CN114612132A - Client renewal prediction method based on machine learning and related equipment - Google Patents
Client renewal prediction method based on machine learning and related equipment Download PDFInfo
- Publication number
- CN114612132A CN114612132A CN202210169141.0A CN202210169141A CN114612132A CN 114612132 A CN114612132 A CN 114612132A CN 202210169141 A CN202210169141 A CN 202210169141A CN 114612132 A CN114612132 A CN 114612132A
- Authority
- CN
- China
- Prior art keywords
- renewal
- data
- prediction
- machine learning
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
-
- 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
- G06Q40/08—Insurance
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Artificial Intelligence (AREA)
- Strategic Management (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Software Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- Technology Law (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a client renewal prediction method based on machine learning and related equipment, wherein the method comprises the following steps: acquiring continuous insurance policy data for model training; extracting multidimensional characteristic data from the renewal warranty data; training a preset machine learning model according to the multi-dimensional feature data to obtain a continuous prediction model; acquiring historical policy data of a target client; and inputting the historical policy data into the renewal prediction model, and outputting a renewal prediction result of the policy corresponding to the target client. The method can quickly and stably predict the renewal intention of the client, is beneficial to marketers to perform exhibition industry according to the renewal prediction result, performs differentiated services on the client, and improves the renewal rate.
Description
Technical Field
The application relates to the technical field of computers, in particular to a client renewal prediction method based on machine learning and related equipment.
Background
In recent years, with the development of insurance business, the number of policies sold via the internet has been increasing year by year. For insurance companies, the renewal of the policy will directly affect the premium size. When the insurance product purchased by the guaranteed customer is due, the guaranteed customer can be expected to continue the guarantee, and in the process, the marketer cannot know the insurance continuing desire of the customer, so that differentiated efficient exhibition can not be performed.
At present, generally, the continuous willingness of a client is predicted through the personal experience of marketers, and due to the fact that the personal experience of different marketers is different, the accuracy of a manual judgment mode is not high and is not stable. Therefore, a scheme for predicting the continuous guarantee of the client is needed to effectively and accurately predict the continuous guarantee desire of the client.
Disclosure of Invention
In view of the above, the present application aims to provide a method and related apparatus for predicting customer renewal based on machine learning to solve the above problems.
In view of the above, a first aspect of the present application provides a client renewal prediction method based on machine learning, including:
acquiring continuous insurance policy data for model training;
extracting multi-dimensional characteristic data from the renewal warranty data;
training a preset machine learning model according to the multi-dimensional feature data to obtain a continuous prediction model;
acquiring historical policy data of a target client;
and inputting the historical policy data into the renewal prediction model, and outputting a renewal prediction result of the policy corresponding to the target customer.
Further, the training a preset machine learning model according to the multidimensional feature data to obtain a persistence prediction model comprises:
the multi-dimensional feature data is pre-processed,
dividing the preprocessed multidimensional characteristic data into a training data set, a verification data set and a test data set;
training the machine learning model by using the training data set, and acquiring the accuracy of the machine learning model through the verification set every time iteration is completed; and
optimizing hyper-parameters of the machine learning model through a hyper-parameter optimization algorithm;
repeatedly executing the operation until the preset iteration times are met or the accuracy of the machine learning model meets the preset condition, and obtaining a trained continuous prediction model;
and verifying the accuracy of the trained continuous prediction model by using the test set to obtain a continuous prediction result.
Further, after the inputting the historical policy data into the renewal prediction model and outputting the renewal prediction result of the policy corresponding to the target customer, the method further comprises:
determining the renewal prediction probability of the target client according to the renewal prediction result;
in response to determining that the renewal prediction probability is greater than or equal to a preset renewal probability threshold, marking the target customer as an renewal intent customer and presenting.
Further, the preprocessing comprises data cleaning and data dimension reduction.
Further, the hyper-parametric optimization algorithm comprises at least one of: a grid search algorithm, a random search algorithm, and/or a bayesian optimization algorithm.
Further, the multi-dimensional feature data includes: the system comprises client basic information, historical insurance application record information, historical claim settlement record information, insurance policy information and marketer basic information.
Further, the machine learning model uses an algorithm comprising: a random forest algorithm, an Xgboost algorithm, or a Wide & Deep algorithm.
