CN113822488B - Risk prediction method and device for financing lease, computer equipment and storage medium - Google Patents
Risk prediction method and device for financing lease, computer equipment and storage medium Download PDFInfo
- Publication number
- CN113822488B CN113822488B CN202111150054.2A CN202111150054A CN113822488B CN 113822488 B CN113822488 B CN 113822488B CN 202111150054 A CN202111150054 A CN 202111150054A CN 113822488 B CN113822488 B CN 113822488B
- Authority
- CN
- China
- Prior art keywords
- risk
- data
- prediction
- feature data
- lessee
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000004364 calculation method Methods 0.000 claims abstract description 73
- 238000004458 analytical method Methods 0.000 claims abstract description 29
- 238000005516 engineering process Methods 0.000 claims abstract description 13
- 238000003062 neural network model Methods 0.000 claims description 14
- 238000012502 risk assessment Methods 0.000 claims description 13
- 238000012549 training Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 9
- 230000009193 crawling Effects 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 4
- 238000013473 artificial intelligence Methods 0.000 abstract description 7
- 230000008901 benefit Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000010801 machine learning Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000012954 risk control Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Finance (AREA)
- General Engineering & Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- Accounting & Taxation (AREA)
- Educational Administration (AREA)
- Technology Law (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to an artificial intelligence technology and provides a risk prediction method, a device, computer equipment and a storage medium for financing leases. The method comprises the following steps: acquiring a plurality of pieces of characteristic data of a target lessee in a financing lease project, wherein the characteristic data are used for representing the operating condition and the credit condition of the target lessee; inputting the multiple feature data into an analysis and calculation engine to obtain risk prediction results of different types; the analysis and calculation engine comprises one or more prediction models trained by big data, and each prediction model correspondingly outputs a branch prediction result; and evaluating the comprehensive risk of the target lessee according to the branch risk prediction result. The invention can realize automatic decision and approval of the credit risk of the lessee, evaluate the lessee in multiple dimensions based on algorithms, models and rules, and enable the total flow of the wind control of the financing and leasing project to be more intelligent, efficient and automatic.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a risk prediction method, a risk prediction device, computer equipment and a storage medium for financing leases.
Background
Financing lease indicates that a lessor makes a supply contract with a third party (supplier) according to a request of the lessee, and the lessor purchases equipment selected by the lessee from the supplier according to the supply contract. In order to guarantee the rights and interests of lessees, it is important to evaluate the risk of the lessees' credit rating. The prior art generally evaluates the credit risk of the lessee through historical transaction data and experience according to aspects of industry characteristics, financial conditions, operation conditions, project transaction structures, enterprise credit, post-loan management and the like corresponding to the lessee.
The existing risk assessment mode often has the problems of insufficient historical data acquisition and excessive manual intervention links, so that the risk assessment efficiency is low, misjudgment is easy to occur, and smooth performance of financing lease projects is affected. Therefore, how to improve the accuracy and efficiency of risk assessment in financing lease projects is a problem to be solved by those skilled in the art.
Disclosure of Invention
The invention aims to provide a lessee credit risk prediction scheme based on big data so as to solve the problems in the prior art.
In order to achieve the above object, the present invention provides a risk prediction method for financing lease, comprising:
Acquiring a plurality of pieces of characteristic data of a target lessee in a financing lease project, wherein the characteristic data are used for representing the operating condition and the credit condition of the target lessee;
Inputting the multiple feature data into an analysis and calculation engine to obtain risk prediction results of different types; the analysis and calculation engine comprises one or more prediction models trained by big data, and each prediction model correspondingly outputs a branch prediction result;
and evaluating the comprehensive risk of the target lessee according to the branch risk prediction result.
According to the risk prediction method for financing leases provided by the invention, the obtaining of the multiple feature data of the target lessee in the financing leasing project comprises the following steps:
Crawling various data information of candidate lessees from a plurality of information publishing websites by utilizing a data crawling technology;
Performing data filtering on various data information of the candidate lessees, extracting keywords, obtaining characteristic data sets corresponding to each candidate lessee, and storing the characteristic data sets in a database;
acquiring identification information of a target lessee, and inquiring candidate lessees which are the same as the identification information from the database;
and taking the characteristic data set corresponding to the candidate lessees with the same identification information as the characteristic data.
