CN108182633B - Loan data processing method, loan data processing device, loan data processing program, and computer device and storage medium - Google Patents
Loan data processing method, loan data processing device, loan data processing program, and computer device and storage medium Download PDFInfo
- Publication number
- CN108182633B CN108182633B CN201810091577.6A CN201810091577A CN108182633B CN 108182633 B CN108182633 B CN 108182633B CN 201810091577 A CN201810091577 A CN 201810091577A CN 108182633 B CN108182633 B CN 108182633B
- Authority
- CN
- China
- Prior art keywords
- loan
- client
- credit
- continuation
- continuous
- 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
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 application relates to a loan data processing method, a loan data processing device, a computer device and a storage medium, wherein the method comprises the following steps: acquiring personal identity information and initial credit application information of each initial credit client in a current initial credit client set, and acquiring a first subsequent credit prediction probability corresponding to each initial credit client by adopting a preset first prediction model according to the personal identity information and the initial credit application information; acquiring monthly supply ratio data of each first credit client in the current first credit client set within a preset time period, and obtaining a second subsequent credit prediction probability corresponding to each first credit client by adopting a preset second prediction model according to the monthly supply ratio data; obtaining a comprehensive continuous loan prediction probability corresponding to each first loan customer by adopting a preset third prediction model according to the first continuous loan prediction probability and the second continuous loan prediction probability; and sequencing the first loan clients according to the comprehensive loan continuation prediction probability corresponding to the first loan clients to obtain a sequencing result, and pushing loan product information according to the sequencing result. The invention can save computer resources.
Description
Technical Field
The present application relates to the field of data processing technologies, and in particular, to a loan data processing method, apparatus, computer device, and storage medium.
Background
With the rapid development of internet technology, more and more internet-based financial products such as financial products and loan products are available. The loan products mainly include small loans and large loans, and the small loans are favored by more and more people due to lower application thresholds, so that marketing of making small loans is urgent for internet financial companies taking loans as main operation services.
In the traditional technology, when an internet finance company carries out petty loan marketing, a background server mainly randomly selects a client to push loan products, and in order to ensure that the marketing success rate is high, the background server often needs to push massive amounts of loan products, so that the waste of computer resources is caused.
Disclosure of Invention
In view of the above, it is desirable to provide a loan data processing method, apparatus, computer device, and storage medium that can save computer resources in view of the above technical problems.
A method of loan data processing, the method comprising:
acquiring personal identity information and initial loan application information of each initial loan client in a current initial loan client set, and acquiring a first continuous loan prediction probability corresponding to each initial loan client by adopting a preset first prediction model according to the personal identity information and the initial loan application information;
acquiring monthly supply ratio data of each first credit client in a current first credit client set within a preset time period, and obtaining a second subsequent credit prediction probability corresponding to each first credit client by adopting a preset second prediction model according to the monthly supply ratio data;
obtaining a comprehensive continuous loan prediction probability corresponding to each first loan customer by adopting a preset third prediction model according to the first continuous loan prediction probability and the second continuous loan prediction probability;
and sequencing the first and second lending clients according to the comprehensive successive lending prediction probability corresponding to each first and second lending client to obtain a sequencing result, and pushing loan product information according to the sequencing result.
In one embodiment, the generating of the first prediction model comprises:
acquiring personal identity information, first loan application information and continuous loan probability of each loan customer in a historical loan customer set;
obtaining a first training sample according to the personal identity information, the first loan application information and the loan continuation probability;
and carrying out model training according to the first training sample to obtain a first prediction model.
In one embodiment, the generating of the second prediction model comprises:
acquiring monthly supply ratio data of each loan client in a historical loan client set within a preset time period;
obtaining a second training sample according to the monthly supply ratio data and the continuous loan probability;
and carrying out model training according to the second training sample to obtain a second prediction model.
In one embodiment, the generating of the third prediction model comprises:
obtaining a first loan continuation prediction probability corresponding to each loan customer by adopting a preset first prediction model according to the personal identity information and the first loan application information of each loan customer in the historical loan customer set;
obtaining a second loan continuation prediction probability corresponding to each loan customer in the historical loan customer set by adopting a preset second prediction model according to monthly supply ratio data of each loan customer in a preset time period;
and obtaining a third training sample according to the first continuous loan prediction probability, the second continuous loan prediction probability and the continuous loan probability corresponding to each loan customer in the historical loan customer set, and performing model training according to the third training sample to obtain a third prediction model.
In one embodiment, the step of ranking the lending clients according to the comprehensive lending continuation prediction probabilities corresponding to the lending clients to obtain a ranking result, and the step of pushing loan product information according to the ranking result includes:
obtaining a loan continuation client set according to the historical loan client set;
selecting a loan client from the current loan client set as a current target client according to the sorting result;
mapping the current target customer and each credit continuation customer in the credit continuation customer set to a multidimensional vector space with the credit first information and the identity information as coordinates, and respectively obtaining the vector coordinates of the current target customer and the vector coordinates corresponding to each credit continuation customer;
calculating the vector distance between the current target client and each continuous loan client in the continuous loan client set;
taking the corresponding continuous credit customer when the vector distance is smaller than the preset value as a reference object of the current target customer to obtain a reference object set;
and pushing loan product information according to the reference object set.
In one embodiment, the step of pushing loan product information according to the reference object set comprises the following steps:
inquiring the continuous loan products of each reference object in the reference object set to obtain a continuous loan product set;
acquiring the reference object quantity corresponding to each continuous loan product in the continuous loan product set;
and obtaining a target push product corresponding to the current target client according to the reference object quantity corresponding to each continuous loan product.
In one embodiment, the method further comprises:
and pushing the target push product to a terminal corresponding to the current target customer.
