CN119515514A - A deposit-free online rental method and system - Google Patents

A deposit-free online rental method and system Download PDF

Info

Publication number
CN119515514A
CN119515514A CN202411579641.7A CN202411579641A CN119515514A CN 119515514 A CN119515514 A CN 119515514A CN 202411579641 A CN202411579641 A CN 202411579641A CN 119515514 A CN119515514 A CN 119515514A
Authority
CN
China
Prior art keywords
user
new
lease
leasing
credit risk
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202411579641.7A
Other languages
Chinese (zh)
Inventor
李耿
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Wuhan Junuo Technology Co ltd
Original Assignee
Wuhan Junuo Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Wuhan Junuo Technology Co ltd filed Critical Wuhan Junuo Technology Co ltd
Priority to CN202411579641.7A priority Critical patent/CN119515514A/en
Publication of CN119515514A publication Critical patent/CN119515514A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0645—Rental transactions; Leasing transactions
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; 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)
  • Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Development Economics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Educational Administration (AREA)
  • Tourism & Hospitality (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Game Theory and Decision Science (AREA)
  • Technology Law (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

本申请提供一种免押金线上租赁方法及系统，涉及线上租赁技术领域，免押金线上租赁方法包括以下步骤：通过神经网络模型对历史租赁用户的个人数据进行训练学习；向训练学习后的神经网络模型输入新租赁用户的个人数据，并根据输出结果确定新租赁用户的第一信用风险评估预测结果，历史租赁用户及新租赁用户的个人数据包括个人标识信息数据、个人基本资料数据、个人信用资料数据和个人家庭资料数据；为新租赁用户匹配可供租赁的手机机型。本申请的免押金线上租赁方法中信用风险评估预测所采用的新租赁用户个人数据相对于传统免押金租赁方法更为全面，从而有效提高了新租赁用户信用风险评估预测结果的准确性。

The present application provides a deposit-free online rental method and system, which relates to the field of online rental technology. The deposit-free online rental method includes the following steps: training and learning the personal data of historical rental users through a neural network model; inputting the personal data of new rental users into the trained neural network model, and determining the first credit risk assessment prediction result of the new rental user based on the output result. The personal data of historical rental users and new rental users include personal identification information data, personal basic information data, personal credit information data, and personal family information data; matching mobile phone models available for rental for new rental users. The personal data of new rental users used in the credit risk assessment prediction in the deposit-free online rental method of the present application is more comprehensive than that of the traditional deposit-free rental method, thereby effectively improving the accuracy of the credit risk assessment prediction results of new rental users.