According to the risk prediction method for financing leases provided by the invention, the analysis and calculation engine comprises a plurality of prediction models, and the step of inputting the plurality of characteristic data into the analysis and calculation engine to obtain different types of risk prediction results comprises the following steps:
determining a first input feature corresponding to a first predictive model of the plurality of predictive models;
extracting the first input features from the multiple feature data, and inputting the first input features into the first prediction model to obtain a first prediction result output by the first prediction model;
the first input feature is all or part of the multiple feature data, and the first prediction result comprises any one of risk score, overdue repayment probability and enterprise loss probability.
According to the risk prediction method for financing leases provided by the invention, the first prediction result comprises a risk score, and the training method of the first prediction model comprises the following steps:
And acquiring a plurality of groups of historical characteristic data and corresponding historical scoring data corresponding to a plurality of sample lessees, wherein the historical characteristic data are used for representing the operating conditions and the credit conditions of the sample lessees, and the historical scoring data are risk percentage values determined by a manual evaluation mode.
And training a neural network model by taking the historical characteristic data as input data and the historical scoring data as output data so as to enable the neural network model to meet convergence conditions.
And determining weight parameters of all hidden variables in the neural network model under the convergence condition to obtain the first prediction model.
According to the risk prediction method for financing lease provided by the invention, the analysis and calculation engine comprises one or more calculation formulas, and the inputting of the multiple characteristic data into the analysis and calculation engine to obtain different types of risk prediction results further comprises:
determining a second input feature corresponding to a second calculation formula in the one or more calculation formulas;
Extracting the second input features from the multiple feature data, substituting the second input features into the second calculation formula, and obtaining a second prediction result corresponding to the second calculation formula;
wherein the second input feature is all or part of the plurality of feature data.
According to the risk prediction method for financing leases provided by the invention, the step of evaluating the comprehensive risk of the target lessee according to the branch risk prediction result comprises the following steps:
Acquiring a preset emphasis value related to the comprehensive risk, wherein the preset emphasis value characterizes a first prediction result and/or a second prediction result which are focused during current comprehensive risk assessment;
And carrying out weighted calculation on the plurality of first prediction results and/or the second prediction results based on the preset emphasis value so as to obtain the comprehensive risk.
According to the risk prediction method for financing leases provided by the invention, the step of evaluating the comprehensive risk of the target lessee according to the branch risk prediction result comprises the following steps:
determining a risk grade according to the numerical range to which the risk score belongs;
and determining whether to send risk early warning according to the risk level.
In order to achieve the above object, the present invention further provides a risk prediction apparatus for financing lease, including:
the feature acquisition module is suitable for acquiring a plurality of pieces of feature data of a target lessee in the financing lease project, wherein the feature data are used for representing the operating condition and the credit condition of the target lessee;
The calculation engine module is suitable for inputting the multiple characteristic data into an analysis calculation engine so as to obtain different types of risk prediction results; the analysis and calculation engine comprises one or more prediction models trained by big data, and each prediction model correspondingly outputs a branch prediction result;
And the risk assessment module is suitable for assessing the comprehensive risk of the target lessee according to the branch risk prediction result.
To achieve the above object, the present invention also provides a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the above method when executing the computer program.
To achieve the above object, the present invention also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the above method.
The risk prediction method, the risk prediction device, the risk prediction computer equipment and the risk prediction storage medium for financing lease provided by the invention have massive data and a complex machine learning model, and can reasonably and accurately distinguish a plurality of groups which cannot be evaluated in a traditional wind control mode. The invention can realize automatic decision and approval of the credit risk of the lessee, evaluate the lessee in multiple dimensions based on algorithms, models and rules, and enable the total flow of the wind control of the financing and leasing project to be more intelligent, efficient and automatic. The invention has remarkable effects of screening high-quality clients, reducing bad loan rate and improving risk management, helps financing leasing enterprises to better avoid risks, improves competitiveness and achieves maximization of benefits.