A loan data processing apparatus, characterized in that the apparatus comprises:
the first continuation credit prediction probability acquisition module is used for acquiring personal identity information and first credit application information of each first credit client in the current first credit client set, and acquiring a first continuation credit prediction probability corresponding to each first credit client by adopting a preset first prediction model according to the personal identity information and the first credit application information;
the second continuation credit prediction probability obtaining module is used for obtaining monthly supply ratio data of each benefit credit client in the current benefit credit client set in a preset time period, and obtaining second continuation credit prediction probabilities corresponding to the benefit credit clients by adopting a preset second prediction model according to the monthly supply ratio data;
the comprehensive continuation credit prediction probability module is used for obtaining the comprehensive continuation credit prediction probability corresponding to each first credit customer by adopting a preset third prediction model according to the first continuation credit prediction probability and the second continuation credit prediction probability;
and the sequencing module is used for sequencing each loan client according to the comprehensive loan continuation prediction probability corresponding to each loan client to obtain a sequencing result, and pushing loan product information according to the sequencing result.
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 following steps when executing the computer program:
acquiring personal identity information and initial loan application information of each initial loan client in a current initial loan client set, and acquiring a first continuous loan prediction probability corresponding to each initial loan client by adopting a preset first prediction model according to the personal identity information and the initial loan application information;
acquiring monthly supply ratio data of each first credit client in a current first credit client set within a preset time period, and obtaining a second subsequent credit prediction probability corresponding to each first credit client by adopting a preset second prediction model according to the monthly supply ratio data;
obtaining a comprehensive continuous loan prediction probability corresponding to each first loan customer by adopting a preset third prediction model according to the first continuous loan prediction probability and the second continuous loan prediction probability;
and sequencing the first and second lending clients according to the comprehensive successive lending prediction probability corresponding to each first and second lending client to obtain a sequencing result, and pushing loan product information according to the sequencing result.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
acquiring personal identity information and initial loan application information of each initial loan client in a current initial loan client set, and acquiring a first continuous loan prediction probability corresponding to each initial loan client by adopting a preset first prediction model according to the personal identity information and the initial loan application information;
acquiring monthly supply ratio data of each first credit client in a current first credit client set within a preset time period, and obtaining a second subsequent credit prediction probability corresponding to each first credit client by adopting a preset second prediction model according to the monthly supply ratio data;
obtaining a comprehensive continuous loan prediction probability corresponding to each first loan customer by adopting a preset third prediction model according to the first continuous loan prediction probability and the second continuous loan prediction probability;
and sequencing the first and second lending clients according to the comprehensive successive lending prediction probability corresponding to each first and second lending client to obtain a sequencing result, and pushing loan product information according to the sequencing result.
When the personal identity information and the initial loan application information of each initial loan client in the current initial loan client set are obtained, the loan data processing method, the loan data processing device, the computer equipment and the storage medium can obtain the first subsequent loan prediction probability corresponding to each initial loan client by adopting a preset first prediction model according to the personal identity information and the initial loan application information, obtain the second subsequent loan prediction probability corresponding to each initial loan client by adopting a preset second prediction model according to the monthly supply ratio data when the monthly supply ratio data of each initial loan client in the current initial loan client set in a preset time period is obtained, obtain the comprehensive subsequent loan prediction probability corresponding to each loan client by adopting a preset third prediction model according to the first subsequent loan prediction probability and the second subsequent loan prediction probability, and sort each initial loan client according to the comprehensive subsequent loan prediction probability corresponding to each loan client to obtain a sorting result, the loan product information is pushed according to the sequencing result, because two times of prediction are carried out from different dimensions, and the comprehensive prediction probability is obtained according to the results of the two times of prediction, the comprehensive probability can reflect the possibility of continuous loan of the client, and targeted pushing is carried out according to the possibility, so that a great amount of computer resources can be saved.
Drawings
FIG. 1 is a diagram illustrating an exemplary implementation of a loan data processing method;
FIG. 2 is a flow diagram illustrating a method of loan data processing, in accordance with one embodiment;
FIG. 3 is a flowchart illustrating the steps of the first predictive model generation of step S202, according to one embodiment;
FIG. 4 is a flowchart illustrating the steps of generating a second predictive model in step S206, according to one embodiment;
FIG. 5 is a flow chart illustrating a loan data processing method according to another embodiment;
FIG. 6 is a block diagram showing the construction of a loan data processing apparatus in one embodiment;
fig. 7 is a block diagram showing the construction of a loan data processing apparatus in another embodiment;
FIG. 8 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The loan data processing method provided by the application can be applied to the application environment shown in fig. 1. In the application environment, the system at least comprises a server 110, a marketing person terminal 120 and a loan client terminal 130, wherein the server 110 predicts the loan continuation probability of a loan client, pushes loan products to the loan client terminal 130 according to the prediction result, and simultaneously sends the prediction result to the marketing person terminal 120. Wherein the marketer terminal 120 communicates with the server 110 through a network, and the loan client terminal 130 communicates with the server 110 through a network. The marketer terminal 120 and the loan client terminal 130 may be, but are not limited to, various personal computers, notebook computers, smart phones, tablet computers and portable wearable devices, and the server 110 may be implemented by an independent server or a server cluster composed of a plurality of servers.
In one embodiment, as shown in fig. 2, a loan data processing method is provided, which is described by taking the method as an example applied to the server in fig. 1, and comprises the following steps:
step S202, acquiring personal identity information and offer application information of each offer client in the current offer client set, and obtaining a first continuation offer prediction probability corresponding to each offer client by adopting a preset first prediction model according to the personal identity information and the offer application information.
Specifically, the current set of lending clients refers to a set of lending clients who have loan behaviors on the loan platform within a preset time period before the current time, and if the current time is 1 month and 5 days, the current set of lending clients may be lending clients who have loan behaviors on the loan platform within 10 days of 12 months and 25 days to 1 month and 5 days. The first loan client refers to a client who has only performed a loan on the loan platform, the personal identity information includes age, gender, occupation, monthly income and the like, and the first loan application information refers to application information including loan amount and loan term when the loan platform performs a first loan.