Description

Deposit-free online leasing method and system
Technical Field
The application relates to the technical field of online leasing, in particular to a deposit-free online leasing method and a deposit-free online leasing system.
Background
Along with the continuous expansion of the demand of online leasing business, the application of the deposit-free leasing technology is more and more extensive, and simultaneously, along with the rapid iteration of the smart phone technology, new mobile phones are continuously promoted and become new, and the demand of users for trying new mobile phones is increasingly increased, so that the development of the deposit-free leasing online mode of the mobile phones is promoted. For example, CN115587872a published patent application discloses an online leasing method based on a blockchain, which receives leasing requirement information of leasing on a user line, marks and determines a leasing target, loads and determines an intelligent contract corresponding to the leasing target based on a blockchain technology, tracks signing and payment processes of a user to generate a signed contract, performs fulfillment verification according to the signed contract when the online leasing expires, performs deposit refund processing according to the fulfillment verification result, and completes an online leasing process of a mobile phone.
In the mobile phone online leasing process, the credit of the leasing user needs to be evaluated, so that the risk of bad leasing behaviors is reduced, and the stability of mobile phone online escort leasing is improved. For example, the invention patent with publication number CN 117474640B discloses a deposit-free leasing method, which comprises the steps of obtaining deposit-free leasing comprehensive data, constructing a deposit-free leasing comprehensive evaluation model according to the deposit-free leasing comprehensive data, obtaining deposit-free leasing comprehensive evaluation coefficient data calculated by the deposit-free leasing comprehensive evaluation model, and evaluating the credit of a leasing user.
However, in the above-mentioned escort renting method, when the credit of the rented user is evaluated, the relevant data is extracted by collecting the relevant data of the credit evaluation of the rented user in the escort renting, so as to obtain the credit evaluation data set of the rented user. The collected related data only comprises the credit scoring data of the leasing user, the overdue times data of the leasing user and the identity authenticity data of the leasing user, so that the collected data is single-sided, the problem of low accuracy of the client credit risk state obtained based on the evaluation prediction is solved, and the risk of bad leasing behaviors is increased.
Disclosure of Invention
The application aims to provide a method and a system for leasing a deposit-free line, which are used for solving the problem that the deposit-free leasing method in the related technology is low in accuracy of evaluating and predicting the credit risk state of a client.
In a first aspect, the present application provides a method for leasing a deposit-free line, which adopts the following technical scheme:
an on-line leasing method for a escort comprises the following steps:
collecting personal data and lease violations of historical lease users;
Training and learning personal data of a history leasing user through a neural network model, adjusting the link weight among neurons of each component of the neural network model, and determining the internal relation between the personal data and leasing default conditions;
collecting personal data of a new leasing user, inputting the personal data of the new leasing user into the neural network model after training and learning, and determining a first credit risk assessment prediction result of the new leasing user according to an output result, wherein the personal data of the historical leasing user and the new leasing user comprise personal identification information data, personal basic data, personal credit data and personal family data;
and receiving the lease requirement of the new lease user, matching the mobile phone model available for lease for the new lease user, and generating a lease order according to the selection of the new lease user.
Optionally, the personal identification information data comprises name, gender, ethnicity, native place and date of birth data, the personal basic data comprises academic, marital, housing, transportation means, work units, working time, professional property, job level, job title and time of getting job title data, the personal credit data comprises application program credit score, annual income, credit card, securities, bank deposit and insurance data, and the personal family data comprises family number, age composition, employment status and social insurance participation status data.
Optionally, setting a threshold value of the number of samples of the historical leasing users in the neural network model, after the number of samples of the historical leasing users reaches the threshold value, removing a group of samples of the historical leasing users before training and learning personal data of the historical leasing users through the neural network model each time, and selecting the removed samples of the historical leasing users according to the priority that the personal data lacks key information, the personal data information perfection is lowest, and the historical leasing users last long.