Drawings
FIG. 1 is a flowchart of a first embodiment of a risk prediction method for financing lease of the present invention;
FIG. 2 is a schematic flow chart of acquiring multiple feature data according to a first embodiment of the invention;
FIG. 3 is a schematic flow chart of training a first predictive model in accordance with a first embodiment of the invention;
FIG. 4 is a schematic diagram illustrating a first exemplary program module of a risk prediction apparatus for financing leases according to the present invention;
fig. 5 is a schematic hardware structure diagram of a risk prediction apparatus for financing lease according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
Referring to fig. 1, the present embodiment provides a risk prediction method for financing lease, which includes the following steps:
and S100, acquiring a plurality of pieces of characteristic data of a target lessee in the financing lease project, wherein the characteristic data are used for representing the operating condition and the credit condition of the target lessee.
The target lessee can be a device demander in a financing lease project, which puts forward a device use demand to a lessor, i.e., a financing lease enterprise, for device transactions between the financing lease enterprise and a third party supplier. The multiple feature data of the target lessee in this embodiment may include multiple data such as financial status, operation status, history lending record, employee composition, intellectual property possession status, credit investigation status, and the like of the target lessee. The above feature data may be provided directly by the user or may be obtained through a different information distribution site, such as an official authority site, to which the present embodiment is not limited.
S200, inputting the multiple feature data into an analysis and calculation engine to obtain different types of risk prediction results; wherein the analysis and calculation engine comprises one or more prediction models trained by big data, and each prediction model correspondingly outputs a branch prediction result.
The analysis and calculation engine in the embodiment is used for calculating all links of the risk in real time and providing a data base for risk assessment. The analysis and computation engine may include one or more big data trained prediction models, with the prediction models being utilized to output quantized prediction results for different types of risk for subsequent functional modules to perform different stages or aspects of risk control based on the quantized prediction results, such as predicting pre-loan risk via a pre-loan wind control prediction model, predicting intra-loan risk via a pre-loan wind control prediction model, predicting post-loan risk via a post-loan wind control prediction model, and so on. In this embodiment, the prediction result output by each prediction model may correspond to one branch prediction result, for example, the first prediction model outputs a first branch prediction result, the second prediction model outputs a second branch prediction result, the third prediction model outputs a third branch prediction result, and so on. In addition to the predictive model, the analytical calculation engine of the present embodiment may further include one or more calculation formulas, which may be determined according to empirical values, and the calculation results obtained via the calculation formulas may reflect quantized prediction results of different types of risks. The calculation result corresponding to each calculation formula in this embodiment may also correspond to a branch prediction result. Different from the prediction model, the calculation formula has no self-learning capability, has high dependency on an empirical value, and is suitable for characteristic data with small front-back variation amplitude. Those skilled in the art understand that the prediction model trained by machine learning has the advantages of high prediction accuracy and strong adaptability to different scenes, but has the disadvantages of larger input cost in the early stage and longer training period. The calculation formula has the advantages of low cost and high efficiency, and the disadvantage of being unable to adjust for different scenes, so that inaccurate prediction risks can be caused in some cases. The analysis and calculation engine in the embodiment combines the advantages of both the prediction model and the calculation formula, adopts the prediction model to predict risk for the dimension with higher accuracy requirement and faster application scene change, and can utilize the calculation formula to reduce cost for the dimension with small scene change and lower weight proportion, and performs risk prediction in a certain controllable range.
