CN117893273A - Financial product recommendation method and related device for financial cabin - Google Patents
Financial product recommendation method and related device for financial cabin Download PDFInfo
- Publication number
- CN117893273A CN117893273A CN202311708989.7A CN202311708989A CN117893273A CN 117893273 A CN117893273 A CN 117893273A CN 202311708989 A CN202311708989 A CN 202311708989A CN 117893273 A CN117893273 A CN 117893273A
- Authority
- CN
- China
- Prior art keywords
- financial
- data
- product
- recommended
- real
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 75
- 230000006399 behavior Effects 0.000 claims description 140
- 238000003860 storage Methods 0.000 claims description 28
- 238000012549 training Methods 0.000 claims description 22
- 238000004590 computer program Methods 0.000 claims description 13
- 238000007781 pre-processing Methods 0.000 claims description 9
- 238000012797 qualification Methods 0.000 claims description 5
- 238000004891 communication Methods 0.000 claims 1
- 230000008569 process Effects 0.000 description 15
- 238000010586 diagram Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 8
- 238000012545 processing Methods 0.000 description 8
- 230000009471 action Effects 0.000 description 4
- 238000004140 cleaning Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- RWSOTUBLDIXVET-UHFFFAOYSA-N Dihydrogen sulfide Chemical compound S RWSOTUBLDIXVET-UHFFFAOYSA-N 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Landscapes
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The application provides a financial product recommendation method and a related device for a financial cabin, wherein the method comprises the following steps: determining a plurality of saleable financial products corresponding to the target financial cabin in the current period, and acquiring product data corresponding to the saleable financial products respectively; responding to login operation of a user to be recommended in a target financial cabin based on an account to be recommended, and acquiring real-time operation behavior data corresponding to the user to be recommended and historical financial product data corresponding to the account to be recommended; taking product data, real-time operation behavior data and historical financial product data corresponding to a plurality of saleable financial products as input data of a prediction model, and determining product interest data corresponding to an account to be recommended through the prediction model; based on the product interest data, determining recommendation sequences corresponding to the plurality of saleable financial products, and recommending the account to be recommended based on the recommendation sequences. By the method, the accuracy of recommendation can be improved, and the real-time performance of recommendation is ensured.
Description
Technical Field
The application relates to the field of finance, in particular to a financial product recommendation method and a related device aiming at a financial cabin.
Background
The user usually has the requirement of purchasing financial products when transacting related business in the financial cabin, and because the quantity of the financial products is usually more, in order to ensure that the user can confirm the financial products suitable for the user and purchase the financial products in a large quantity of the financial products, the financial cabin needs to conduct personalized financial product recommendation for the user, namely the financial cabin usually pushes the financial products suitable for the user to the user through a recommendation system so as to promote sales of the financial products and promote user experience.
In the related art, most recommendation systems mainly depend on historical behavior data of users, that is, the recommendation systems can predict the interest degree of users in financial products based on the historical behavior data of the users, and then determine the financial products suitable for the users according to the interest degree of the users in the financial products. However, the technical solutions in the related art have the problems of low accuracy and poor real-time performance of recommendation.
Disclosure of Invention
The embodiment of the application at least provides a financial product recommendation method and a related device for a financial cabin, by the method, product interest data corresponding to an account to be recommended can be comprehensively determined from multiple dimensions of product data, real-time operation behavior data and historical financial product data, so that the accuracy of recommendation is improved, and meanwhile, the real-time operation behavior data of a user to be recommended can be responded in time when the account to be recommended is recommended, so that the instantaneity of recommendation is guaranteed.
In a first aspect, the present application provides a financial product recommendation method for a financial cabin, including:
determining a plurality of saleable financial products corresponding to a target financial cabin in a current period, and acquiring product data corresponding to the saleable financial products respectively;
responding to login operation of a user to be recommended in the target financial cabin based on an account to be recommended, and acquiring real-time operation behavior data corresponding to the user to be recommended and historical financial product data corresponding to the account to be recommended; the account number to be recommended has a binding relation with the user to be recommended, the real-time operation behavior data are used for identifying the real-time operation behavior of the user to be recommended for a financial product interface in the target financial cabin, and the historical financial product data comprise product data corresponding to a warehouse-holding financial product corresponding to the account number to be recommended;
taking the product data, the real-time operation behavior data and the historical financial product data which respectively correspond to the plurality of saleable financial products as input data of a prediction model, and determining product interest data corresponding to the account to be recommended through the prediction model; the product interest data is used for identifying the interest degree of the user to be recommended on each of the plurality of saleable financial products;
And determining the recommendation sequence corresponding to the plurality of saleable financial products based on the product interest data, and recommending the account to be recommended based on the recommendation sequence.