In one embodiment, the server may collect loan data periodically, obtain a current set of lending clients according to the loan data, and obtain personal identity information and lending application information of each lending client in the current set of lending clients, for example, collect loan data every 10 days to obtain the current set of lending clients; in another embodiment, the server collects loan data in the current time period after receiving the request of the marketer terminal, for example, after receiving the request of the marketer terminal, collects loan data 10 days before the current time, obtains a current loan-originating client set according to the current loan data, and acquires the personal identity information and the loan-originating application information of each loan-originating client in the current loan-originating client set.
Further, the server inputs the acquired personal identity information of each loan client and the received application information into a preset first prediction model to obtain a first loan continuation prediction probability corresponding to each loan client. The first prediction model can be obtained by performing machine learning training on loan data of a client with continuous loan behavior stored in the server, wherein continuous loan refers to loan again on the same platform. In the model training, a supervised model training mode may be adopted, such as a regression tree model, a bayesian model, an SVM (Support Vector Machine), and so on.
In one embodiment, the server may rank each of the current set of lending clients according to the first lending continuation prediction probability to obtain a preliminary marketing priority order, and send a ranking result to the marketer terminal, and the marketer terminal may perform preliminary marketing according to the ranking result.
Step S204, acquiring monthly supply ratio data of each loan customer in the current loan customer set within a preset time period, and obtaining a second loan continuation prediction probability corresponding to each loan customer by adopting a preset second prediction model according to the monthly supply ratio data.
Specifically, the monthly payment ratio is a ratio of the monthly repayment amount to the total loan amount, and if the total amount of three-year loan is 10000, the repayment amount of the first month is 1000, and the repayment amount of the second month is 2000, the monthly payment ratio of the first month of three-year loan is 10%, and the repayment amount of the second month is 20%. The preset time period refers to a period of time from the first month of payment, which can be set in advance by the marketer according to a specific marketing condition, and generally includes a period of at least two months, such as three months, five months, and the like. The server acquires the monthly offer ratio data of each initial credit client in the current initial credit client set in the preset time period refers to the server acquiring the monthly offer ratio of each initial credit client in each month in the preset time period, for example, acquiring the monthly offer ratio of each month of each initial credit client in three consecutive months.
Further, in this embodiment, after obtaining the monthly offer ratio data of each offer client within the preset time period, the server inputs the monthly offer ratio data into a preset second prediction model to obtain a second continuation credit prediction probability corresponding to each offer client. Wherein the second prediction model can be obtained by performing machine learning training on loan data of the client with continuous loan behaviors, which is stored in the server. In the model training, a supervised model training mode may be adopted, such as a regression tree model, a bayesian model, an SVM (Support Vector Machine), and so on.
In one embodiment, after obtaining the second continuation credit prediction probability, the server may rank each of the first and second continuation credit clients in the current first and second continuation credit client sets according to the second continuation credit prediction probability to obtain a preliminary marketing priority order, and send the rank order to the marketer terminal, and the marketer terminal may perform preliminary marketing according to the rank order result.
And step S206, obtaining the comprehensive continuation credit prediction probability corresponding to each first credit customer by adopting a preset third prediction model according to the first continuation credit prediction probability and the second continuation credit prediction probability.
Specifically, the comprehensive loan continuation prediction probability is used for representing the possibility of carrying out loan continuation behaviors by each loan customer in the current loan customer set, and the higher the comprehensive loan continuation prediction probability is, the higher the possibility of carrying out loan continuation by the loan customer is represented. And the third prediction model is obtained by performing model training according to the training data and is used for predicting the continuous loan probability of each loan client in the current loan client set. In this embodiment, after obtaining the first continuation credit prediction probability and the second continuation credit prediction probability, the server inputs the first continuation credit prediction probability and the second continuation credit prediction probability into the third prediction model to obtain the comprehensive continuation credit prediction probability.
And S208, sequencing the first loan clients according to the comprehensive continuous loan prediction probability corresponding to the first loan clients to obtain a sequencing result, and pushing loan product information according to the sequencing result.
Specifically, the server may perform descending or ascending ranking on each loan client according to the comprehensive loan continuation probability corresponding to each loan client, so as to obtain a ranking result. Further, the server pushes loan product information to the loan client terminal according to the sequencing result, and when the sequencing result is in descending order, the client who is ranked in the preset range before 100 is selected to push loan products; when the sequencing result is in ascending order, selecting the customers in the preset range, such as the last 100 customers, to push loan products. The loan product may be a loan product currently pushed by the loan platform, a randomly pushed loan product, a loan product that the lending client has browsed once, or the like. In one embodiment, a threshold value of the comprehensive loan continuation prediction probability may be preset, and the loan continuation products are pushed only when the comprehensive loan continuation probability of the lending client is greater than the preset threshold value, so as to further save computer resources.
In one embodiment, some loan products may have marketing limits, for example, the marketing limit when some loan products are issued is 100w, users of the first loan client set may be further classified according to the ranking, if 300 clients exist, the clients ranked 1-100 are classified into the first category when the ranking is performed in a descending order, the clients ranked 101-.
Further, the server can send the obtained sequencing result to a terminal corresponding to the marketer. The server can send the sequencing result according to the sequencing result acquisition request after receiving the sequencing result acquisition request carrying the marketing staff user identification sent by the marketing staff terminal, and can also select the terminal corresponding to the pre-bound marketing staff user identification to send the sequencing result in real time after obtaining the sequencing result. After the marketing personnel terminal receives the sequencing result, the corresponding marketing personnel can selectively carry out marketing according to the sequencing result, so that the marketing success rate is improved.