For the case where multiple prediction models are included, it is understood that different prediction models perform risk prediction based on different dimensions, and different prediction results are output. Thus when using different predictive models, different input feature dimensions need to be determined. Assume that the plurality of feature data acquired in step S100 includes feature data 1, feature data 2, feature data 3, feature data 4, feature data 5, and feature data 6, and the plurality of prediction models includes prediction model 1, prediction model 2, and prediction model 3, wherein feature data that needs to be input by prediction model 1 is feature data 1, feature data 2, and feature data 3, feature data that needs to be input by prediction model 2 is feature data 2, feature data 3, and feature data 4, and feature data that needs to be input by prediction model 3 is feature data 4, feature data 5, and feature data 6. Wherein, the feature data corresponding to each prediction model may be all or part of the multiple feature data. The mapping relation between the prediction model and the feature data can be saved through a data table, and when a certain prediction model needs to be used, the feature data corresponding to the certain prediction model can be determined through a table lookup. On the basis, different characteristic data are input into different prediction models, so that different prediction results can be obtained. For example, prediction model 1 outputs prediction result 1, prediction model 2 outputs prediction result 2, and prediction model 3 outputs prediction result 3. Based on the above, the embodiment can perform different weighted calculation according to the prediction results, so as to obtain comprehensive risk assessment under different dimensions.
For the case of multiple calculation formulas, it is also necessary to first determine the different input feature dimensions. Assuming that the multiple item of feature data acquired in step S100 includes feature data 1, feature data 2, feature data 3, feature data 4, feature data 5, and feature data 6, the multiple calculation formulas include calculation formula 1, calculation formula 2, and calculation formula 3, where feature data required to be input by calculation formula 1 is feature data 1, feature data 2, and feature data 3, feature data required to be input by calculation formula 2 is feature data 2, feature data 3, and feature data 4, and feature data required to be input by calculation formula 3 is feature data 4, feature data 5, and feature data 6. The feature data corresponding to each calculation formula may be all or part of the multiple feature data. The mapping relation between the calculation formula and the characteristic data can be saved through a data table, and when a certain calculation formula needs to be used, the characteristic data corresponding to the certain calculation formula can be determined through a table lookup. On the basis, different characteristic data are input into different calculation formulas, so that different calculation results can be obtained. For example, the calculation result 1 is calculated by the calculation formula 1, the calculation result 2 is calculated by the calculation formula 2, and the calculation result 3 is calculated by the calculation formula 3. Based on the calculation results, the embodiment can carry out different weighted calculation according to the calculation results, so that comprehensive risk assessment under different dimensions is obtained. Of course, the above prediction result and the above calculation result may be weighted together to obtain the comprehensive risk assessment, which is also within the protection scope of the present embodiment.
And S300, evaluating the comprehensive risk of the target lessee according to the branch risk prediction result.
The integrated risk in this embodiment may include multiple different types of risk indicators, such as multiple indicators of pre-loan risk, intra-loan risk, post-loan risk, overdue risk level, bankruptcy risk level, risk early warning, and the like. Wherein, different risk indexes are calculated according to branch prediction results with different weights. The weights of different branch prediction results in different comprehensive risks can be determined through preset rules. For example, preset rule 1 specifies that overall risk 1 = 0.5 x branch prediction 1+0.2 x branch prediction 2+0.3 x branch prediction 3; preset rule 2 specifies that comprehensive risk 2 = 0.4 x branch prediction result 2+0.3 x branch prediction result 3+0.3 x branch prediction result 4; … … can reflect the emphasis points of different comprehensive risk indexes through different preset rules, so that personalized customization of different financing lease projects is realized, and the requirements of different financing lease enterprises are met.
Fig. 2 shows a schematic flow chart of acquiring multiple feature data in a first embodiment of the invention. As shown in fig. 2, step S100 includes:
And S110, crawling various data information of the candidate lessees from the familia Wei websites by using a data crawling technology. The authoritative website may include a national enterprise credit information display system of the national institute of industry and commerce, a national land market network of the national resource department, a national referee document network of the highest national court, a national court executed person information inquiry system of the highest national court, a national court out-of-trust executed person list information inquiry system of the highest national court, a national license information disclosure website, a national intellectual property office patent search system, and a national trademark office Chinese trademark network of the national institute of industry and commerce. It can be understood that each authoritative website reflects the basic information, the management information, the financial condition and the like of the lessees from different sides, so that the information can be used as a data base for risk assessment of the lessees.
And S120, carrying out data filtering on various data information of the candidate lessees, extracting keywords, obtaining characteristic data sets corresponding to each candidate lessee, and storing the characteristic data sets in a database.