Based on the same inventive concept, a second aspect of the present application provides a client renewal prediction device based on machine learning, comprising:
a first acquisition module configured to acquire renewal sheet data for model training;
a feature extraction module configured to extract multi-dimensional feature data from the renewal warranty data;
the model training module is configured to train a preset machine learning model according to the multi-dimensional feature data to obtain a continuous prediction model;
a second obtaining module configured to obtain historical policy data of the target customer;
and the renewal prediction module is configured to input the historical policy data into the renewal prediction model and output a renewal prediction result of the policy corresponding to the target customer.
Based on the same inventive concept, a third aspect of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the method according to the first aspect when executing the program.
Based on the same inventive concept, a fourth aspect of the present application provides a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method of the first aspect.
From the above, the client renewal prediction method and the related equipment based on machine learning provided by the application can be used for training the machine learning model by using the renewal policy to obtain the trained renewal prediction model, and can be used for quickly and stably predicting the renewal desire of the client to be predicted by using the trained renewal prediction model, thereby being beneficial to the marketer to perform the exhibition industry according to the renewal prediction result, performing differentiated services on the client and improving the renewal rate.
Drawings
In order to more clearly illustrate the technical solutions in the present application or related technologies, the drawings required for the embodiments or related technologies in the following description are briefly introduced, and it is obvious that the drawings in the following description are only the embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flowchart of a method for predicting customer renewal based on machine learning according to an embodiment of the present application;
FIG. 2 is a flowchart of a continuation prediction model training method according to an embodiment of the present application;
FIG. 3 is a flowchart of a renewal prediction result display method according to an embodiment of the present application;
FIG. 4 is a schematic structural diagram of a client renewal prediction device based on machine learning according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is further described in detail below with reference to the accompanying drawings in combination with specific embodiments.
It should be noted that technical terms or scientific terms used in the embodiments of the present application should have a general meaning as understood by those having ordinary skill in the art to which the present application belongs, unless otherwise defined. The use of "first," "second," and similar terms in the embodiments of the present application do not denote any order, quantity, or importance, but rather the terms are used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that the element or item listed before the word covers the element or item listed after the word and its equivalents, but does not exclude other elements or items. The terms "connected" or "coupled" and the like are not restricted to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", and the like are used merely to indicate relative positional relationships, and when the absolute position of the object being described is changed, the relative positional relationships may also be changed accordingly.
As described in the background section, the prediction scheme of the renewal intention in the related art is also difficult to satisfy, and the renewal intention of the customer is generally judged by the personal experience of the marketer. The applicant finds that the prediction scheme of the renewal willingness in the prior art at least has the following problems in the process of implementing the application: there is uncertainty in judging the customer's willingness to continue with the business by only relying on the marketer's personal experience. The personal experience of the marketer with longer working time is richer than that of the marketer with shorter working time, so that the judgment accuracy of the continuous insurance willingness of the marketer with longer working time to the client is higher than that of the marketer with shorter working time. In addition, when the amount of clients needing to predict the renewal intention is large, the accuracy of manually judging the renewal intention of the clients cannot be guaranteed, the working efficiency is greatly reduced, and the method is not beneficial to marketers to perform exhibition.
In view of this, the embodiment of the present application provides a client renewal prediction method based on machine learning, which extracts feature data from a historical renewal sheet, trains a machine learning model by using the feature data to obtain a renewal prediction model, and can quickly and stably predict the renewal intention of a client by using the trained renewal prediction model.
Hereinafter, the technical means of the present application will be described in detail by specific examples.
Referring to fig. 1, an embodiment of the present application provides a client renewal prediction method based on machine learning, which specifically includes the following steps:
and step S101, acquiring continuous insurance policy data for model training.
In this step, when renewal is about to expire, the insured life applies for the insurer to require the extension of the life of the insurance contract or the re-handling of insurance procedures. In the process of dealing with the renewal, the insurer or insured life can increase or decrease the amount of insurance or make other changes according to the current objective situation or need. For insurance companies, the influence of the renewal operation condition of the policy on the premium scale is large, the renewal condition of the policy about to expire is reasonably controlled, the renewal rate is favorably improved, and the company is continuously charged.