In a second aspect, the present application further provides a financial product recommendation device for a financial cabin, including:
the first determining unit is used for determining a plurality of saleable financial products corresponding to the target financial cabin in the current period and acquiring product data corresponding to the saleable financial products respectively;
the acquisition unit is used for responding to the login operation of the user to be recommended based on the account to be recommended in the target financial cabin, and acquiring real-time operation behavior data corresponding to the user to be recommended and historical financial product data corresponding to the account to be recommended; the account number to be recommended has a binding relation with the user to be recommended, the real-time operation behavior data are used for identifying the real-time operation behavior of the user to be recommended for a financial product interface in the target financial cabin, and the historical financial product data comprise product data corresponding to a warehouse-holding financial product corresponding to the account number to be recommended;
the second determining unit is used for taking the product data, the real-time operation behavior data and the historical financial product data corresponding to the plurality of saleable financial products as input data of a prediction model, and determining the product interest data corresponding to the account to be recommended through the prediction model; the product interest data is used for identifying the interest degree of the user to be recommended on each of the plurality of saleable financial products;
And the third determining unit is used for determining the recommendation sequence corresponding to the plurality of saleable financial products based on the product interest data and recommending the account to be recommended based on the recommendation sequence.
In a third aspect, the present application further provides an electronic device, including: the financial product recommendation method for the financial cabin comprises a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, when the electronic device runs, the processor and the memory are communicated through the bus, and the machine-readable instructions are executed by the processor to execute the financial product recommendation method for the financial cabin.
In a fourth aspect, the present application also provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the financial product recommendation method for a financial cabin provided herein.
In summary, the present application provides a financial product recommendation method and related devices for a financial cabin, where the method includes: determining a plurality of saleable financial products corresponding to the target financial cabin in the current period, and acquiring product data corresponding to the saleable financial products respectively, so as to avoid recommending financial products which cannot be sold by the target financial cabin to a user to be recommended; responding to login operation of a user to be recommended in a target financial cabin based on the account to be recommended, acquiring real-time operation behavior data corresponding to the user to be recommended and historical financial product data corresponding to the account to be recommended, wherein the account to be recommended has a binding relationship with the user to be recommended, the real-time operation behavior data is used for identifying real-time operation behaviors of the user to be recommended for a financial product interface in the target financial cabin, and the historical financial product data comprises product data corresponding to a holding financial product corresponding to the account to be recommended; taking product data, real-time operation behavior data and historical financial product data corresponding to a plurality of saleable financial products as input data of a prediction model, determining product interest data corresponding to an account to be recommended through the prediction model, wherein the product interest data is used for identifying the interest degree of a user to be recommended on each saleable financial product in the plurality of saleable financial products; based on the product interest data, determining recommendation sequences corresponding to the plurality of saleable financial products, and recommending the account to be recommended based on the recommendation sequences. By the method, the product interest data corresponding to the account to be recommended can be comprehensively determined from the product data, the real-time operation behavior data and the historical financial product data, so that the accuracy of recommendation is improved, and meanwhile, the real-time operation behavior data of the user to be recommended can be responded in time when the account to be recommended is recommended, so that the instantaneity of recommendation is guaranteed.
Other advantages of the present application will be explained in more detail in connection with the following description and accompanying drawings.
It should be understood that the foregoing description is only an overview of the technical solutions of the present application, so that the technical means of the present application can be generally understood and implemented in accordance with the content of the specification. The following specific embodiments of the present application are illustrated in order to make the above and other objects, features and advantages of the present application more comprehensible.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below. The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the technical aspects of the application. It is appreciated that the drawings illustrate only certain embodiments of the application and are therefore not to be considered limiting of its scope, for the invention may admit to other equally relevant drawings without inventive effort to those of ordinary skill in the art. Also, like reference numerals are used to designate like parts throughout the figures. In the drawings:
Fig. 1 is a flowchart of a financial product recommendation method for a financial cabin according to an embodiment of the present application;
fig. 2 is a timing chart corresponding to a training process and an application process of a financial product recommendation method for a financial cabin according to an embodiment of the present application;
fig. 3 is a schematic diagram of a financial product recommendation device for a financial cabin according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
Exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
In the description of embodiments of the present application, it should be understood that terms such as "comprises" or "comprising" are intended to indicate that the disclosed features, numbers, steps, acts, components, portions, or combinations thereof, are present in the specification, and do not preclude the presence or addition of one or more other features, numbers, steps, acts, components, portions, or combinations thereof.