In the loan data processing method, when personal identity information and loan application information of each loan customer in a current loan customer set are obtained, a preset first prediction model is adopted to obtain a first loan continuation prediction probability corresponding to each loan customer according to the personal identity information and the loan application information, when monthly supply ratio data of each loan customer in the current loan customer set in a preset time period is obtained, a preset second prediction model is adopted to obtain a second loan continuation prediction probability corresponding to each loan customer according to the monthly supply ratio data, then a preset third prediction model is adopted to obtain a comprehensive loan continuation prediction probability corresponding to each loan customer according to the first loan continuation prediction probability and the second loan continuation prediction probability, finally, the loan customers are sequenced according to the comprehensive loan continuation prediction probability corresponding to each loan customer to obtain a sequencing result, and loan product information is pushed according to the sequencing result, because the two predictions are carried out from different dimensions, and the comprehensive prediction probability is obtained according to the results of the two predictions, the comprehensive probability can reflect the possibility of continuous loan of the client, and targeted push is carried out according to the possibility, so that a large amount of computer resources can be saved.
In one embodiment, as shown in fig. 3, the generating step of the first prediction model in step S202 includes:
step S302, personal identity information, first loan application information and continuous loan probability of each loan customer in the historical loan customer set are obtained.
Step S304, a first training sample is obtained according to the personal identity information, the first loan application information and the loan continuation probability.
And S306, carrying out model training according to the first training sample to obtain a first prediction model.
Specifically, the historical loan client set refers to a set of clients who have performed a loan-first action before the current time period. Since the loan continuation result of each loan client in the historical loan client set is known, the personal identity information, the first loan application information and the loan continuation probability can be obtained as a first training sample, wherein the loan continuation probability of the loan client with the loan continuation behavior is 100%, and the loan continuation probability of the loan client without the loan continuation behavior is 0.
The first training sample is used for training the model to obtain a first prediction model through training. In the model training, a supervised model training mode may be adopted, such as a decision tree model, a logistic regression model, an SVM (support vector Machine), a bayesian model, and so on. The training samples can comprise positive samples and negative samples, when supervised model training is carried out, the personal identity information, the first loan application information and the loan probability corresponding to the loan clients with continuous loan behaviors form positive samples, and the personal identity information, the first loan application information and the loan probability corresponding to the loan clients without continuous loan behaviors form positive samples.
In this embodiment, the first prediction model is obtained by performing model training using the historical data of each loan client in the historical loan set as a training sample, so that the accuracy of prediction can be improved.
In one embodiment, the step of generating the second prediction model in step S204 includes: acquiring monthly supply ratio data of each loan client in a historical loan client set within a preset time period; obtaining a second training sample according to the monthly supply ratio data and the continuous loan probability; and carrying out model training according to the second training sample to obtain a second prediction model.
It should be noted that, in this embodiment, if learning is performed using all the data in the historical loan client set, an overfitting phenomenon is easily caused. Therefore, in one embodiment, cross-validation is considered when training the model. Cross-validation is a practical way to statistically cut a data sample into smaller subsets, where one subset can be analyzed first, while the other subset is used for subsequent validation and validation of the analysis. The first subset is called the training set, while the other subsets are called the validation set or test set. The goal of cross-validation is to define a data set to the model under test, during the training phase, in order to reduce the problem of over-fitting.
In one embodiment, as shown in fig. 4, the step of generating the third prediction model in step S206 includes:
and step S402, obtaining a first loan continuation prediction probability corresponding to each loan customer by adopting a preset first prediction model according to the personal identity information and the first loan application information of each loan customer in the historical loan customer set.
Specifically, after the server acquires the personal identity information and the first loan information of each loan customer in the historical loan customer set, the information is input into a trained first loan continuation prediction model to obtain the first loan continuation prediction probability corresponding to each loan customer.
And S404, obtaining a second loan continuation prediction probability corresponding to each loan customer in the historical loan customer set by adopting a preset second prediction model according to monthly supply ratio data of each loan customer in a preset time period.
Specifically, after acquiring the monthly offer ratio of each month in the preset time period of each loan customer in the historical loan customer set, the server inputs the monthly offer ratio data into the second prediction model to obtain the second loan continuation prediction probability corresponding to each customer. It can be understood that, in this embodiment, the preset time period is the same as the prediction time period when the second prediction model is trained, for example, when the second prediction model is trained, the data included in the training set is the monthly ratio of the previous three months, and when the second loan continuation prediction probability of each loan customer in the historical loan set is obtained, the obtained monthly ratio data is also the monthly ratio of the previous three months.
And step S406, obtaining a third training sample according to the first continuous loan prediction probability, the second continuous loan prediction probability and the continuous loan probability corresponding to each loan customer in the historical loan customer set, and performing model training according to the third training sample to obtain a third prediction model.
Further, since the continuous loan situation of each loan client in the historical loan client set is known, the model training may be performed according to the first continuous loan prediction probability, the second continuous loan prediction probability, and the continuous loan probability of each loan client as a training set to obtain a third prediction model, where the loan probability of the loan client with continuous loan behavior is 100%, and the continuous loan probability of the loan client without continuous loan behavior is summarized as 0.
In one embodiment, an initialized third prediction model Y of α may be set0+α1X1+α2X2Wherein Y represents the overall prediction probability, X1Representing a first prediction probability, X2Representing the second prediction probability. After the initialized prediction model is established, a training set for training and learning the initialized third prediction model is required to be established, existing customer data is substituted into the first prediction model and the second prediction model to obtain a first prediction probability and a second prediction probability, the first prediction probability, the second prediction probability and corresponding continuous loan results form a training set, and the initialized prediction model is subjected to model training by adopting a Machine learning algorithm so as to obtain corresponding coefficient values.
Taking SVM as an example, a random gradient algorithm may be used for model training, and the cost function J (θ) needs to be minimized in the gradient descent process, and in one embodiment, the cost function may be represented by the following formula:
is shown byIn m denotes the number of sample features, x(i)To input, y(i)The value representing the integrated prediction probability in the training samples, the positive sample may be set to 1 and the negative sample may be set to-1. h isθ(x(i)) The output value of each training is represented, wherein,
wherein the content of the first and second substances,
i.e. thetaTx is equal to the sum of the products of the features and the parameters.
In this embodiment, the second prediction model is obtained by performing model training using the historical data of each loan client in the historical loan set as a training sample, so that the accuracy of prediction can be improved.