Optionally, receiving the lease demand of the new lease user, and matching the mobile phone model for lease for the new lease user comprises the following steps of constructing a user portrait according to the purchase history, browsing behavior and evaluation feedback information of the new lease user, analyzing the lease preference of the new lease user according to the lease demand of the new lease user through a cluster analysis and association rule method, and generating a mobile phone model list matched with the new lease user through collaborative filtering and a content-based recommendation algorithm.
Optionally, the functional expression of the neural network model is:
Error function extraction
Wherein, net jt is the input of the jth neuron of the t layer, y jt is the output of the jth neuron of the t layer, x i is the output of the ith neuron of the t-1 layer to the jth neuron of the t layer, w ij is the link weight between the ith neuron of the t-1 layer and the jth neuron of the t layer, y pm' is the target output, y pm is the actual output, θ jt is the output threshold of the jth neuron of the t layer, MSE is the mean square error between the output value of the neural network model and the expected value of the sample, P is the number of training samples, and M is the output node;
The training learning is carried out on the personal data of the historical leasing user through the neural network model, and the link weight among the neurons of each component of the neural network model is adjusted, which comprises the following steps:
Carrying out normalization processing on personal data of the historical leasing user, converting the personal data of the historical leasing user into sample data with unified standards, inputting the sample data into a neural network model, and calculating output of the neural network model;
and calculating a mean square error MSE between the output value and the sample expected value in the neural network model, then reversely calculating from the output layer to the input layer, adjusting each link weight w towards the direction of reducing the mean square error MSE, and terminating training when the mean square error MSE is smaller than a given allowable output threshold value theta.
Optionally, the normalization processing is performed on the personal data of the historical rental user, and the step of converting the personal data of the historical rental user into the sample data with unified standards comprises the steps of giving different numerical values in the range of [0,1] to each piece of personal data according to the influence degree of the non-numerical data on the personal credit evaluation in actual work, and converting the numerical data into numerical values distributed in the range of (0, 1) through normal distribution S function.
Optionally, after personal data of the new leasing user is input to the neural network model after training and learning and an output result is calculated, calculating a leasing default rate of the new leasing user through a verification unit, determining a second credit risk assessment prediction result of the new leasing user, if the second credit risk assessment prediction result is identical to the first credit risk assessment prediction result, matching a mobile phone model for the new leasing user for leasing according to the first credit risk assessment prediction result, otherwise, calculating a third credit risk assessment prediction result of the new leasing user through a rechecking unit, and selecting one of the first credit risk assessment prediction result and the second credit risk assessment prediction result, which is identical to the third credit risk assessment prediction result, as a basis for matching the mobile phone model for the new leasing user.
Optionally, the verification unit calculates the lease violations of the new lease user by substituting the personal data of the history lease user into the Logit prediction model, selecting the optimal personal data weight according to the SPSS software, substituting the personal data of the new lease user into the Logit distribution function, and calculating the lease violations of the new lease user;
the Logit prediction model is:
logitP=a0+a1y1+a2y2+...+amym,
Wherein P is the lease violation rate of the history leasing user, y 1,y2,...,ym is the personal data of the history leasing user, and a 0,a1,...,am is the personal data weight;
the Logit distribution function is:
Where P is the lease violation rate of the new lease subscriber, y 1,y2,...,ym is the personal data of the new lease subscriber, and a 0,a1,...,am is the optimal personal data weight selected according to the SPSS software.
Optionally, the calculating, by the rechecking unit, the third credit risk assessment prediction result of the new rental user includes the following steps:
Let the credit risk assessment discriminant function be y=c 1X1+C2X2+...+CpXp,
Wherein Y is a credit risk assessment index, X 1,X2,...,XP is personal data of a leasing user, and C 1,C2,...,CP is personal data weight;
Dividing historical leasing user samples into two groups according to credit risk assessment preference and difference, wherein one group of the credit risk assessment preference is group A, the number of samples is group n 1, and the average credit risk assessment index is The group of credit risk assessment differences is group B, the sample number is group n 2, and the average credit risk assessment index is