Unless otherwise indicated, "/" means or, e.g., A/B may represent A or B; "and/or" herein is merely an association relationship describing an association object, and means that three relationships may exist, for example, a and/or B may mean: a exists alone, A and B exist together, and B exists alone.
The terms "first," "second," and the like are used merely for convenience of description to distinguish between the same or similar technical features, and are not to be construed as indicating or implying a relative importance or quantity of such technical features. Thus, a feature defined by "first," "second," etc. may explicitly or implicitly include one or more such feature. In the description of embodiments of the present application, the term "plurality" means two or more unless otherwise indicated.
The financial cabin is a financial equipment terminal not limited to banking sites, has a fully-closed operation space, can be movably deployed outside the banking sites, such as a mall, a square, a subway station and the like, and can be used for self-service handling of related services without accompanying related staff. The financial cabin is a movable closed cabin equipment terminal which is composed of an outer cabin application, an outer cabin display screen, an outer cabin body (comprising glass around), an inner cabin application, an inner cabin host, an inner cabin storage device, an inner cabin touch screen, an inner cabin external hardware device, a face camera and the like.
The user usually has the demand of purchasing financial products when handling related business in the financial cabin, because under the background of fast development of financial science and technology, the quantity of financial products is usually more, and the user can meet the trouble when selecting suitable financial products, so in order to let the user confirm the financial products that are fit for oneself in a large amount of financial products and purchase, the financial cabin needs to carry out individualized financial product recommendation for the user, namely the financial cabin usually pushes the financial products that the user is fit for to the user through the recommendation system to promote sales of financial products and promote user experience. However, in a practical process, the recommendation of the financial product to the user faces many challenges, such as massive data, diversity of user demands, complexity of the financial product, etc., so that the recommended financial product may not quickly and accurately meet the personalized demands of the user.
In the related art, some recommendation systems make recommendations with reference to social network data, i.e., the recommendation system can determine financial products suitable for a user by analyzing correlations among the user, the financial products, and the social network. However, this approach may ignore the unique needs and risk preferences of the user in the financial field, resulting in lower accuracy of the recommendation.
Most of recommendation systems mainly depend on historical behavior data of users, namely, the recommendation systems can predict the interest degree of the users in financial products based on the historical behavior data of the users, and then determine the financial products suitable for the users according to the interest degree of the users in the financial products. However, the technical solutions in the related art have the problems of poor real-time performance and low accuracy of recommendation.
In view of this, the application provides a financial product recommendation method and related device for a financial cabin, by which product interest data corresponding to an account to be recommended can be comprehensively determined from multiple dimensions of product data, real-time operation behavior data and historical financial product data, so that accuracy of recommendation is improved, and meanwhile, real-time operation behavior data of a user to be recommended can be responded in time when the account to be recommended is recommended, so that instantaneity of recommendation is guaranteed.
It will be appreciated that in the specific embodiments of the present application, data such as real-time operation behavior, historical financial product data, and error reporting information are involved, and when the embodiments of the present application are applied to specific products or technologies, user permission or consent is required, and the collection, use, and processing of relevant data is required to comply with relevant laws and regulations and standards of relevant countries and regions.
The following describes a financial product recommendation method for a financial cabin provided by the present application through a method embodiment, as shown in fig. 1, fig. 1 is a method flowchart of a financial product recommendation method for a financial cabin provided by the present application, where the method includes:
s101, determining a plurality of saleable financial products corresponding to a target financial cabin in a current period, and acquiring product data corresponding to the saleable financial products respectively.
The financial cabin refers to a financial equipment terminal not limited to banking sites, and in practical application, in order to facilitate users located in different areas to process related businesses, a bank may set a plurality of financial cabins corresponding to a plurality of areas one by one. The plurality of financial cabins are all required to recommend financial products to a user, and for convenience of explanation, any one of the plurality of financial cabins, i.e., a target financial cabin, will be described below as an example.
In this embodiment, in order to avoid network delay and improve operation efficiency, the target financial cabin is equivalent to a local calculator operation terminal, and the provided financial product recommendation method can be implemented by the target financial cabin.
Since financial products that can be sold by the financial cabins in different areas are generally different, in order to avoid recommending financial products that cannot be sold to users in the target financial cabins, the target financial cabins can determine a plurality of saleable financial products corresponding to the target financial cabins in the current period, and the saleable financial products refer to the financial products that can be sold by the corresponding financial cabins, wherein the period time corresponding to the current period can be set by related personnel according to needs, for example, the period time can be set to be a season, a month, a week, a day, etc., and in practical application of the embodiment, the period time is generally set to be a day in order to ensure the accuracy of recommendation, and at this time, the target financial cabins can determine a plurality of saleable financial products corresponding to the target financial cabins every day.