In one embodiment, as shown in fig. 5, step S208 includes:
and step S502, obtaining a loan continuation client set according to the historical loan client set.
The loan continuation client set refers to a set formed by clients with loan continuation behaviors.
And step S504, selecting the loan clients from the current loan client set as current target clients according to the sorting result.
Specifically, since the ranking result is ranked according to the magnitude of the comprehensive continuation credit prediction probability, after ranking, the server may sequentially select, according to the ranking result, the client with the highest comprehensive continuation credit prediction probability as the current target client, for example, when the ranking result is in a descending order, the first 100 clients are sequentially selected as the current target clients from the client with the first ranking.
Step S506, mapping the current target customer and each loan continuation customer in the loan continuation customer set to a multidimensional vector space using the loan information and the identity information as coordinates, and obtaining a vector coordinate of the current target customer and a vector coordinate corresponding to each loan continuation customer, respectively.
Specifically, the first loan information is various loan information and repayment information of the client during the first loan. In one embodiment, the loan origination information includes an amount of the loan origination, and a number of repayment options. The identity information includes age, gender, monthly income, and the like. In this embodiment, each dimension in the multidimensional vector space with the loan lead information and the identity information as coordinates represents a different piece of information, the server maps each client in the current target client and the loan continuation client set to the multidimensional vector space with the loan lead information and the identity information as coordinates, each client uniquely corresponds to one space vector, the space vector takes the origin as the starting point, and therefore, the vector coordinates can be represented by the coordinates of the end point. It can be understood that the dimensions of the vector space and the information corresponding to each dimension can be set in advance as required, and the more the dimensions are, the more accurate the obtained customer information represented by the space vector is.
In one embodiment, when the vector space is a three-dimensional vector space with the loan amount, the payment period, and the age as the x-axis, the y-axis, and the z-axis, respectively, the obtained vector coordinates corresponding to each client are (x, y, and z), and if the loan amount of the target client is 100000, the payment period is 5, and the age is 30, the vector coordinates corresponding to the client are (100000,5, 30).
Step S508, calculating a vector distance between the current target client and each loan continuation client in the loan continuation client set.
Specifically, the vector distance can be calculated by: let the continuation credit customer have vector coordinates of (x)1，y1，z1… …), the vector coordinate of the target customer is (x)2，y2，z2… …), then the vector distance is:
and step S510, taking the corresponding loan continuation client when the vector distance is smaller than the preset value as a reference object of the current target client to obtain a reference object set, and pushing loan product information according to the reference object set.
Specifically, there may be a plurality of loan continuation clients whose vector distance to the target client is smaller than a preset value, and the loan continuation clients are used as reference objects of the target client to obtain a reference object set, and loan products are pushed to the target client according to the reference object set.
In one embodiment, pushing the loan product to the target customer based on the set of reference objects comprises: inquiring the continuous loan products of each reference object in the reference object set to obtain a continuous loan product set; acquiring the reference object quantity corresponding to each continuous loan product in the continuous loan product set; and obtaining the target push product according to the reference object quantity corresponding to each continuous loan product.
In this embodiment, the server queries the continuous loan products of each reference object in the reference object set from the stored historical data to obtain a continuous loan product set, counts the continuous loan number corresponding to each continuous loan product in the continuous loan product set, and selects the continuous loan product with the largest continuous loan number as the target push product. When the number of the continuous loan products with the largest continuous loan number is more than 1, all the continuous loan products can be used as target push products, and one continuous loan product can be randomly selected to be used as a target push product.
Further, the server acquires a user identifier corresponding to the target client and pushes the target pushed product information to a terminal corresponding to the user identifier.
In the embodiment, the reference object is determined, and then the loan continuation products of the reference object are counted to obtain the loan continuation products with the largest number of loan continuation persons as the target push products, so that the loan products can be pushed in a targeted manner, and the marketing hit rate of the server in pushing the loan products can be improved.
It should be understood that although the various steps in the flow charts of fig. 2-5 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-5 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternating with other steps or at least some of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 6, there is provided a loan data processing apparatus 600 comprising: a first continuation credit prediction probability obtaining module 602, a second continuation credit prediction probability obtaining module 604, a comprehensive continuation credit prediction probability module 606, and a ranking module 608, wherein: a first continuation credit prediction probability obtaining module 602, configured to obtain personal identity information and first credit application information of each benefit credit client in a current benefit credit client set, and obtain a first continuation credit prediction probability corresponding to each benefit credit client by using a preset first prediction model according to the personal identity information and the first credit application information; a second continuation credit prediction probability obtaining module 604, configured to obtain monthly supply ratio data of each benefit client in the current benefit client set in a preset time period, and obtain a second continuation credit prediction probability corresponding to each benefit client according to the monthly supply ratio data by using a preset second prediction model; the comprehensive continuation credit prediction probability module 606 is configured to obtain a comprehensive continuation credit prediction probability corresponding to each first credit customer by using a preset third prediction model according to the first continuation credit prediction probability and the second continuation credit prediction probability; and the sorting module 608 is configured to sort the lending clients according to the comprehensive lending continuation prediction probabilities corresponding to the lending clients to obtain sorting results, and push loan product information according to the sorting results.
In one embodiment, the above apparatus further comprises: the first prediction model establishing module is used for obtaining the personal identity information, the first loan application information and the continuous loan probability of each loan customer in the historical loan customer set, obtaining a first training sample according to the personal identity information, the first loan application information and the continuous loan probability, and carrying out model training according to the first training sample to obtain a first prediction model.
In one embodiment, the above apparatus further comprises: and the second prediction model establishing module is used for acquiring monthly supply ratio data of each loan client in the historical loan client set within a preset time period, obtaining a second training sample according to the monthly supply ratio data and the loan continuation probability, and performing model training according to the second training sample to obtain a second prediction model.