The categories of insurance fall into two main categories: property risk and personal risk categories, wherein the property risk categories may include: enterprise insurance, engineering insurance, vehicle insurance, responsibility insurance, ship insurance, freight insurance, family insurance, credit insurance, agricultural insurance; the personal risks categories may include: accident insurance, medical insurance, serious illness insurance, life insurance, child education insurance, endowment insurance, annuity insurance and group insurance. Different types of insurance, the willingness to renew by the customer is also different, for example: the truck driver needs to drive the truck all the year round, so that the truck driver has higher continuous insurance willingness on accident danger; people with poor physical condition have high continuous willingness on severe illness and medical insurance.
When obtaining the renewal policy data, the renewal policy can be extracted from each category risk, so as to improve the prediction accuracy of the machine learning model which is trained subsequently. The policy data at least includes: the type of insurance purchased, the name of the insurance purchased, the premium due, the marketer, the total premium, the customer property information, the customer age information, the number of claims for which the customer has purchased insurance, etc.
And S102, extracting multi-dimensional feature data from the continuous insurance policy data.
In this step, the data size in the renewal warranty is large, so warranty data favorable for improving the renewal prediction accuracy needs to be selected, and the customer basic information, the historical insurance application record information, the historical claim settlement record information, the warranty information and the marketer basic information can be specifically selected to form the multidimensional feature data.
And S103, training a preset machine learning model according to the multi-dimensional feature data to obtain a continuous prediction model.
In this step, the algorithm used by the machine learning model may be a random forest algorithm, an Xgboost algorithm, or a Wide & Deep algorithm.
The random forest algorithm is that training samples are input into each decision tree, for each decision tree, random and replaced extraction part of the training samples are taken as a training set of the tree, and the final classification result depends on the classification result with most trees.
The Xgboost algorithm is an integrated machine learning algorithm based on a decision tree, and employs a Gradient Boosting (Gradient Boosting) framework, which can be used for classification or regression by inputting parameter data.
The Wide & Deep algorithm aims to make the trained model obtain the memory capacity and the generalization capacity simultaneously.
Among the three algorithms, the Xgboost algorithm is the optimal choice, and has better effect no matter on the classification accuracy, the model training and the model running speed.
And step S104, acquiring historical policy data of the target client.
In this step, the target client is the applicant whose insurance contract period is about to expire, and the obtained historical policy data is also the policy data corresponding to the applicant's period about to expire.
Step S105, inputting the historical policy data into the renewal prediction model, and outputting a renewal prediction result of the policy corresponding to the target customer.
Therefore, the client renewal prediction method based on machine learning provided by the embodiment is based on machine learning, trains the machine learning model by using the renewal policy to obtain the trained renewal prediction model, and rapidly and stably predicts the renewal desire of the client to be predicted by using the trained renewal prediction model, thereby being beneficial to a marketer to perform the exhibition industry according to the renewal prediction result, performing differentiated services on the client and improving the renewal rate.
In some embodiments, in conjunction with fig. 2, for step S103 in the foregoing embodiments, it may further include the following steps:
and step S1031, preprocessing the multi-dimensional feature data.
In the step, the preprocessing comprises data cleaning and data dimension reduction, and the processing result directly influences the effect of a subsequent model. Wherein the data cleaning comprises the processing of abnormal values, the processing of null values, the processing of missing values and repeated values. The repeated value and the abnormal value can adopt a direct deleting processing mode; the abnormal value can be directly deleted or replaced, and the null value can be filled with the missing value by replacing the value.
When the data volume of washing is great, can set up fixed time quantum, divide data, in a time quantum, wash to a section fixed data, when avoiding wasing data in real time, because the data increase the apparent increase of the data washing number of times that brings to avoid carrying out the repeated washing many times to data.
The data dimension reduction method comprises the following specific steps: standardizing the multidimensional characteristic data, wherein the mean value is 0, and the variance is 1; calculating a covariance matrix, an eigenvalue of the covariance matrix and an eigenvector corresponding to the eigenvalue; sorting the eigenvalues according to the sizes, selecting the largest k of the eigenvalues, and taking the corresponding eigenvectors as row vectors respectively to form an eigenvector matrix; and converting the multi-dimensional feature data into a new space consisting of k feature vectors.