Different keyword filtering schemes can be formulated according to different requirements, for example, for the data of a patent retrieval system of the national intellectual property office, a disclosure text or an authorized text can be filtered out, so that different data statistics requirements are met. The feature data set in this embodiment may include a plurality of pieces of feature data, each piece of feature data from one of the familia web sites. Further, each candidate tenant may be tagged with unique identification information, and the identification information and the corresponding feature data set may be stored as a data record in a database.
S130, obtaining identification information of the target lessee, and inquiring candidate lessees which are the same as the identification information from the database.
And S140, taking the characteristic data set corresponding to the candidate lessees with the same identification information as the plurality of characteristic data.
Through the steps, all feature data related to the target lessee can be quickly obtained, and a complete data basis is provided for improving the accuracy of predicting credit risk.
Fig. 3 shows a schematic flow chart of training a first predictive model in a first embodiment of the invention. As shown in fig. 3, the first prediction model is trained by:
S310, acquiring a plurality of groups of historical characteristic data and corresponding historical scoring data corresponding to a plurality of sample lessees, wherein the historical characteristic data are used for representing the operation condition and the credit condition of the sample lessees, and the historical scoring data are risk percentage values determined by a manual evaluation mode.
And S320, training a neural network model by taking the historical characteristic data as input data and the historical scoring data as output data so that the neural network model meets convergence conditions. The neural network model may be any one of a convolutional neural network, a residual neural network, a multi-layer perceptron, a deep learning neural network, and the like, which is not limited in this embodiment.
And S330, determining weight parameters of all hidden variables in the neural network model under the convergence condition to obtain the first prediction model.
It will be appreciated that the scoring data output by the first predictive model described above is for example only and is not intended to be limiting. The neural network model can be trained by a person skilled in the art through different sample input data and different sample output data, so that different types of credit risks can be predicted, and various personalized requirements of users are met.
Further, in the step of evaluating the comprehensive risk of the target tenant according to the branch risk prediction result, the present embodiment may further include: and determining a risk grade according to the numerical range to which the risk score belongs, and determining whether to send risk early warning according to the risk grade. The steps can qualitatively reflect the risk condition of the target lessee, so that management personnel can find potential risks in time and take corresponding treatment, and unnecessary losses of financing leasing enterprises are avoided.
The embodiment of the application can acquire and process the related data based on the artificial intelligence technology. Wherein artificial intelligence (ARTIFICIAL INTELLIGENCE, AI) is the theory, method, technique, and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend, and expand human intelligence, sense the environment, acquire knowledge, and use knowledge to obtain optimal results. Artificial intelligence infrastructure technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and other directions.
With continued reference to fig. 4, a risk prediction apparatus for financing leases is shown, in which the risk prediction apparatus 40 may include or be divided into one or more program modules, one or more program modules being stored in a storage medium and executed by one or more processors to implement the present invention and the risk prediction method described above. Program modules in the present invention refer to a series of computer program instruction segments capable of performing a specific function, which are more suitable than the program itself for describing the execution of risk prediction means 40 in a storage medium. The following description will specifically describe functions of each program module of the present embodiment:
The feature acquisition module 41 is adapted to acquire a plurality of feature data of a target lessee in a financing lease project, wherein the feature data is used for representing the operation condition and the credit condition of the target lessee;
The calculation engine module 42 is adapted to input the multiple feature data into an analysis calculation engine to obtain different types of risk prediction results; the analysis and calculation engine comprises one or more prediction models trained by big data, and each prediction model correspondingly outputs a branch prediction result;
a risk assessment module 43 adapted to assess the overall risk of the target tenant based on the branch risk prediction result.
The present embodiment also provides a computer device, such as a smart phone, a tablet computer, a notebook computer, a desktop computer, a rack-mounted server, a blade server, a tower server, or a rack-mounted server (including an independent server or a server cluster formed by a plurality of servers) that can execute a program. The computer device 50 of the present embodiment includes at least, but is not limited to: a memory 51, a processor 52, which may be communicatively coupled to each other via a system bus, as shown in fig. 5. It should be noted that fig. 5 only shows a computer device 50 having components 51-52, but it should be understood that not all of the illustrated components are required to be implemented, and that more or fewer components may be implemented instead.