Meanwhile, the target financial cabin may determine product data corresponding to each of the plurality of marketable financial products, wherein the product data refers to various data related to the corresponding financial product, and for example, the product data may include a product name, an investment period, a category, a risk level, a purchase amount, and the like of the corresponding financial product.
It should be noted that, in this embodiment, the target financial cabin may include a corresponding storage module, where the storage module is configured to store product data corresponding to each of the plurality of marketable financial products acquired in S101, so that the target financial cabin may call the product data corresponding to each of the plurality of marketable financial products from the storage module at any time until the current period is over, and update the product data corresponding to each of the plurality of marketable financial products acquired in the next period.
S102, responding to login operation of a user to be recommended in a target financial cabin based on an account to be recommended, and acquiring real-time operation behavior data corresponding to the user to be recommended and historical financial product data corresponding to the account to be recommended.
The account number refers to a virtual identity of a user for logging in the financial cabin to transact related business, the account number can comprise words, numbers, english and the like, the account number and the user have binding relation, and when different users need to transact related business through the financial cabin, the user can log in the financial cabin through the corresponding account number.
In this embodiment, the account to be recommended refers to any account to be recommended for financial products to be recommended, the user corresponding to the account to be recommended is the user to be recommended, the user to be recommended and the account to be recommended have a binding relationship, and during the process that the financial cabin is logged in through the account to be recommended, the user to be recommended can use the financial cabin to transact related business through the account to be recommended.
After the account to be recommended logs in, in order to timely recommend financial products to the account to be recommended when the account to be recommended operates on a financial product interface of the target financial cabin, real-time operation behavior data corresponding to the user to be recommended can be obtained on the basis of obtaining historical financial product data corresponding to the account to be recommended by the target financial cabin, wherein the historical financial product data comprises product data corresponding to a financial product held by the account to be recommended, and the financial product held by the bin refers to the financial product held by the corresponding account; the real-time operation behavior data is used for identifying the real-time operation behavior of the user to be recommended aiming at the financial product interface in the target financial cabin, and the real-time operation behavior can comprise operations such as checking a product specification, checking a product bright point, checking a profit curve and performance trend, checking a transaction rule, checking a product notice, a product protocol and the like of the user to be recommended aiming at the financial product interface.
In one possible implementation, the real-time operational behavior data includes primary real-time operational behavior data and secondary real-time operational behavior data.
The real-time operation behavior data is used for identifying the real-time operation behavior of the user to be recommended aiming at the financial product interface in the target financial cabin, and in order to be capable of more accurately analyzing the operation behavior of the user to be recommended, in this embodiment, the real-time operation behavior data comprises primary real-time operation behavior data and secondary real-time operation behavior data.
The primary real-time operation behavior data is used for identifying primary real-time operation behaviors, the primary real-time operation behaviors refer to simple preliminary operation behaviors generated by corresponding users aiming at financial product interfaces in a target financial cabin, account numbers generate primary real-time operation behaviors on the financial product interfaces, the primary real-time operation behaviors represent that the users corresponding to the account numbers perform simple preliminary interactions on the financial product interfaces, the primary real-time operation behaviors can refer to simple preliminary operation behaviors such as checking product specifications, checking product bright spots, checking income curves and performance trends, checking transaction rules, checking product announcements and product protocols on the financial product interfaces, and at the moment, in order to perform more accurate identification on the primary real-time operation behaviors, the real-time operation behaviors can be identified for a corresponding duration, for example, the real-time operation behaviors can identify browsing duration corresponding to checking the product specifications, and the browsing duration can be calculated by recording the time of entering a page corresponding to the product specifications to be recommended and the page corresponding to exiting the product specifications.
The secondary real-time operation behavior data is used for identifying secondary real-time operation behaviors, the secondary real-time operation behaviors refer to deep operation behaviors generated by corresponding users aiming at financial product interfaces in a target financial cabin, the account numbers generate secondary real-time operation behaviors on the financial product interfaces to represent that the users corresponding to the account numbers perform deep interaction on the financial product interfaces, and the secondary real-time operation behaviors can refer to operation behaviors such as clicking purchase on the financial product interfaces, carrying out customer risk level assessment, carrying out product suitability assessment and the like. It should be noted that, because the user can perform the deep operation action only after performing the simple operation action on the financial product interface, the user generates the first-level real-time operation action on the financial product interface, which is a precondition for the user to generate the second-level real-time operation action on the financial product interface.
