4. The method as claimed in claim 3, wherein the financing channel is one or more of loan, credit card, and private loan.
5. The method of claim 1, further comprising:
receiving a loan service request submitted by a customer, and acquiring basic information of the customer;
acquiring financial information of the client according to the basic information of the client and by combining a credit investigation center and third-party big data information;
predicting the financial life cycle and liability level of the customer based on the financial information of the customer;
evaluating the client's debt transfer capacity and level of willingness to save on duty;
and integrating the loan amount, the loan interest rate, the loan term, the liability level, the debt transfer capability and the agreement willingness level of the client to establish a time-varying agreement default probability model.
6. The default probability prediction method of claim 1, further comprising, after establishing the financial lifecycle-based default probability model:
selecting a trust period at an acceptable breach probability level; and/or.
The credit risk of the customer is monitored.
7. A default probability prediction system, the default probability prediction system comprising: a memory and a processor, the memory including a default probability prediction method program, the default probability prediction method program when executed by the processor implementing the steps of:
receiving a service request submitted by a client and acquiring basic information of the client;
acquiring financial information of the client according to the basic information of the client and by combining a credit investigation center and third-party big data information;
predicting the financial life cycle and liability level of the customer based on the financial information of the customer;
evaluating the client's debt transfer capacity and level of willingness to save on duty;
and integrating the liability level, the debt transfer capability and the level of the contractual willingness of the client to establish a default probability model based on the financial life cycle.
8. The default probability prediction system of claim 7, wherein the financial lifecycle and liability level of the customer is predicted based on the financial information of the customer, further comprising:
predicting the financial life cycle of the customer according to the financial information of the customer and by adopting a financial life cycle model; and/or
And predicting the liability level of the client according to the financial information of the client and by adopting a liability level model.
9. The default probability prediction system of claim 7, wherein evaluating the debt transfer capacity and the level of willingness to commit of the customer further comprises:
analyzing the existing financing channel and financing amount of the customer and evaluating the debt transfer capability under the fund turnover predicament; and/or
And establishing a comprehensive evaluation model according to the overdue records and social information of the clients, and dynamically evaluating the level of the client's willingness to keep in charge.
10. A computer-readable storage medium, characterized in that a default probability prediction method program is included in the computer-readable storage medium, which, when executed by a processor, carries out the steps of a default probability prediction method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911003344.7A CN110782339A (en) | 2019-10-22 | 2019-10-22 | Default probability prediction method, system and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911003344.7A CN110782339A (en) | 2019-10-22 | 2019-10-22 | Default probability prediction method, system and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110782339A true CN110782339A (en) | 2020-02-11 |
Family
ID=69384374
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911003344.7A Pending CN110782339A (en) | 2019-10-22 | 2019-10-22 | Default probability prediction method, system and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110782339A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111754341A (en) * | 2020-07-07 | 2020-10-09 | 浪潮卓数大数据产业发展有限公司 | Method for calculating loan default probability PD of small and micro enterprise |
| CN112116402A (en) * | 2020-09-28 | 2020-12-22 | 中国建设银行股份有限公司 | Credit risk customer-level default rate determination method and device |
| CN112308293A (en) * | 2020-10-10 | 2021-02-02 | 北京贝壳时代网络科技有限公司 | Default probability prediction method and device |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7089207B1 (en) * | 2000-09-27 | 2006-08-08 | Jpmorgan Chase & Co. | Method and system for determining a company's probability of no default |
| CN101685526A (en) * | 2008-09-28 | 2010-03-31 | 阿里巴巴集团控股有限公司 | Loan permission assessment method and system |
| AU2011253885A1 (en) * | 2004-10-13 | 2012-01-12 | Bendigo And Adelaide Bank Limited | A Data Processing System and Method with Mitigates for Collateral Valuation Risk and Consumer Gaming |
| US20130332338A1 (en) * | 2010-01-13 | 2013-12-12 | Corelogic Solutions, Llc | System and method of detecting and assessing multiple types of risks related to mortgage lending |
| CN106296389A (en) * | 2016-07-28 | 2017-01-04 | 联动优势科技有限公司 | The appraisal procedure of a kind of user credit degree and device |
| CN106886883A (en) * | 2017-02-06 | 2017-06-23 | 黑龙江工业学院 | A kind of processing system of financial accounting form |