In the present embodiment, the memory 51 (i.e., readable storage medium) includes a flash memory, a hard disk, a multimedia card, a card memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, and the like. In some embodiments, the memory 51 may be an internal storage unit of the computer device 50, such as a hard disk or memory of the computer device 50. In other embodiments, the memory 51 may also be an external storage device of the computer device 50, such as a plug-in hard disk provided on the computer device 50, a smart memory card (SMART MEDIA CARD, SMC), a Secure Digital (SD) card, a flash memory card (FLASH CARD), or the like. Of course, the memory 51 may also include both internal storage units of the computer device 20 and external storage devices. In this embodiment, the memory 51 is generally used to store an operating system and various types of application software installed on the computer device 50, such as program codes of the risk prediction apparatus 40 of the first embodiment. Further, the memory 51 may also be used to temporarily store various types of data that have been output or are to be output.
Processor 52 may be a central processing unit (Central Processing Unit, CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments. The processor 52 is generally used to control the overall operation of the computer device 50. In this embodiment, the processor 52 is configured to execute the program code stored in the memory 51 or process data, such as running the risk prediction device 40, to implement the risk prediction method of the first embodiment.
The present embodiment also provides a computer-readable storage medium such as a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, a server, an App application store, etc., on which a computer program is stored, which when executed by a processor, performs the corresponding functions. The computer readable storage medium of the present embodiment is used for storing the risk prediction device 40 for financing lease, and when executed by a processor, implements the risk prediction method for financing lease of the first embodiment.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and further implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
It will be appreciated by those of ordinary skill in the art that all or part of the steps carried out in the method of the above-described embodiments may be implemented by a program to instruct related hardware, and the program may be stored in a computer readable medium, where the program when executed includes one or a combination of the steps of the method embodiment.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (7)
1. A risk prediction method for financing lease, comprising:
Acquiring multiple pieces of characteristic data of a target lessee in a financing lease project, wherein the multiple pieces of characteristic data are used for representing the operating condition and the credit condition of the target lessee;
Inputting the multiple feature data into an analysis and calculation engine to obtain risk prediction results of different types; the analysis and calculation engine comprises one or more prediction models trained by big data, and each prediction model correspondingly outputs a branch prediction result;
evaluating the comprehensive risk of the target lessee according to the branch prediction result;
The analysis and computation engine includes a plurality of prediction models, and the inputting the plurality of feature data into the analysis and computation engine to obtain different types of risk prediction results includes:
determining a first input feature corresponding to a first predictive model of the plurality of predictive models;
extracting the first input features from the multiple feature data, and inputting the first input features into the first prediction model to obtain a first prediction result output by the first prediction model;
the first input feature is all or part of the multiple feature data, and the first prediction result comprises any one of risk score, overdue repayment probability and enterprise loss probability;
the analysis and computation engine includes one or more computation formulas, and the inputting the plurality of feature data into the analysis and computation engine to obtain different types of risk prediction results further includes:
Determining a second input feature corresponding to a second calculation formula of the one or more calculation formulas;
Extracting the second input features from the multiple feature data, substituting the second input features into the second calculation formula, and obtaining a second prediction result corresponding to the second calculation formula;
wherein the second input feature is all or part of the plurality of feature data;
the training method of the first prediction model comprises the following steps:
Acquiring a plurality of groups of history feature data and corresponding history scoring data corresponding to a plurality of sample lessees, wherein the history feature data are used for representing the operation condition and the credit condition of the sample lessees;
Training a neural network model by taking the historical characteristic data as input data and the historical scoring data as output data so that the neural network model meets convergence conditions;
And determining weight parameters of all hidden variables in the neural network model under the convergence condition to obtain the first prediction model.