In this embodiment, the real-time operation behavior data not only includes the first-level real-time operation behavior data for identifying the first-level real-time operation behavior of the user to be recommended for the financial product interface in the target financial cabin, but also includes the second-level real-time operation behavior data for identifying the second-level real-time operation behavior of the user to be recommended for the financial product interface in the target financial cabin, which is favorable for more comprehensive analysis of the operation behaviors of the user to be recommended in the subsequent steps, thereby ensuring the accuracy of recommendation.
In this embodiment, in order to timely respond to the operation behavior of the user to be recommended for the financial product interface, the target financial cabin may acquire real-time operation behavior data corresponding to the user to be recommended through the sensor or the camera on the premise of obtaining the consent of the user to be recommended.
S103, taking product data, real-time operation behavior data and historical financial product data corresponding to a plurality of saleable financial products as input data of a prediction model, and determining product interest data corresponding to an account to be recommended through the prediction model.
In the related art, most of the recommendation systems mainly depend on historical behavior data of the user, that is, most of the recommendation systems generally predict the interest degree of the user in the financial product only according to the historical behavior data of the user, which may cause the recommendation systems in the related art to fail to refer to the current requirement of the user in real time, that is, the analysis of the requirement of the user by most of the recommendation systems in the related art has hysteresis.
In this regard, after the real-time operation behavior data corresponding to the user to be recommended and the historical financial product data corresponding to the account to be recommended are obtained in S102, the target financial cabin may use not only the historical financial product data as input data of the prediction model, but also the real-time operation behavior data as input data of the prediction model, where the prediction model refers to a model capable of predicting the interest degree of the user in the financial product. The real-time operation behavior data is also used as the input data of the prediction model, so that the prediction model can refer to the knowledge related to the current demand of the user to be recommended, and the prediction model can refer to the current demand of the user to be recommended for more accurate analysis, and the accuracy of recommendation is improved.
Meanwhile, in the related art, product data corresponding to financial products is usually ignored or simply processed, which also affects the accuracy of recommendation.
In this embodiment, the target financial cabin may also use product data corresponding to each of the plurality of marketable financial products as input data of the prediction model, so that the prediction model can learn knowledge related to the marketable financial products, thereby improving accuracy of recommendation.
That is, in this embodiment, the target financial cabin may use product data, real-time operation behavior data, and historical financial product data corresponding to a plurality of marketable financial products as input data of a prediction model, and determine product interest data corresponding to an account to be recommended through the prediction model, where the product interest data is used to identify interest degrees of a user to be recommended on each marketable financial product in the plurality of marketable financial products, that is, the target financial cabin may comprehensively determine product interest data corresponding to the account to be recommended from a plurality of dimensions of the product data, the real-time operation behavior data, and the historical financial product data, thereby improving accuracy of recommendation.
In one possible implementation manner, the target financial cabin may perform data preprocessing on product data, real-time operation behavior data and historical financial product data corresponding to the plurality of marketable financial products respectively; the data quality corresponding to the data after the data pretreatment is greater than the data quality corresponding to the data without the data pretreatment.
In order to ensure the quality of the data, the target financial cabin can be used as the input data of the prediction model after the data is subjected to data preprocessing, and the data preprocessing can comprise cleaning, deduplication, format conversion and the like, so that the data quality after the data preprocessing is higher than the data quality before the data preprocessing.
In one possible implementation, the target financial cabin may acquire error reporting information received by the account to be recommended, and use the error reporting information as input data of the prediction model.
Specifically, the target financial cabin may acquire error reporting information received by the account to be recommended, where the error reporting information refers to information for reporting errors received by the account in a process of purchasing the financial product based on the account, for example, when the user a purchases the financial product a, if the user a does not satisfy the purchase condition of the financial product a, the account a corresponding to the user a will receive error reporting information prompting the user not to satisfy the purchase condition.
After the error reporting information is acquired, the target financial cabin can take the error reporting information as input data of the prediction model, so that the prediction model can learn relevant knowledge of the error reporting information when determining the product interest data, and further financial products which can generate the error reporting information are prevented from being recommended to users to be recommended.