Calculating a weighted average of the average credit risk assessment indicators Y c:
Substituting personal data X 0 1,X0 2,...,X0 P of the new leasing user into the credit risk assessment discriminant function to obtain the credit risk assessment index of the new leasing user:
Y0＝C1X0 1+C2X0 2+...+CpX0 p;
When (when) If Y 0>Yc, the credit risk of the new leasing user is evaluated to be good, and if Y 0<Yc, the credit risk of the new leasing user is evaluated to be bad;
When (when) If Y 0<Yc, the credit risk of the new rental user is evaluated as excellent, and if Y 0>Yc, the credit risk of the new rental user is evaluated as poor.
In a second aspect, the present application provides a system for renting on-line free deposit, which adopts the following technical scheme:
a deposit-free online rental system, comprising:
The information collection unit is used for collecting personal data and lease violations of historical lease users;
The first credit risk assessment prediction unit is used for training and learning the personal data of the historical leasing user through the neural network model, collecting the personal data of the new leasing user and calculating a first credit risk assessment prediction result of the new leasing user;
the lease matching unit is used for receiving lease requirements of the new lease user, matching mobile phone models available for lease for the new lease user, and generating lease orders according to the selection of the new lease user.
In summary, the application at least comprises the following beneficial technical effects:
1. According to the deposit-free online leasing method, training and learning are carried out on personal data of a history leasing user through the neural network model, the personal data of a new leasing user is input into the neural network model after training and learning, and a first credit risk assessment prediction result of the new leasing user is determined according to an output result, so that a mobile phone model for leasing can be matched for the new leasing user. Because the personal data of the historical leasing user and the new leasing user comprise personal identification information data, personal basic data, personal credit data and personal family data, the credit risk assessment prediction method for the escort online leasing method provided by the application has the advantages that the personal data of the new leasing user adopted by credit risk assessment prediction is more comprehensive compared with the traditional escort lease method, meanwhile, the internal connection between the personal data of the historical leasing user and the leasing default situation is deeply mined through a neural network model, and a reliable basis is provided for the credit risk assessment prediction of the new leasing user, so that the accuracy of the credit risk assessment prediction result of the new leasing user is effectively improved, and the risk of bad leasing behaviors is reduced.
2. And if the verification is wrong, rechecking the credit risk assessment prediction result by a rechecking unit, and selecting a more reliable one of the first credit risk assessment prediction result or the second credit risk assessment prediction result as the basis for matching the new leasing user with the leasing mobile phone model, thereby further improving the accuracy of the credit risk assessment prediction.
Drawings
FIG. 1 is a block diagram of a system for renting on-line free deposit according to the present application.
Detailed Description
The present application will be described in further detail with reference to fig. 1.
The embodiment of the application discloses a method for leasing a deposit-free line.
An on-line leasing method for a escort comprises the following steps:
s1, collecting personal data and lease violations of historical lease users.
S2, training and learning personal data of the historical leasing user through the neural network model, adjusting the link weight among neurons of each component of the neural network model, and determining the internal relation between the personal data and the leasing default condition.
The neural network model can control the sample number of the sample set of the history leasing user for training and learning, so that the sample number of the sample set of the history leasing user is maintained at a better level, the problem that the neural network model cannot well master and learn the internal rules and correlations in the sample set caused by too small sample number in the learning process is avoided, and meanwhile, the problems that the learning time is slow and the learning data extraction and summarization capacity is reduced caused by too large sample number are avoided.
In an alternative embodiment, the functional expression of the neural network model is:
Error function extraction
Wherein, net jt is the input of the jth neuron of the t layer, y jt is the output of the jth neuron of the t layer, x i is the output of the ith neuron of the t-1 layer to the jth neuron of the t layer, w ij is the link weight between the ith neuron of the t-1 layer and the jth neuron of the t layer, y pm' is the target output, y pm is the actual output, θ jt is the output threshold of the jth neuron of the t layer, MSE is the mean square error between the output value of the neural network model and the expected value of the sample, P is the number of training samples, and M is the output node.