The multidimensional characteristic data are processed by adopting a preprocessing method of data cleaning and data dimension reduction, so that the training data volume is greatly reduced, the training time and the prediction accuracy of the model are improved, new characteristic data without losing the original data information volume are generated by reducing the dimension of the data, the calculation time is greatly shortened, and the model prediction capability is improved.
Further, the following may be performed on the maldistribution samples: performing up-sampling operation on a sample with low ratio by using various up-sampling methods such as Random, SMOTE, bSMOTE (1&2), SVM SMOTE, ADASYNC and the like in an immbalanced-least development kit; and (3) carrying out down-sampling operation on the high-ratio sample by adopting various down-sampling methods such as Random, Tomek links, NearMiss and the like. When the algorithm applied by the machine learning model is the Xgboost algorithm, a specific parameter scale _ pos _ weight exists in the Xgboost algorithm, and the function of the method is mainly to adjust the error function of the model according to a set proportion for unbalanced samples, increase the learning rate of a few samples, thereby enhancing the influence degree of misjudgment of low-duty samples on model errors and achieving the effect of adjusting the sample proportion.
Step S1032, the preprocessed multidimensional characteristic data is divided into a training data set, a verification data set and a test data set.
In this step, the ratio of the training data set, the verification data set, and the test data set may be selected from 7:1:2 or 8:1:1, or the ratio of the training data set, the verification data set, and the test data set may be adjusted according to the actual data volume, which is not specifically limited herein.
And step S1033, training the machine learning model by using the training data set, acquiring the accuracy of the machine learning model through the verification set every time iteration is completed, and optimizing the hyper-parameters of the machine learning model through a hyper-parameter optimization algorithm.
In this step, the hyper-parameters of the machine learning model can be optimized by a grid search algorithm, a random search algorithm and/or a Bayesian optimization algorithm. The grid search algorithm is a hyper-parameter search method, and specifically comprises the following steps: traversing the parameters of all the step points in a hyper-parameter space according to a fixed step length, selecting the best hyper-parameter point, then continuously reducing the step length in the neighborhood of the hyper-parameter point, and continuously traversing until the set minimum step length is reached, wherein the obtained hyper-parameter point is the optimal hyper-parameter point. The random search algorithm is to combine the hyper-parameters randomly, and compared with the network search algorithm, the random search algorithm has the randomness and reduces the calculated amount with a certain probability. Bayes optimization is to calculate posterior probability distribution of the front n points through Gaussian process regression to obtain expected mean and variance of each group of hyper-parameters of the model at the value taking point, wherein the mean represents expected effect of the model under the hyper-parameters corresponding to the point, and the larger the mean is, the better the final effect of the model is; the variance represents the uncertainty of the effect, and a larger variance represents a larger uncertainty of the effect achieved at this point.
And S1034, repeatedly executing the step S1033 until a preset iteration number is met or the accuracy of the machine learning model meets a preset condition, and obtaining a trained continuous prediction model.
In this step, the preset condition is an accuracy threshold, and it should be noted that the iteration number and the accuracy threshold may be set according to an actual situation, which is not specifically limited herein.
And step S1035, verifying the accuracy of the trained continuous prediction model by using the test set to obtain a continuous prediction result.
In this step, when the continuation prediction model is input by using the test set and the corresponding continuation prediction result meets the preset prediction accuracy, the performance of the continuation prediction model is better.
In some embodiments, referring to fig. 3, for step S105 in the foregoing embodiments, it may further include the following steps after that:
step S301, determining the renewal prediction probability of the target client according to the renewal prediction result.
Step S302, in response to the fact that the renewal prediction probability is larger than or equal to a preset renewal probability threshold, marking the target customer as an intention-to-renew customer and displaying the intention-to-renew customer.
In this embodiment, by setting the renewal probability threshold, the client with a higher renewal will is selected and displayed to the corresponding marketer, so that the marketer preferentially formulates the exhibition business strategy. In addition, a plurality of continuous guarantee probability threshold values can be set, the continuous guarantee willingness of the client is divided into a plurality of grades, and the marketing efficiency of the marketer is further improved.
It should be noted that the method of the embodiment of the present application may be executed by a single device, such as a computer or a server. The method of the embodiment can also be applied to a distributed scene and completed by the mutual cooperation of a plurality of devices. In such a distributed scenario, one of the multiple devices may only perform one or more steps of the method of the embodiment, and the multiple devices interact with each other to complete the method.