In one possible implementation, the predictive model may be trained as follows:
s11, obtaining product data corresponding to a plurality of financial products respectively;
s12, responding to login operation of a sample user based on a sample account, and acquiring real-time operation behavior sample data corresponding to the sample user and historical financial product sample data corresponding to the sample account; the sample user has a binding relation with the sample account, the real-time operation behavior training data is used for identifying the real-time operation behavior of the sample user aiming at the financial product interface, and the historical financial product sample data comprises product data corresponding to a warehouse holding financial product corresponding to the sample account;
s13, taking product data, real-time operation behavior sample data and historical financial product sample data corresponding to a plurality of financial products as input data of an initial prediction model, and determining product interest sample data corresponding to a sample account through the initial prediction model; the product interest sample data is used for identifying the interest degree of a sample user on each financial product in the plurality of financial products respectively;
s14, training the initial prediction model based on the difference between the sample label corresponding to the sample account number and the sample interest sample data to obtain the prediction model.
The prediction model refers to a model capable of predicting the interest degree of a user in financial products, and the initial prediction model refers to an initial model which can be trained by a training sample to obtain the prediction model.
The target financial cabin can firstly acquire product data corresponding to a plurality of financial products respectively, so that the product data corresponding to the financial products respectively in the subsequent steps are used as input data of an initial prediction model.
In the training process, the sample account number refers to any account number used as a training sample, a user corresponding to the sample account number is a sample user, the sample user and the sample account number have a binding relationship, and the sample user can log in the financial cabin based on the sample account number.
In order to acquire corresponding data to train the initial prediction model, a sample user can log in based on a sample account, at this time, a target financial cabin can acquire real-time operation behavior sample data corresponding to the sample user and historical financial product sample data corresponding to the sample account, wherein the real-time operation behavior training data is used for identifying real-time operation behaviors of the sample user aiming at a financial product interface, and the historical financial product sample data comprises product data corresponding to a holding financial product corresponding to the sample account.
The target financial cabin can take product data, real-time operation behavior sample data and historical financial product sample data corresponding to a plurality of financial products respectively as input data of an initial prediction model, and product interest sample data corresponding to a sample account number is determined through the initial prediction model, wherein the product interest sample data is used for identifying the interest degree of a sample user on each financial product in the plurality of financial products respectively.
After determining the product interest sample data corresponding to the sample account, the target financial cabin may train the initial prediction model based on a difference between the product interest sample data and a sample label corresponding to the sample account, where the sample label is used to identify a real interest level of the sample user on each of the plurality of financial products, and for example, a deep learning algorithm may be used to train the initial prediction model. During the training process, the target financial cabin can be trained and optimized by using the cross entropy loss function, and a proper optimizer can be selected, for example, two optimizers of adaptive learning rate (Adaptive Moment Estimation, adam) or random gradient descent (Stochastic Gradient Descent, SGD) can be selected, and a corresponding prediction model can be obtained through training.
It should be noted that, in this embodiment, the trained prediction model may be stored in the storage module of the target financial cabin, so that the relevant steps can be invoked in time.
In one possible implementation manner, the target financial cabin may cluster product data corresponding to a plurality of financial products respectively to obtain a plurality of product data sets, and use the plurality of product data sets as input data of an initial prediction model.
Specifically, when recommending financial products for a user, the user usually has a certain preference for a certain type of financial product, and for this purpose, the target financial cabin can cluster product data corresponding to a plurality of financial products respectively to obtain a plurality of product data sets, where each product data set includes product data corresponding to a plurality of financial products belonging to the same type.
After obtaining the plurality of product data sets, the target financial cabin can take the plurality of product data sets as input data of the initial prediction model, so that the initial prediction model can better learn related knowledge of financial products belonging to the same type in the training process.
It should be noted that, by clustering the product data corresponding to the plurality of financial products, some abnormal product data can be identified, so that further cleaning and processing of the data can be realized.
In one possible implementation manner, the target financial cabin may cluster the real-time operation behavior sample data corresponding to the plurality of sample users respectively to obtain a plurality of real-time operation behavior sample data sets, and use the plurality of real-time operation behavior sample data sets as input data of the initial prediction model.
Specifically, when recommending financial products for users, users of the same type generally have similar operation behavior patterns, and for this purpose, the target financial cabin may cluster real-time operation behavior sample data corresponding to a plurality of sample users respectively, so as to obtain a plurality of real-time operation behavior sample data sets, where each real-time operation behavior sample data set includes real-time operation behavior sample data corresponding to sample users belonging to the same type respectively.
After obtaining the plurality of real-time operation behavior sample data sets, the target financial cabin can use the plurality of real-time operation behavior sample data sets as input data of the initial prediction model, so that the initial prediction model can better learn related knowledge of users belonging to the same type in the training process.
It should be noted that, through clustering the real-time operation behavior sample data corresponding to the plurality of sample users, some abnormal real-time operation behavior sample data can be identified, so that further cleaning and processing of the data are realized.