In one embodiment, the above apparatus further comprises: the third prediction model establishing module is used for obtaining a first loan continuation prediction probability corresponding to each loan client by adopting a preset first prediction model according to the personal identity information and the first loan application information of each loan client in the historical loan client set, obtaining a second loan continuation prediction probability corresponding to each loan client by adopting a preset second prediction model according to monthly offer ratio data of each loan client in the historical loan client set within a preset time period, obtaining a third training sample according to the first loan continuation prediction probability, the second loan continuation prediction probability and the loan continuation probability corresponding to each loan client in the historical loan client set, and performing model training according to the third training sample to obtain a third prediction model.
In one embodiment, as shown in fig. 7, the above apparatus further comprises: a loan continuation client set obtaining module 702, configured to obtain a loan continuation client set according to the historical loan client set; a target client selecting module 704, configured to select a loan client from the current loan client set as a current target client according to the sorting result; a vector coordinate obtaining module 706, configured to map the current target client and each credit continuation client in the credit continuation client set to a multidimensional vector space with the credit information and the identity information as coordinates, and obtain a vector coordinate of the current target client and a vector coordinate corresponding to each credit continuation client respectively; a vector distance calculation module 708, configured to calculate a vector distance between the current target client and each loan continuation client in the loan continuation client set; and the reference object set obtaining module 710 is configured to take the corresponding loan continuation client when the vector distance is smaller than the preset value as a reference object of the current target client, obtain a reference object set, and push loan product information according to the reference object set.
In one embodiment, the above apparatus further comprises: and the target push product acquisition module is used for inquiring the continuous credit products of each reference object in the reference object set to obtain a continuous credit product set, acquiring the reference object quantity corresponding to each continuous credit product in the continuous credit product set, and acquiring the target push product according to the reference object quantity corresponding to each continuous credit product.
In one embodiment, the above apparatus further comprises: and the product pushing module is used for pushing the target pushed product to a terminal corresponding to the current target client.
For the detailed definition of the loan data processing apparatus, reference may be made to the above definition of the loan data processing method, which is not described herein again. The various modules in the loan data processing apparatus described above may be implemented in whole or in part by software, hardware, and combinations thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 8. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used to store loan data processing data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a loan data processing method.
Those skilled in the art will appreciate that the architecture shown in fig. 8 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program: acquiring personal identity information and initial credit application information of each initial credit client in a current initial credit client set, and acquiring a first subsequent credit prediction probability corresponding to each initial credit client by adopting a preset first prediction model according to the personal identity information and the initial credit application information; acquiring monthly supply ratio data of each first credit client in the current first credit client set within a preset time period, and obtaining a second subsequent credit prediction probability corresponding to each first credit client by adopting a preset second prediction model according to the monthly supply ratio data; obtaining a comprehensive continuous loan prediction probability corresponding to each first loan customer by adopting a preset third prediction model according to the first continuous loan prediction probability and the second continuous loan prediction probability; and sequencing the first loan clients according to the comprehensive loan continuation prediction probability corresponding to the first loan clients to obtain a sequencing result, and pushing loan product information according to the sequencing result.
In one embodiment, the processor, when executing the computer program, further performs the steps of: acquiring personal identity information, first loan application information and continuous loan probability of each loan customer in a historical loan customer set; obtaining a first training sample according to the personal identity information, the first loan application information and the loan continuation probability; and carrying out model training according to the first training sample to obtain a first prediction model.
In one embodiment, the processor, when executing the computer program, further performs the steps of: acquiring monthly supply ratio data of each loan client in a historical loan client set within a preset time period; obtaining a second training sample according to the monthly supply ratio data and the continuous loan probability; and carrying out model training according to the second training sample to obtain a second prediction model.
In one embodiment, the processor, when executing the computer program, further performs the steps of: obtaining a first loan continuation prediction probability corresponding to each loan customer by adopting a preset first prediction model according to the personal identity information and the first loan application information of each loan customer in the historical loan customer set; obtaining a second loan continuation prediction probability corresponding to each loan customer by adopting a preset second prediction model according to monthly offer ratio data of each loan customer in the historical loan customer set within a preset time period; and obtaining a third training sample according to the first continuous loan prediction probability, the second continuous loan prediction probability and the continuous loan probability corresponding to each loan customer in the historical loan customer set, and performing model training according to the third training sample to obtain a third prediction model.
In one embodiment, the processor, when executing the computer program, further performs the steps of: obtaining a loan continuation client set according to the historical loan client set; selecting a first loan client from the current first loan client set as a current target client according to the sorting result; mapping the current target customer and each credit continuation customer in the credit continuation customer set to a multidimensional vector space with the credit first information and the identity information as coordinates, and respectively obtaining the vector coordinates of the current target customer and the vector coordinates corresponding to each credit continuation customer; calculating the vector distance between the current target client and each continuous loan client in the continuous loan client set; and taking the corresponding loan continuation client when the vector distance is smaller than the preset value as a reference object of the current target client to obtain a reference object set, and pushing loan product information according to the reference object set.
In one embodiment, the processor, when executing the computer program, further performs the steps of: inquiring the continuous loan products of each reference object in the reference object set to obtain a continuous loan product set; acquiring the reference object quantity corresponding to each continuous loan product in the continuous loan product set; and obtaining the target push product according to the reference object quantity corresponding to each continuous loan product.
In one embodiment, the processor, when executing the computer program, further performs the steps of: and pushing the target push product to a terminal corresponding to the current target customer.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of: acquiring personal identity information and initial credit application information of each initial credit client in a current initial credit client set, and acquiring a first subsequent credit prediction probability corresponding to each initial credit client by adopting a preset first prediction model according to the personal identity information and the initial credit application information; acquiring monthly supply ratio data of each first credit client in the current first credit client set within a preset time period, and obtaining a second subsequent credit prediction probability corresponding to each first credit client by adopting a preset second prediction model according to the monthly supply ratio data; obtaining a comprehensive continuous loan prediction probability corresponding to each first loan customer by adopting a preset third prediction model according to the first continuous loan prediction probability and the second continuous loan prediction probability; and sequencing the first loan clients according to the comprehensive loan continuation prediction probability corresponding to the first loan clients to obtain a sequencing result, and pushing loan product information according to the sequencing result.