| CN107492033A (en) * | 2017-08-30 | 2017-12-19 | 广东信基蜂巢科技有限责任公司 | A kind of credit estimation method and device based on air control model |
| CN109118013A (en) * | 2018-08-29 | 2019-01-01 | 黑龙江工业学院 | A kind of management data prediction technique, readable storage medium storing program for executing and forecasting system neural network based |
| WO2019021314A1 (en) * | 2017-07-26 | 2019-01-31 | Capitaworld Platform Private Limited | A system and method for default probability prediction and credit scoring framework |
| CN110110981A (en) * | 2019-04-26 | 2019-08-09 | 重庆第二师范学院 | A kind of credit rating Default Probability estimates and method for prewarning risk |
-
2019
- 2019-10-22 CN CN201911003344.7A patent/CN110782339A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7089207B1 (en) * | 2000-09-27 | 2006-08-08 | Jpmorgan Chase & Co. | Method and system for determining a company's probability of no default |
| AU2011253885A1 (en) * | 2004-10-13 | 2012-01-12 | Bendigo And Adelaide Bank Limited | A Data Processing System and Method with Mitigates for Collateral Valuation Risk and Consumer Gaming |
| CN101685526A (en) * | 2008-09-28 | 2010-03-31 | 阿里巴巴集团控股有限公司 | Loan permission assessment method and system |
| US20130332338A1 (en) * | 2010-01-13 | 2013-12-12 | Corelogic Solutions, Llc | System and method of detecting and assessing multiple types of risks related to mortgage lending |
| CN106296389A (en) * | 2016-07-28 | 2017-01-04 | 联动优势科技有限公司 | The appraisal procedure of a kind of user credit degree and device |
| CN106886883A (en) * | 2017-02-06 | 2017-06-23 | 黑龙江工业学院 | A kind of processing system of financial accounting form |
| WO2019021314A1 (en) * | 2017-07-26 | 2019-01-31 | Capitaworld Platform Private Limited | A system and method for default probability prediction and credit scoring framework |
| CN107492033A (en) * | 2017-08-30 | 2017-12-19 | 广东信基蜂巢科技有限责任公司 | A kind of credit estimation method and device based on air control model |
| CN109118013A (en) * | 2018-08-29 | 2019-01-01 | 黑龙江工业学院 | A kind of management data prediction technique, readable storage medium storing program for executing and forecasting system neural network based |
| CN110110981A (en) * | 2019-04-26 | 2019-08-09 | 重庆第二师范学院 | A kind of credit rating Default Probability estimates and method for prewarning risk |
Non-Patent Citations (4)
| Title |
|---|
| 张颖;马玉林;: "基于因子分析的Logistic违约概率模型" * |
| 杨朝晖;: "商业银行消费信贷风险分析与对策研究" * |
| 汪海婴: "信用档案是打造社会信用体系的基础" * |
| 王勇;: "客户负债水平会影响供应商的信贷融资成本吗?――基于制造业上市公司的经验研究" * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111754341A (en) * | 2020-07-07 | 2020-10-09 | 浪潮卓数大数据产业发展有限公司 | Method for calculating loan default probability PD of small and micro enterprise |
| CN111754341B (en) * | 2020-07-07 | 2022-07-12 | 浪潮卓数大数据产业发展有限公司 | Method for calculating loan default probability PD of small and micro enterprise |
| CN112116402A (en) * | 2020-09-28 | 2020-12-22 | 中国建设银行股份有限公司 | Credit risk customer-level default rate determination method and device |
| CN112308293A (en) * | 2020-10-10 | 2021-02-02 | 北京贝壳时代网络科技有限公司 | Default probability prediction method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Biancone et al. | Crowdfunding and Fintech: business model sharia compliant | |
| Kauffman et al. | Technology investment decision-making under uncertainty | |
| Thomas | Consumer finance: Challenges for operational research | |
| Ouyang | Cashless payment and financial inclusion | |
| CN110083765A (en) | Financing information-pushing method, device, computer equipment and storage medium | |
| CN110782339A (en) | Default probability prediction method, system and readable storage medium | |
| Petrides et al. | Cost-sensitive learning for profit-driven credit scoring | |
| JP2017530494A (en) | Trading platform system and method | |
| Ufo et al. | Determinants of financial distress in manufacturing firms of Ethiopia | |
| CN113222732A (en) | Information processing method, device, equipment and storage medium | |
| CN115545886A (en) | Overdue risk identification method, overdue risk identification device, overdue risk identification equipment and storage medium | |
| US8255316B2 (en) | Integrated business decision-making system and method | |
| Barbon et al. | NFT bubbles | |
| Wagdi et al. | The integration of big data and artificial neural networks for enhancing credit risk scoring in emerging markets: Evidence from Egypt | |
| Bileki et al. | Order book mid-price movement inference by CatBoost classifier from convolutional feature maps | |
| Halladay | Using predictive analytics to improve decisionmaking | |
| Hubert et al. | Imperfect information in macroeconomics | |
| CN107844874A (en) | Enterprise operation problem analysis system and its method | |
| Jackson | Customer value exchange | |
| Ufo | Impact of Financial Distress on the Liquidity of Selected Manufacturing Firms of Ethiopia | |
| Philip et al. | A Partial Parameter HMM Based Clustering on Loan Repayment Data: Insights into Financial Behavior and Intent to Repay | |
| Brunel | Lifetime PD Analytics for Credit Portfolios: A Survey | |
| Horemuz | Application of Machine Learning to Financial Trading | |
| Benavente-Peces et al. | Applied Data Analytics | |
| Bastos de Sá Borges et al. | Analysis of CSR and ESG Investment Decisions: A Real Option Insight |
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: 20200211 |
|
| RJ01 | Rejection of invention patent application after publication |