The training learning is carried out on the personal data of the historical leasing user through the neural network model, and the link weight among the neurons of each component of the neural network model is adjusted, which comprises the following steps:
And carrying out normalization processing on the personal data of the historical leasing user, converting the personal data of the historical leasing user into sample data with unified standards, inputting the sample data into a neural network model, and calculating the output of the neural network model. The method comprises the steps of carrying out normalization processing on personal data of a historical leasing user, and converting the personal data of the historical leasing user into sample data with unified standards, wherein for non-numerical data, different numerical values in the range of [0,1] are given to each personal data according to the influence degree of the non-numerical data on personal credit evaluation in actual work, and for numerical data, the personal data is converted into numerical values distributed in the range of (0, 1) through normal distribution S function.
And calculating a mean square error MSE between the output value and the sample expected value in the neural network model, then reversely calculating from the output layer to the input layer, adjusting each link weight w towards the direction of reducing the mean square error MSE, and terminating training when the mean square error MSE is smaller than a given allowable output threshold value theta.
S3, collecting personal data of the new leasing user, wherein the personal data of the history leasing user and the new leasing user comprise but are not limited to personal identification information data, personal basic data, personal credit data and personal family data, the personal identification information data comprise but are not limited to name, gender, ethnicity, native place and date of birth data, the personal basic data comprise but are not limited to academy, marital, housing, vehicles, work units, working time, professional properties, job classes, title and time of acquisition, the personal credit data comprise but are not limited to application program credit scores, annual income, credit cards, securities, bank deposit and insurance data, and the personal family data comprise but are not limited to family number, age composition, employment status and social insurance participation status data.
And inputting personal data of the new leasing user into the neural network model after training and learning, and determining a first credit risk assessment prediction result of the new leasing user according to the output result.
S4, after personal data of the new leasing user are input into the neural network model after training and learning and output results are calculated, calculating a leasing default rate of the new leasing user through a verification unit, determining a second credit risk assessment prediction result of the new leasing user, if the second credit risk assessment prediction result is identical to the first credit risk assessment prediction result, matching a mobile phone model for leasing for the new leasing user according to the first credit risk assessment prediction result, otherwise, calculating a third credit risk assessment prediction result of the new leasing user through a rechecking unit, and selecting one of the first credit risk assessment prediction result and the second credit risk assessment prediction result, which is identical to the third credit risk assessment prediction result, as a basis for matching the mobile phone model for leasing for the new leasing user.
And if the verification is wrong, rechecking the credit risk assessment prediction result by a rechecking unit, and selecting a more reliable one of the first credit risk assessment prediction result or the second credit risk assessment prediction result as the basis for matching the new leasing user with the leasing mobile phone model, thereby greatly improving the accuracy of the credit risk assessment prediction.
In an alternative embodiment, the calculating the lease violations of the new lease user through the verification unit includes the steps of substituting the personal data of the history lease user into the Logit prediction model, selecting the optimal personal data weight according to the SPSS software, substituting the personal data of the new lease user into the Logit distribution function, and calculating the lease violations of the new lease user;
the Logit prediction model is:
logitP=a0+a1y1+a2y2+...+amym,
Wherein P is the lease violation rate of the history leasing user, y 1,y2,...,ym is the personal data of the history leasing user, and a 0,a1,...,am is the personal data weight;
the Logit distribution function is:
Where P is the lease violation rate of the new lease subscriber, y 1,y2,...,ym is the personal data of the new lease subscriber, and a 0,a1,...,am is the optimal personal data weight selected according to the SPSS software.
In an alternative embodiment, the calculating, by the rechecking unit, the third credit risk assessment forecast of the new rental user includes the steps of:
Let the credit risk assessment discriminant function be y=c 1X1+C2X2+...+CpXp,
Wherein Y is a credit risk assessment index, X 1,X2,...,XP is personal data of a leasing user, and C 1,C2,...,CP is personal data weight;
Dividing historical leasing user samples into two groups according to credit risk assessment preference and difference, wherein one group of the credit risk assessment preference is group A, the number of samples is group n 1, and the average credit risk assessment index is The group of credit risk assessment differences is group B, the sample number is group n 2, and the average credit risk assessment index is
Calculating a weighted average of the average credit risk assessment indicators Y c:
Substituting personal data X 0 1,X0 2,...,X0 P of the new leasing user into the credit risk assessment discriminant function to obtain the credit risk assessment index of the new leasing user:
Y0＝C1X0 1+C2X0 2+...+CpX0 p;
When (when) If Y 0>Yc, the credit risk of the new leasing user is evaluated to be good, and if Y 0<Yc, the credit risk of the new leasing user is evaluated to be bad;
When (when) If Y 0<Yc, the credit risk of the new rental user is evaluated as excellent, and if Y 0>Yc, the credit risk of the new rental user is evaluated as poor.
S5, receiving the lease requirement of the new lease user, combining the first credit risk assessment prediction result or the second credit risk assessment prediction result selected in the step S4, matching the mobile phone model available for lease for the new lease user, and generating a lease order according to the selection of the new lease user. The method for receiving the lease demand of the new lease user comprises the following steps of constructing a user portrait according to purchase history, browsing behavior and evaluation feedback information of the new lease user, analyzing lease preference of the new lease user through a clustering analysis and association rule method, and generating a mobile phone model list matched with the new lease user through collaborative filtering and a content-based recommendation algorithm.
The embodiment of the application also discloses an on-line leasing system without deposit.
Referring to fig. 1, an escort on-line rental system, comprising:
and the information collection unit is used for collecting personal data of the historical lease subscribers and lease violations.
The first credit risk assessment prediction unit is used for training and learning the personal data of the historical leasing user through the neural network model, collecting the personal data of the new leasing user and calculating a first credit risk assessment prediction result of the new leasing user.
The lease matching unit is used for receiving lease requirements of the new lease user, matching mobile phone models available for lease for the new lease user, and generating lease orders according to the selection of the new lease user.
The verification unit is used for calculating the lease violation rate of the new lease user, determining a second credit risk assessment prediction result of the new lease user, comparing the second credit risk assessment prediction result with the first credit risk assessment prediction result, and outputting the first credit risk assessment prediction result to the lease matching unit as a basis for matching the new lease user with the available lease mobile phone model.
The rechecking unit is used for calculating a third credit risk assessment prediction result of the new leasing user, comparing the third credit risk assessment prediction result with the first credit risk assessment prediction result and the second credit risk assessment prediction result, and outputting the first credit risk assessment prediction result or the second credit risk assessment prediction result to the leasing matching unit as a basis for matching the new leasing user with the available leasing mobile phone model.
The embodiment of the application also provides corresponding equipment and a computer storage medium, which are used for realizing the scheme provided by the embodiment of the application. The apparatus includes a memory for storing instructions or code and a processor for executing the instructions or code to cause the apparatus to perform the methods described in embodiments of the present application. The computer storage medium stores code, and when the code is executed, the device executing the code implements the method according to the embodiment of the present application.
From the foregoing description of the embodiments, it will be apparent to those skilled in the art that all or part of the steps of the methods of the embodiments described above may be implemented by means of software plus general hardware platforms. Based on such understanding, the technical solution of the present application may be embodied in the form of a software product, which may be stored in a storage medium, such as a read-only memory, a magnetic disk, an optical disk, etc.
The embodiments of the present application are all preferred embodiments of the present application, and are not intended to limit the scope of the present application, wherein like reference numerals are used to refer to like elements throughout. Therefore, all equivalent changes according to the structure, shape and principle of the present application should be covered in the protection scope of the present application.