In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring personal identity information, first loan application information and continuous loan probability of each loan customer in a historical loan customer set; obtaining a first training sample according to the personal identity information, the first loan application information and the loan continuation probability; and carrying out model training according to the first training sample to obtain a first prediction model.
In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring monthly supply ratio data of each loan client in a historical loan client set within a preset time period; obtaining a second training sample according to the monthly supply ratio data and the continuous loan probability; and carrying out model training according to the second training sample to obtain a second prediction model.
In one embodiment, the computer program when executed by the processor further performs the steps of: obtaining a first loan continuation prediction probability corresponding to each loan customer by adopting a preset first prediction model according to the personal identity information and the first loan application information of each loan customer in the historical loan customer set; obtaining a second loan continuation prediction probability corresponding to each loan customer by adopting a preset second prediction model according to monthly offer ratio data of each loan customer in the historical loan customer set within a preset time period; and obtaining a third training sample according to the first continuous loan prediction probability, the second continuous loan prediction probability and the continuous loan probability corresponding to each loan customer in the historical loan customer set, and performing model training according to the third training sample to obtain a third prediction model.
In one embodiment, the computer program when executed by the processor further performs the steps of: obtaining a loan continuation client set according to the historical loan client set; selecting a first loan client from the current first loan client set as a current target client according to the sorting result; mapping the current target customer and each credit continuation customer in the credit continuation customer set to a multidimensional vector space with the credit first information and the identity information as coordinates, and respectively obtaining the vector coordinates of the current target customer and the vector coordinates corresponding to each credit continuation customer; calculating the vector distance between the current target client and each continuous loan client in the continuous loan client set; and taking the corresponding loan continuation client when the vector distance is smaller than the preset value as a reference object of the current target client to obtain a reference object set, and pushing loan product information according to the reference object set.
In one embodiment, the computer program when executed by the processor further performs the steps of: inquiring the continuous loan products of each reference object in the reference object set to obtain a continuous loan product set; acquiring the reference object quantity corresponding to each continuous loan product in the continuous loan product set; and obtaining the target push product according to the reference object quantity corresponding to each continuous loan product.
In one embodiment, the computer program when executed by the processor further performs the steps of: and pushing the target push product to a terminal corresponding to the current target customer.
It will be understood by those of ordinary skill in the art that all or a portion of the processes of the methods of the embodiments described above may be implemented by a computer program that may be stored on a non-volatile computer-readable storage medium, which when executed, may include the processes of the embodiments of the methods described above, wherein any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A method of loan data processing, the method comprising:
acquiring personal identity information and initial loan application information of each initial loan client in a current initial loan client set, and acquiring a first continuous loan prediction probability corresponding to each initial loan client by adopting a preset first prediction model according to the personal identity information and the initial loan application information;
acquiring monthly supply ratio data of each first credit client in a current first credit client set within a preset time period, and obtaining a second subsequent credit prediction probability corresponding to each first credit client by adopting a preset second prediction model according to the monthly supply ratio data;
obtaining a comprehensive continuous loan prediction probability corresponding to each first loan customer by adopting a preset third prediction model according to the first continuous loan prediction probability and the second continuous loan prediction probability;
and sequencing the first and second lending clients according to the comprehensive successive lending prediction probability corresponding to each first and second lending client to obtain a sequencing result, and pushing loan product information according to the sequencing result.
2. The method of claim 1, wherein the step of generating the first predictive model comprises:
acquiring personal identity information, first loan application information and continuous loan probability of each loan customer in a historical loan customer set; wherein, the continuous loan probability of the loan clients with continuous loan behaviors is 100 percent, and the continuous loan probability of the loan clients without continuous loan behaviors is 0;
obtaining a first training sample according to the personal identity information, the first loan application information and the loan continuation probability;
and carrying out model training according to the first training sample to obtain a first prediction model.
3. The method of claim 2, wherein the step of generating the second predictive model comprises:
acquiring monthly supply ratio data of each loan client in a historical loan client set within a preset time period;
obtaining a second training sample according to the monthly supply ratio data and the continuous loan probability;
and carrying out model training according to the second training sample to obtain a second prediction model.
4. The method of claim 3, wherein the step of generating the third predictive model comprises:
obtaining a first loan continuation prediction probability corresponding to each loan customer by adopting a preset first prediction model according to the personal identity information and the first loan application information of each loan customer in the historical loan customer set;
obtaining a second loan continuation prediction probability corresponding to each loan customer in the historical loan customer set by adopting a preset second prediction model according to monthly supply ratio data of each loan customer in a preset time period;
and obtaining a third training sample according to the first continuous loan prediction probability, the second continuous loan prediction probability and the continuous loan probability corresponding to each loan customer in the historical loan customer set, and performing model training according to the third training sample to obtain a third prediction model.
5. The method according to any one of claims 2 to 4, wherein the step of ranking the individual lending clients according to the comprehensive lending continuation prediction probabilities corresponding to the individual lending clients to obtain a ranking result, and the step of pushing loan product information according to the ranking result comprises:
obtaining a loan continuation client set according to the historical loan client set;
selecting a loan client from the current loan client set as a current target client according to the sorting result;
mapping the current target customer and each credit continuation customer in the credit continuation customer set to a multidimensional vector space with the credit first information and the identity information as coordinates, and respectively obtaining the vector coordinates of the current target customer and the vector coordinates corresponding to each credit continuation customer;
calculating the vector distance between the current target client and each continuous loan client in the continuous loan client set;
taking the corresponding continuous credit customer when the vector distance is smaller than the preset value as a reference object of the current target customer to obtain a reference object set;
and pushing loan product information according to the reference object set.
6. The method of claim 5, wherein the step of pushing loan product information according to the reference object set comprises:
inquiring the continuous loan products of each reference object in the reference object set to obtain a continuous loan product set;
acquiring the reference object quantity corresponding to each continuous loan product in the continuous loan product set;
and obtaining a target pushed product corresponding to the current target client according to the reference object quantity corresponding to each continuous loan product in the continuous loan product set.