It should be noted that the above describes some embodiments of the present application. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments described above and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
Based on the same inventive concept, corresponding to the method of any embodiment, the application also provides a client renewal prediction device based on machine learning.
Referring to fig. 4, the machine learning-based client renewal prediction device includes:
a first acquisition module configured to acquire renewal data for model training.
A feature extraction module configured to extract multi-dimensional feature data from the renewal warranty data.
And the model training module is configured to train a preset machine learning model according to the multi-dimensional feature data to obtain a continuous prediction model.
A second obtaining module configured to obtain historical policy data for the target customer.
And the renewal prediction module is configured to input the historical policy data into the renewal prediction model and output a renewal prediction result of the policy corresponding to the target customer.
As an alternative embodiment, the model training module is specifically configured to preprocess the multi-dimensional feature data;
dividing the preprocessed multidimensional characteristic data into a training data set, a verification data set and a test data set;
training the machine learning model by using the training data set, and acquiring the accuracy of the machine learning model through the verification set every time iteration is completed; optimizing the hyper-parameters of the machine learning model through a hyper-parameter optimization algorithm; repeatedly executing the operation until the preset iteration times are met or the accuracy of the machine learning model meets the preset condition, and obtaining a trained continuous prediction model; and verifying the accuracy of the trained continuous prediction model by using the test set to obtain a continuous prediction result.
As an optional embodiment, the apparatus further comprises a forecast result presentation module (not shown) configured to determine a renewal prediction probability of the target customer based on the renewal forecast result; in response to determining that the renewal prediction probability is greater than or equal to a preset renewal probability threshold, marking the target customer as an renewal intent customer and presenting.
As an alternative embodiment, the preprocessing includes data cleansing and data dimensionality reduction.
As an alternative embodiment, the hyper-parametric optimization algorithm comprises at least one of: a grid search algorithm, a random search algorithm, and/or a bayesian optimization algorithm.
As an alternative embodiment, the multi-dimensional feature data includes: the system comprises client basic information, historical insurance application record information, historical claim settlement record information, insurance policy information and marketer basic information.
As an alternative embodiment, the machine learning model uses an algorithm comprising: a random forest algorithm, an Xgboost algorithm, or a Wide & Deep algorithm.
For convenience of description, the above devices are described as being divided into various modules by functions, and are described separately. Of course, the functionality of the various modules may be implemented in the same one or more software and/or hardware implementations as the present application.
The device in the foregoing embodiment is used to implement the corresponding client renewal prediction method based on machine learning in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiment, which are not described herein again.
Based on the same inventive concept, corresponding to the method of any embodiment described above, the present application further provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the program, the method for predicting the renewal of the client based on the machine learning according to any embodiment described above is implemented.
Fig. 5 is a schematic diagram illustrating a more specific hardware structure of an electronic device according to this embodiment, where the electronic device may include: a processor 1010, a memory 1020, an input/output interface 1030, a communication interface 1040, and a bus 1050. Wherein the processor 1010, memory 1020, input/output interface 1030, and communication interface 1040 are communicatively coupled to each other within the device via bus 1050.
The processor 1010 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits, and is configured to execute related programs to implement the technical solutions provided in the embodiments of the present disclosure.
The Memory 1020 may be implemented in the form of a ROM (Read Only Memory), a RAM (Random Access Memory), a static Memory device, a dynamic Memory device, or the like. The memory 1020 may store an operating system and other application programs, and when the technical solution provided by the embodiments of the present specification is implemented by software or firmware, the relevant program codes are stored in the memory 1020 and called to be executed by the processor 1010.
The input/output interface 1030 is used for connecting an input/output module to input and output information. The i/o module may be configured as a component in a device (not shown) or may be external to the device to provide a corresponding function. The input devices may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output devices may include a display, a speaker, a vibrator, an indicator light, etc.
The communication interface 1040 is used for connecting a communication module (not shown in the drawings) to implement communication interaction between the present apparatus and other apparatuses. The communication module can realize communication in a wired mode (such as USB, network cable and the like) and also can realize communication in a wireless mode (such as mobile network, WIFI, Bluetooth and the like).