Claims (10)

1. The method for renting the deposit-free line is characterized by comprising the following steps of:
collecting personal data and lease violations of historical lease users;
Training and learning personal data of a history leasing user through a neural network model, adjusting the link weight among neurons of each component of the neural network model, and determining the internal relation between the personal data and leasing default conditions;
collecting personal data of a new leasing user, inputting the personal data of the new leasing user into the neural network model after training and learning, and determining a first credit risk assessment prediction result of the new leasing user according to an output result, wherein the personal data of the historical leasing user and the new leasing user comprise personal identification information data, personal basic data, personal credit data and personal family data;
and receiving the lease requirement of the new lease user, matching the mobile phone model available for lease for the new lease user, and generating a lease order according to the selection of the new lease user.
2. The method of claim 1, wherein the personal identification information data includes name, gender, ethnicity, native and date of birth data, the personal profile data includes school, marital, housing, vehicle, work unit, time of work, professional properties, job level, title and time of acquisition title data, the personal profile data includes application credit score, annual income, credit card, securities, bank deposit and insurance data, and the personal family profile data includes family number, age composition, employment status and social insurance participation status data.
3. The deposit-free online renting method according to claim 1, wherein a threshold value of the number of samples of the historical renting users in the neural network model is set, after the number of samples of the historical renting users reaches the threshold value, a group of samples of the historical renting users are removed before training and learning personal data of the historical renting users through the neural network model each time, and the removed samples of the historical renting users are selected according to the priority that the personal data lacks key information, the personal data information perfection is lowest, and the historical renting users last long.
4. The method for on-line rental of a free deposit according to claim 1, wherein the step of receiving the rental requirements of the new rental user and matching the mobile phone models available for rental for the new rental user comprises the steps of constructing a user portrait according to the purchase history, browsing behavior and evaluation feedback information of the new rental user, analyzing the rental preferences of the new rental user according to the rental requirements of the new rental user through a clustering analysis and association rule method, and generating a mobile phone model list matched with the new rental user through collaborative filtering and a content-based recommendation algorithm.
5. The method of claim 1, wherein the functional expression of the neural network model is:
Error function extraction
Wherein, net jt is the input of the jth neuron of the t layer, y jt is the output of the jth neuron of the t layer, x i is the output of the ith neuron of the t-1 layer to the jth neuron of the t layer, w ij is the link weight between the ith neuron of the t-1 layer and the jth neuron of the t layer, y pm' is the target output, y pm is the actual output, θ jt is the output threshold of the jth neuron of the t layer, MSE is the mean square error between the output value of the neural network model and the expected value of the sample, P is the number of training samples, and M is the output node;
The training learning is carried out on the personal data of the historical leasing user through the neural network model, and the link weight among the neurons of each component of the neural network model is adjusted, which comprises the following steps:
Carrying out normalization processing on personal data of the historical leasing user, converting the personal data of the historical leasing user into sample data with unified standards, inputting the sample data into a neural network model, and calculating output of the neural network model;
and calculating a mean square error MSE between the output value and the sample expected value in the neural network model, then reversely calculating from the output layer to the input layer, adjusting each link weight w towards the direction of reducing the mean square error MSE, and terminating training when the mean square error MSE is smaller than a given allowable output threshold value theta.
6. The deposit-free online renting method according to claim 5, characterized in that the normalizing the personal data of the history renting user, converting the personal data of the history renting user into unified sample data comprises the steps of assigning different numerical values in a range of [0,1] to each personal data according to the influence degree of the non-numerical value data on the personal credit evaluation in actual work, and converting the numerical value data into numerical values distributed in (0, 1) through a normal distribution S function.
7. The deposit-free online leasing method according to claim 1, wherein after personal data of a new leasing user is input to the trained and learned neural network model and an output result is calculated, a leasing violation rate of the new leasing user is calculated through a verification unit, a second credit risk assessment prediction result of the new leasing user is determined, if the second credit risk assessment prediction result is identical to the first credit risk assessment prediction result, the new leasing user is matched with a mobile phone model for leasing according to the first credit risk assessment prediction result, otherwise, a third credit risk assessment prediction result of the new leasing user is calculated through a rechecking unit, and one of the first credit risk assessment prediction result and the second credit risk assessment prediction result, which is identical to the third credit risk assessment prediction result, is selected as a basis for matching the new leasing user with the mobile phone model for leasing.
8. The method for on-line lease of a deposit-free line as claimed in claim 7, wherein said calculating a lease violating rate of a new lease user by a verification unit includes the steps of substituting personal data of a history lease user into a Logit prediction model, selecting an optimal personal data weight according to SPSS software, substituting the personal data of the new lease user into a Logit distribution function, and calculating a lease violating rate of the new lease user;
the Logit prediction model is:
logitP=a0+a1y1+a2y2+...+amym,
Wherein P is the lease violation rate of the history leasing user, y 1,y2,...,ym is the personal data of the history leasing user, and a 0,a1,...,am is the personal data weight;
the Logit distribution function is:
Where P is the lease violation rate of the new lease subscriber, y 1,y2,...,ym is the personal data of the new lease subscriber, and a 0,a1,...,am is the optimal personal data weight selected according to the SPSS software.
9. The method for on-line lease of a deposit-free line according to claim 7, characterized in that said calculating a third credit risk evaluation prediction result of a new lease subscriber by a rechecking unit comprises the steps of:
Let the credit risk assessment discriminant function be y=c 1X1+C2X2+...+CpXp,
Wherein Y is a credit risk assessment index, X 1,X2,...,XP is personal data of a leasing user, and C 1,C2,...,CP is personal data weight;
Dividing historical leasing user samples into two groups according to credit risk assessment preference and difference, wherein one group of the credit risk assessment preference is group A, the number of samples is group n 1, and the average credit risk assessment index is The group of credit risk assessment differences is group B, the sample number is group n 2, and the average credit risk assessment index is
Calculating a weighted average of the average credit risk assessment indicators Y c:
Substituting personal data X 0 1,X0 2,...,X0 P of the new leasing user into the credit risk assessment discriminant function to obtain the credit risk assessment index of the new leasing user:
Y0＝C1X0 1+C2X0 2+...+CpX0 p;
When (when) If Y 0>Yc, the credit risk of the new leasing user is evaluated to be good, and if Y 0<Yc, the credit risk of the new leasing user is evaluated to be bad;
When (when) If Y 0<Yc, the credit risk of the new rental user is evaluated as excellent, and if Y 0>Yc, the credit risk of the new rental user is evaluated as poor.
10. A deposit-free online rental system, comprising:
The information collection unit is used for collecting personal data and lease violations of historical lease users;
The first credit risk assessment prediction unit is used for training and learning the personal data of the historical leasing user through the neural network model, collecting the personal data of the new leasing user and calculating a first credit risk assessment prediction result of the new leasing user;
the lease matching unit is used for receiving lease requirements of the new lease user, matching mobile phone models available for lease for the new lease user, and generating lease orders according to the selection of the new lease user.
CN202411579641.7A 2024-11-06 2024-11-06 A deposit-free online rental method and system Pending CN119515514A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202411579641.7A CN119515514A (en) 2024-11-06 2024-11-06 A deposit-free online rental method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202411579641.7A CN119515514A (en) 2024-11-06 2024-11-06 A deposit-free online rental method and system