7. The method of claim 6, further comprising:
and pushing the target push product to a terminal corresponding to the current target customer.
8. A loan data processing apparatus, characterized in that the apparatus comprises:
the first continuation credit prediction probability acquisition module is used for acquiring personal identity information and first credit application information of each first credit client in the current first credit client set, and acquiring a first continuation credit prediction probability corresponding to each first credit client by adopting a preset first prediction model according to the personal identity information and the first credit application information;
the second continuation credit prediction probability obtaining module is used for obtaining monthly supply ratio data of each benefit credit client in the current benefit credit client set in a preset time period, and obtaining second continuation credit prediction probabilities corresponding to the benefit credit clients by adopting a preset second prediction model according to the monthly supply ratio data;
the comprehensive continuation credit prediction probability module is used for obtaining the comprehensive continuation credit prediction probability corresponding to each first credit customer by adopting a preset third prediction model according to the first continuation credit prediction probability and the second continuation credit prediction probability;
and the sequencing module is used for sequencing each loan client according to the comprehensive loan continuation prediction probability corresponding to each loan client to obtain a sequencing result, and pushing loan product information according to the sequencing result.
9. 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 steps of the method of any of claims 1 to 7 are implemented when the computer program is executed by the processor.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810091577.6A CN108182633B (en) | 2018-01-30 | 2018-01-30 | Loan data processing method, loan data processing device, loan data processing program, and computer device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810091577.6A CN108182633B (en) | 2018-01-30 | 2018-01-30 | Loan data processing method, loan data processing device, loan data processing program, and computer device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108182633A CN108182633A (en) | 2018-06-19 |
| CN108182633B true CN108182633B (en) | 2020-08-04 |
Family
ID=62551877
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810091577.6A Active CN108182633B (en) | 2018-01-30 | 2018-01-30 | Loan data processing method, loan data processing device, loan data processing program, and computer device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108182633B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109165983A (en) * | 2018-09-04 | 2019-01-08 | 中国平安人寿保险股份有限公司 | Insurance products recommended method, device, computer equipment and storage medium |
| CN111582898A (en) * | 2019-02-18 | 2020-08-25 | 北京奇虎科技有限公司 | Data processing method, device, equipment and storage medium |
| CN110321393A (en) * | 2019-06-28 | 2019-10-11 | 深圳前海微众银行股份有限公司 | Method for computing data, device, equipment and readable storage medium storing program for executing |
| CN112116405B (en) * | 2020-09-29 | 2024-02-02 | 中国银行股份有限公司 | Data processing method, device, electronic equipment and medium |
| CN112541817A (en) * | 2020-12-22 | 2021-03-23 | 建信金融科技有限责任公司 | Marketing response processing method and system for potential customers of personal consumption loan |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104978689A (en) * | 2015-06-19 | 2015-10-14 | 徐晓晖 | Stock market combination characteristic based network loan risk quantitative analysis method |
| CN106600369A (en) * | 2016-12-09 | 2017-04-26 | 广东奡风科技股份有限公司 | Real-time recommendation system and method of financial products of banks based on Naive Bayesian classification |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7805363B2 (en) * | 2008-03-28 | 2010-09-28 | American Express Travel Related Services Company, Inc. | Consumer behaviors at lender level |
-
2018
- 2018-01-30 CN CN201810091577.6A patent/CN108182633B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104978689A (en) * | 2015-06-19 | 2015-10-14 | 徐晓晖 | Stock market combination characteristic based network loan risk quantitative analysis method |
| CN106600369A (en) * | 2016-12-09 | 2017-04-26 | 广东奡风科技股份有限公司 | Real-time recommendation system and method of financial products of banks based on Naive Bayesian classification |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108182633A (en) | 2018-06-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108182633B (en) | Loan data processing method, loan data processing device, loan data processing program, and computer device and storage medium | |
| CN112148987B (en) | Message pushing method based on target object activity and related equipment | |
| CN109902753B (en) | User recommendation model training method and device, computer equipment and storage medium | |
| CN109829020B (en) | Method and device for pushing place resource data, computer equipment and storage medium | |
| CN110598845A (en) | Data processing method, data processing device, computer equipment and storage medium | |
| CN109245996B (en) | Mail pushing method and device, computer equipment and storage medium | |
| CN111178949B (en) | Service resource matching reference data determining method, device, equipment and storage medium | |
| US11748452B2 (en) | Method for data processing by performing different non-linear combination processing | |
| CN112163963B (en) | Service recommendation method, device, computer equipment and storage medium | |
| CN110888911A (en) | Sample data processing method and device, computer equipment and storage medium | |
| CN112258238A (en) | User life value cycle detection method and device and computer equipment | |
| CN115730125A (en) | Object identification method and device, computer equipment and storage medium | |
| CN112887371A (en) | Edge calculation method and device, computer equipment and storage medium | |
| CN111291795A (en) | Crowd characteristic analysis method and device, storage medium and computer equipment | |
| CN112116393B (en) | Method, device and equipment for realizing event user maintenance | |
| CN114925275A (en) | Product recommendation method and device, computer equipment and storage medium | |
| CN113779116A (en) | Object sorting method, related equipment and medium | |
| CN112131607B (en) | Resource data processing method and device, computer equipment and storage medium | |
| CN114330929B (en) | Content contribution evaluation method, device, electronic equipment and readable storage medium | |
| CN114676167B (en) | User persistence model training method, user persistence prediction method and device | |
| CN116611506B (en) | User analysis model training method, user label determining method and device | |
| CN113792342B (en) | Desensitization data reduction method, device, computer equipment and storage medium | |
| CN114048392B (en) | Multimedia resource pushing method and device, electronic equipment and storage medium | |
| CN111818114B (en) | Information sharing method and device | |
| CN113313587A (en) | Credit risk analysis method, device, equipment and medium based on artificial intelligence |
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 |