In one possible implementation, the target financial cabin may evaluate the prediction model according to the test sample, and determine an accuracy index corresponding to the prediction model;
and if the accuracy index does not meet the qualification condition, adjusting model parameters of the prediction model.
After training the initial prediction model to obtain the prediction model, in order to ensure the effectiveness of the prediction model, the target financial cabin can evaluate the prediction model according to the test sample to determine the accuracy index corresponding to the prediction model.
If the accuracy index does not meet the qualification condition, wherein the qualification condition can be set by related staff as required, the accuracy of the prediction model is lower, and the target financial cabin can adjust model parameters of the prediction model so as to optimize the model performance of the prediction model and improve the recommended accuracy.
S104, determining recommendation sequences corresponding to the plurality of saleable financial products based on the product interest data, and recommending the account to be recommended based on the recommendation sequences.
After determining the product interest data in S103, since the product interest data is used to identify the interest degree of the user to be recommended in each of the plurality of saleable financial products, the target financial cabin may determine the recommendation order corresponding to the plurality of saleable financial products based on the product interest data, and specifically, the target financial cabin may rank the saleable financial products with higher interest degree of the user to be recommended before and rank the saleable financial products with lower interest degree of the user to be recommended after.
After determining the recommendation sequence, the target financial cabin can recommend the account to be recommended based on the recommendation sequence, namely, the target financial cabin can sequentially recommend the account to be recommended based on the recommendation sequence, so that a user to be recommended can sequentially check corresponding saleable financial products according to the recommendation sequence.
Through the steps from S101 to S104, after the user to be recommended logs in based on the account to be recommended, the real-time operation behavior data of the user to be recommended can be responded, the account to be recommended is timely recommended, and the real-time performance of the recommendation is ensured.
The training process and the application process corresponding to the financial product recommendation method provided by the application are integrally described below based on fig. 2:
at time t1, the user data acquisition module may acquire real-time operation behavior data of the user, and the product data acquisition module may acquire historical financial product data corresponding to the account number.
At time t2, the data preprocessing module can receive the real-time operation behavior data and the historical financial product data, and starts to perform the processes of cleaning, deduplication, format conversion and the like.
At time t3, the model training module receives the preprocessed data and trains the initial prediction model, so that a trained prediction model is obtained.
At time t4, the real-time recommendation module can receive the trained prediction model, and predicts the interest degrees corresponding to the plurality of saleable financial products respectively by the user to be recommended through the prediction model according to the real-time operation behavior data corresponding to the user to be recommended.
It can be seen that the present application provides a financial product recommendation method and related device for a financial cabin, the method comprising: determining a plurality of saleable financial products corresponding to the target financial cabin in the current period, and acquiring product data corresponding to the saleable financial products respectively, so as to avoid recommending financial products which cannot be sold by the target financial cabin to a user to be recommended; responding to login operation of a user to be recommended in a target financial cabin based on the account to be recommended, acquiring real-time operation behavior data corresponding to the user to be recommended and historical financial product data corresponding to the account to be recommended, wherein the account to be recommended has a binding relationship with the user to be recommended, the real-time operation behavior data is used for identifying real-time operation behaviors of the user to be recommended for a financial product interface in the target financial cabin, and the historical financial product data comprises product data corresponding to a holding financial product corresponding to the account to be recommended; taking product data, real-time operation behavior data and historical financial product data corresponding to a plurality of saleable financial products as input data of a prediction model, determining product interest data corresponding to an account to be recommended through the prediction model, wherein the product interest data is used for identifying the interest degree of a user to be recommended on each saleable financial product in the plurality of saleable financial products; based on the product interest data, determining recommendation sequences corresponding to the plurality of saleable financial products, and recommending the account to be recommended based on the recommendation sequences. By the method, the product interest data corresponding to the account to be recommended can be comprehensively determined from the product data, the real-time operation behavior data and the historical financial product data, so that the accuracy of recommendation is improved, and meanwhile, the real-time operation behavior data of the user to be recommended can be responded in time when the account to be recommended is recommended, so that the instantaneity of recommendation is guaranteed.
In the description of the present specification, descriptions with reference to the terms "some possible embodiments," "some embodiments," "examples," "specific examples," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiments or examples is included in at least one embodiment or example of the present application, and that the above terms do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the various embodiments or examples described in this specification and the features of the various embodiments or examples may be combined and combined by those skilled in the art without contradiction.