Publications (1)

Publication Number Publication Date
CN119515514A true CN119515514A (en) 2025-02-25

Family

ID=94662115

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202411579641.7A Pending CN119515514A (en) 2024-11-06 2024-11-06 A deposit-free online rental method and system

Country Status (1)

Country Link
CN (1) CN119515514A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN120975537A (en) * 2025-06-20 2025-11-18 北京小马快租科技有限公司 A Method and System for Optimizing Risk Control in Mobile Phone Rental Based on Multi-Dimensional AI Model Analysis

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN120975537A (en) * 2025-06-20 2025-11-18 北京小马快租科技有限公司 A Method and System for Optimizing Risk Control in Mobile Phone Rental Based on Multi-Dimensional AI Model Analysis

Similar Documents

Publication Publication Date Title
CN116342259A (en) A user credit automatic rating method, device, electronic equipment and medium
CN112102073A (en) Credit risk control method and system, electronic device and readable storage medium
CN111062444B (en) Credit risk prediction methods, systems, terminals and storage media
CN112990989B (en) Value prediction model input data generation method, device, equipment and medium
CN110704730A (en) Product data pushing method and system based on big data and computer equipment
CN113706258A (en) Product recommendation method, device, equipment and storage medium based on combined model
CN115293336A (en) Risk assessment model training method and device and server
CN112990386B (en) User value clustering method and device, computer equipment and storage medium
CN110288459A (en) Loan prediction technique, device, equipment and storage medium
CN112561691B (en) Client trust prediction method, device, equipment and storage medium
CN116596659A (en) Enterprise intelligent credit approval method, system and medium based on big data wind control
CN112950347A (en) Resource data processing optimization method and device, storage medium and terminal
CN117094817B (en) Credit risk control intelligent prediction method and system
CN119515514A (en) A deposit-free online rental method and system
CN118568513B (en) A user portrait construction method, system, device and medium based on AI
CN113807943A (en) A multi-factor valuation method and system, medium and equipment for non-performing assets
CN114187154A (en) Anti-money laundering identification method and device, computer equipment and storage medium
CN110533528A (en) Assess the method and apparatus of business standing
CN118134630A (en) Credit risk rating assessment method, device and electronic equipment
CN114693428B (en) Data determination method, device, computer readable storage medium and electronic device
CN117575773A (en) Method, device, computer equipment and storage medium for determining service data
CN116384750A (en) Method and computing device for generating labeled samples and training risk rating prediction model
CN113989012A (en) Classification method and device, medium and equipment for borrowing target population of non-performing assets
KR100686466B1 (en) Method and system for providing asset valuation and stability analysis system for profitability
CN112862602B (en) A method for determining user request, storage medium, and electronic device

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