2. The method for predicting risk of financing lease of claim 1, wherein the acquiring the plurality of feature data of the target lessee in the financing lease item comprises:
Crawling various data information of candidate lessees from a plurality of information publishing websites by utilizing a data crawling technology;
Performing data filtering on various data information of the candidate lessees, extracting keywords, obtaining characteristic data sets corresponding to each candidate lessee, and storing the characteristic data sets in a database;
acquiring identification information of a target lessee, and inquiring candidate lessees which are the same as the identification information from the database;
and taking the characteristic data set corresponding to the candidate lessees with the same identification information as the characteristic data.
3. The method of claim 1, wherein the evaluating the aggregate risk of the target tenant based on the branch prediction results comprises:
Acquiring a preset emphasis value related to the comprehensive risk, wherein the preset emphasis value characterizes a first prediction result and/or a second prediction result which are focused during current comprehensive risk assessment;
And carrying out weighted calculation on the plurality of first prediction results and/or the second prediction results based on the preset emphasis value so as to obtain the comprehensive risk.
4. The method of claim 1, wherein the evaluating the aggregate risk of the target tenant based on the branch prediction results comprises:
determining a risk grade according to the numerical range to which the risk score belongs;
and determining whether to send risk early warning according to the risk level.
5. A risk prediction apparatus for financing lease, comprising:
The feature acquisition module is suitable for acquiring a plurality of pieces of feature data of a target lessee in the financing lease project, wherein the plurality of pieces of feature data are used for representing the operating condition and the credit condition of the target lessee;
The calculation engine module is suitable for inputting the multiple characteristic data into an analysis calculation engine so as to obtain different types of risk prediction results; the analysis and calculation engine comprises one or more prediction models trained by big data, and each prediction model correspondingly outputs a branch prediction result;
the risk assessment module is suitable for assessing the comprehensive risk of the target lessee according to the branch prediction result;
The analysis and computation engine includes a plurality of prediction models, and the inputting the plurality of feature data into the analysis and computation engine to obtain different types of risk prediction results includes:
determining a first input feature corresponding to a first predictive model of the plurality of predictive models;
extracting the first input features from the multiple feature data, and inputting the first input features into the first prediction model to obtain a first prediction result output by the first prediction model;
the first input feature is all or part of the multiple feature data, and the first prediction result comprises any one of risk score, overdue repayment probability and enterprise loss probability;
the analysis and computation engine includes one or more computation formulas, and the inputting the plurality of feature data into the analysis and computation engine to obtain different types of risk prediction results further includes:
Determining a second input feature corresponding to a second calculation formula of the one or more calculation formulas;
Extracting the second input features from the multiple feature data, substituting the second input features into the second calculation formula, and obtaining a second prediction result corresponding to the second calculation formula;
wherein the second input feature is all or part of the plurality of feature data;
the training method of the first prediction model comprises the following steps:
Acquiring a plurality of groups of history feature data and corresponding history scoring data corresponding to a plurality of sample lessees, wherein the history feature data are used for representing the operation condition and the credit condition of the sample lessees;
Training a neural network model by taking the historical characteristic data as input data and the historical scoring data as output data so that the neural network model meets convergence conditions;
And determining weight parameters of all hidden variables in the neural network model under the convergence condition to obtain the first prediction model.
6. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of claims 1 to 4 when the computer program is executed.
7. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111150054.2A CN113822488B (en) | 2021-09-29 | 2021-09-29 | Risk prediction method and device for financing lease, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111150054.2A CN113822488B (en) | 2021-09-29 | 2021-09-29 | Risk prediction method and device for financing lease, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113822488A CN113822488A (en) | 2021-12-21 |
| CN113822488B true CN113822488B (en) | 2024-05-14 |
Family
ID=78921439
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111150054.2A Active CN113822488B (en) | 2021-09-29 | 2021-09-29 | Risk prediction method and device for financing lease, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113822488B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115271553B (en) * | 2022-09-27 | 2023-01-20 | 湖南华菱电子商务有限公司 | Contract management method and device based on big data, electronic equipment and storage medium |
| CN116822968B (en) * | 2023-08-28 | 2023-11-21 | 富鸿资本(湖南)融资租赁有限公司 | Risk management method for continuously generating cash flow based on rentals |
| CN117036009B (en) * | 2023-10-09 | 2024-02-06 | 深圳薪汇科技有限公司 | Full-period management method and system for security service |
| CN117634893A (en) * | 2024-01-24 | 2024-03-01 | 浙江浙商金控有限公司 | Risk assessment model training method and risk prediction method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106780117A (en) * | 2016-12-02 | 2017-05-31 | 国网浙江省电力公司经济技术研究院 | A kind of power distribution network project financial leasing methods of risk assessment |
| CN109816534A (en) * | 2018-12-17 | 2019-05-28 | 平安国际融资租赁有限公司 | Financing lease Products Show method, apparatus, computer equipment and storage medium |
| CN112435105A (en) * | 2021-01-27 | 2021-03-02 | 支付宝(杭州)信息技术有限公司 | Rental risk assessment method, device, equipment and system based on block chain |
| CN113409119A (en) * | 2021-06-22 | 2021-09-17 | 远光软件股份有限公司 | Method and device for assessing capital risk of financing lease enterprise, storage medium and electronic equipment |
-
2021
- 2021-09-29 CN CN202111150054.2A patent/CN113822488B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106780117A (en) * | 2016-12-02 | 2017-05-31 | 国网浙江省电力公司经济技术研究院 | A kind of power distribution network project financial leasing methods of risk assessment |
| CN109816534A (en) * | 2018-12-17 | 2019-05-28 | 平安国际融资租赁有限公司 | Financing lease Products Show method, apparatus, computer equipment and storage medium |
| CN112435105A (en) * | 2021-01-27 | 2021-03-02 | 支付宝(杭州)信息技术有限公司 | Rental risk assessment method, device, equipment and system based on block chain |
| CN113409119A (en) * | 2021-06-22 | 2021-09-17 | 远光软件股份有限公司 | Method and device for assessing capital risk of financing lease enterprise, storage medium and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113822488A (en) | 2021-12-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113822488B (en) | Risk prediction method and device for financing lease, computer equipment and storage medium | |
| CN110009174B (en) | Risk recognition model training method and device and server | |
| CN110020770A (en) | Risk and information management based on artificial intelligence | |
| CN110020862B (en) | Business risk assessment method and device and computer readable storage medium | |
| CN109859052B (en) | Intelligent recommendation method and device for investment strategy, storage medium and server | |
| US20220343433A1 (en) | System and method that rank businesses in environmental, social and governance (esg) | |
| CN105528465A (en) | Credit status assessment method and device | |
| JP2006216019A (en) | Value chain and enterprise value analysis device and method | |
| CN112750029A (en) | Credit risk prediction method, device, electronic equipment and storage medium | |
| Kim | Spatiotemporal scale dependency and other sensitivities in dynamic land-use change simulations | |
| CN115760332A (en) | Risk prediction method, system, medium and device based on enterprise data analysis | |
| CN117235608B (en) | Risk detection method, risk detection device, electronic equipment and storage medium | |
| CN117132383A (en) | Credit data processing method, device, equipment and readable storage medium | |
| CN116843483A (en) | Vehicle insurance claim settlement method, device, computer equipment and storage medium | |
| CN115809930A (en) | Anti-fraud analysis method, device, equipment and medium based on data fusion matching | |
| KR102543211B1 (en) | Company's growth potential prediction system using unstructured data | |
| CN114298825A (en) | Method and device for extremely evaluating repayment volume | |
| CN108805603A (en) | Marketing activity method for evaluating quality, server and computer readable storage medium | |
| CN114581209A (en) | Method, device and equipment for training financial analysis model and storage medium | |
| CN114092057A (en) | Project model construction method and device, terminal equipment and storage medium | |
| Park et al. | A new forecasting system using the latent dirichlet allocation (LDA) topic modeling technique | |
| CN117094817B (en) | Credit risk control intelligent prediction method and system | |
| CN113742495B (en) | Rating feature weight determining method and device based on prediction model and electronic equipment | |
| Kaisar et al. | Explainable Machine Learning Models for Credit Risk Analysis: A Survey | |
| US20230027774A1 (en) | Smart real estate evaluation system |
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 |