It should be noted that although the above-mentioned device only shows the processor 1010, the memory 1020, the input/output interface 1030, the communication interface 1040 and the bus 1050, in a specific implementation, the device may also include other components necessary for normal operation. In addition, those skilled in the art will appreciate that the above-described apparatus may also include only the components necessary to implement the embodiments of the present disclosure, and need not include all of the components shown in the figures.
The electronic device of the foregoing embodiment is used to implement the corresponding machine learning-based client renewal prediction method in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiment, which are not described herein again.
Based on the same inventive concept, corresponding to any of the above-described embodiment methods, the present application further provides a non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the machine learning-based customer renewal prediction method according to any of the above embodiments.
Computer-readable media of the present embodiments, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device.
The computer instructions stored in the storage medium of the above embodiment are used to enable the computer to execute the client renewal prediction method based on machine learning according to any of the above embodiments, and have the beneficial effects of corresponding method embodiments, which are not described herein again.
Those of ordinary skill in the art will understand that: the discussion of any embodiment above is meant to be exemplary only, and is not intended to intimate that the scope of the disclosure, including the claims, is limited to these examples; within the context of the present application, features from the above embodiments or from different embodiments may also be combined, steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present application as described above, which are not provided in detail for the sake of brevity.
In addition, well-known power/ground connections to Integrated Circuit (IC) chips and other components may or may not be shown in the provided figures for simplicity of illustration and discussion, and so as not to obscure the embodiments of the application. Furthermore, devices may be shown in block diagram form in order to avoid obscuring embodiments of the application, and this also takes into account the fact that specifics with respect to implementation of such block diagram devices are highly dependent upon the platform within which the embodiments of the application are to be implemented (i.e., specifics should be well within purview of one skilled in the art). Where specific details (e.g., circuits) are set forth in order to describe example embodiments of the application, it should be apparent to one skilled in the art that the embodiments of the application can be practiced without, or with variation of, these specific details. Accordingly, the description is to be regarded as illustrative instead of restrictive.
While the present application has been described in conjunction with specific embodiments thereof, many alternatives, modifications, and variations of these embodiments will be apparent to those of ordinary skill in the art in light of the foregoing description. For example, other memory architectures (e.g., dynamic ram (dram)) may use the discussed embodiments.
The present embodiments are intended to embrace all such alternatives, modifications and variances which fall within the broad scope of the appended claims. Therefore, any omissions, modifications, substitutions, improvements, and the like that may be made without departing from the spirit and principles of the embodiments of the present application are intended to be included within the scope of the present application.
Claims (10)
1. A client renewal prediction method based on machine learning is characterized by comprising the following steps:
acquiring continuous insurance policy data for model training;
extracting multi-dimensional characteristic data from the renewal warranty data;
training a preset machine learning model according to the multi-dimensional feature data to obtain a continuous prediction model;
acquiring historical policy data of a target client;
and inputting the historical policy data into the renewal prediction model, and outputting a renewal prediction result of the policy corresponding to the target customer.
2. The prediction method according to claim 1, wherein the training of a preset machine learning model according to the multidimensional feature data to obtain a continuous prediction model comprises:
preprocessing the multi-dimensional feature data;
dividing the preprocessed multidimensional characteristic data into a training data set, a verification data set and a test data set;
training the machine learning model by using the training data set, and acquiring the accuracy of the machine learning model through the verification set every time iteration is completed; and
optimizing the hyper-parameters of the machine learning model through a hyper-parameter optimization algorithm;
repeatedly executing the operation until the preset iteration times are met or the accuracy of the machine learning model meets the preset condition, and obtaining a trained continuous prediction model;
and verifying the accuracy of the trained continuous prediction model by using the test set to obtain a continuous prediction result.
3. The forecasting method of claim 1, wherein the step of inputting the historical policy data into the renewal prediction model and outputting the renewal prediction result for the policy corresponding to the target customer further comprises:
determining the renewal prediction probability of the target client according to the renewal prediction result;
in response to determining that the renewal prediction probability is greater than or equal to a preset renewal probability threshold, marking the target customer as an renewal intent customer and presenting.
4. The prediction method of claim 2, wherein the preprocessing comprises data cleansing and data dimensionality reduction.
5. The prediction method of claim 2, wherein the hyper-parametric optimization algorithm comprises at least one of: a grid search algorithm, a random search algorithm, and/or a bayesian optimization algorithm.
6. The prediction method according to any one of claims 1 to 5, wherein the multi-dimensional feature data comprises: the system comprises client basic information, historical insurance application record information, historical claim settlement record information, insurance policy information and marketer basic information.
7. The prediction method according to any one of claims 1 to 5, wherein the machine learning model uses an algorithm comprising: a random forest algorithm, an Xgboost algorithm, or a Wide & Deep algorithm.
8. A client renewal prediction device based on machine learning, comprising:
a first acquisition module configured to acquire renewal sheet data for model training;
a feature extraction module configured to extract multi-dimensional feature data from the renewal warranty data;
the model training module is configured to train a preset machine learning model according to the multi-dimensional feature data to obtain a continuous prediction model;
a second obtaining module configured to obtain historical policy data of the target customer;
and the renewal prediction module is configured to input the historical policy data into the renewal prediction model and output a renewal prediction result of the policy corresponding to the target customer.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method according to any of claims 1 to 7 when executing the program.
10. A non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method of any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210169141.0A CN114612132A (en) | 2022-02-23 | 2022-02-23 | Client renewal prediction method based on machine learning and related equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210169141.0A CN114612132A (en) | 2022-02-23 | 2022-02-23 | Client renewal prediction method based on machine learning and related equipment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114612132A true CN114612132A (en) | 2022-06-10 |
Family
ID=81859543
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210169141.0A Pending CN114612132A (en) | 2022-02-23 | 2022-02-23 | Client renewal prediction method based on machine learning and related equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114612132A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117150389A (en) * | 2023-07-14 | 2023-12-01 | 广州易尊网络科技股份有限公司 | Model training method, carrier card activation prediction method and equipment thereof |
-
2022
- 2022-02-23 CN CN202210169141.0A patent/CN114612132A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117150389A (en) * | 2023-07-14 | 2023-12-01 | 广州易尊网络科技股份有限公司 | Model training method, carrier card activation prediction method and equipment thereof |
CN117150389B (en) * | 2023-07-14 | 2024-04-12 | 广州易尊网络科技股份有限公司 | Model training method, carrier card activation prediction method and equipment thereof |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Jones et al. | An empirical evaluation of the performance of binary classifiers in the prediction of credit ratings changes | |
Kolassa | Combining exponential smoothing forecasts using Akaike weights | |
US11640617B2 (en) | Metric forecasting employing a similarity determination in a digital medium environment | |
CN103370722B (en) | The system and method that actual volatility is predicted by small echo and nonlinear kinetics | |
WO2019015631A1 (en) | Method for generating combined features for machine learning samples and system | |
Han et al. | Forecasting dry bulk freight index with improved SVM | |
CN106445988A (en) | Intelligent big data processing method and system | |
EP4322031A1 (en) | Recommendation method, recommendation model training method, and related product | |
Maldonado et al. | Advanced conjoint analysis using feature selection via support vector machines | |
AU2020325094B2 (en) | Finite rank deep kernel learning with linear computational complexity | |
CN110766481A (en) | Client data processing method and device, electronic equipment and computer readable medium | |
CN110796171A (en) | Unclassified sample processing method and device of machine learning model and electronic equipment | |
AU2020326407B2 (en) | Extending finite rank deep kernel learning to forecasting over long time horizons | |
CN111582589A (en) | Car rental insurance prediction method, device, equipment and storage medium | |
CN114612132A (en) | Client renewal prediction method based on machine learning and related equipment | |
Shaprapawad et al. | Car Price Prediction: An Application of Machine Learning | |
CN117195061B (en) | Event response prediction model processing method and device and computer equipment | |
CN112561569B (en) | Dual-model-based store arrival prediction method, system, electronic equipment and storage medium | |
CN112991026A (en) | Commodity recommendation method, system, equipment and computer readable storage medium | |
Rane et al. | Used car price prediction | |
CN114219084B (en) | Sales visit display counterfeiting identification method and device in fast moving industry | |
Shymanskyi et al. | Cascade Model for Price and Time of Car Sales Prediction. | |
CN115641198A (en) | User operation method, device, electronic equipment and storage medium | |
CN114722941A (en) | Credit default identification method, apparatus, device and medium | |
CN113947431A (en) | User behavior quality evaluation method, device, equipment and storage medium |
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 |