With respect to the method flowcharts of the embodiments of the present application, certain operations are described as distinct steps performed in a certain order. Such a flowchart is illustrative and not limiting. Some steps described herein may be grouped together and performed in a single operation, or may be divided into multiple sub-steps and may be performed in an order different than that shown herein. The various steps illustrated in the flowcharts may be implemented in any manner by any circuit structure and/or tangible mechanism (e.g., by software running on a computer device, hardware (e.g., processor or chip implemented logic functions), etc., and/or any combination thereof).
It will be appreciated by those skilled in the art that in the methods described in the above embodiments, the written order of steps does not imply a strict order of execution, and that the specific order of execution of the steps should be determined by its function and possible inherent logic.
1-2, the financial product recommendation device for a financial cabin provided in the present application is described below through device embodiments, as shown in FIG. 3, the financial product recommendation device 300 for a financial cabin includes:
a first determining unit 301, configured to determine a plurality of saleable financial products corresponding to a target financial cabin in a current period, and acquire product data corresponding to the plurality of saleable financial products respectively;
the acquiring unit 302 is configured to acquire real-time operation behavior data corresponding to a user to be recommended and historical financial product data corresponding to the account to be recommended in response to a login operation of the user to be recommended in the target financial cabin based on the account to be recommended; the account number to be recommended has a binding relation with the user to be recommended, the real-time operation behavior data are used for identifying the real-time operation behavior of the user to be recommended for a financial product interface in the target financial cabin, and the historical financial product data comprise product data corresponding to a warehouse-holding financial product corresponding to the account number to be recommended;
A second determining unit 303, configured to determine, according to a prediction model, product interest data corresponding to the account to be recommended, where the product data, the real-time operation behavior data, and the historical financial product data respectively corresponding to the plurality of saleable financial products are used as input data of the prediction model; the product interest data is used for identifying the interest degree of the user to be recommended on each of the plurality of saleable financial products;
and a third determining unit 304, configured to determine a recommendation order corresponding to the plurality of saleable financial products based on the product interest data, and recommend the account to be recommended based on the recommendation order.
In one possible implementation, the financial product recommendation device 300 for a financial cabin further includes a training unit for:
acquiring product data corresponding to a plurality of financial products respectively;
responding to login operation of a sample user based on a sample account, and acquiring real-time operation behavior sample data corresponding to the sample user and historical financial product sample data corresponding to the sample account; the sample user has a binding relation with the sample account, the real-time operation behavior training data is used for identifying the real-time operation behavior of the sample user aiming at a financial product interface, and the historical financial product sample data comprises product data corresponding to a warehouse-holding financial product corresponding to the sample account;
Taking product data, the real-time operation behavior sample data and the historical financial product sample data corresponding to the plurality of financial products respectively as input data of an initial prediction model, and determining product interest sample data corresponding to the sample account through the initial prediction model; the product interest sample data is used for identifying the interest degree of the sample user on each financial product in the plurality of financial products respectively;
and training the initial prediction model based on the difference between the product interest sample data and the sample label corresponding to the sample account number to obtain the prediction model.
In a possible implementation, the training unit is further configured to:
clustering product data corresponding to a plurality of financial products respectively to obtain a plurality of product data sets, and taking the plurality of product data sets as input data of the initial prediction model.
In a possible implementation, the training unit is further configured to:
clustering the real-time operation behavior sample data respectively corresponding to a plurality of sample users to obtain a plurality of real-time operation behavior sample data sets, and taking the plurality of real-time operation behavior sample data sets as input data of the initial prediction model.
In a possible implementation, the training unit is further configured to:
evaluating the prediction model according to a sample to be tested, and determining an accuracy index corresponding to the prediction model;
and if the accuracy index does not meet the qualification condition, adjusting model parameters of the prediction model.
In one possible implementation, the real-time operational behavior data includes primary real-time operational behavior data and secondary real-time operational behavior data.
In a possible implementation, the obtaining unit 302 is further configured to:
and acquiring error reporting information received by the account to be recommended, and taking the error reporting information as input data of the prediction model.
In one possible implementation, the financial product recommendation device 300 for a financial cabin further includes a data preprocessing unit, configured to:
carrying out data preprocessing on the product data, the real-time operation behavior data and the historical financial product data which respectively correspond to the plurality of saleable financial products; the data quality corresponding to the data after the data pretreatment is greater than the data quality corresponding to the data without the data pretreatment.
It should be noted that, the apparatus in the embodiments of the present application may implement each process of the foregoing method embodiment and achieve the same effects and functions, which are not described herein again.
The embodiment of the application also provides an electronic device, as shown in fig. 4, which is a schematic structural diagram of the electronic device provided in the embodiment of the application, including: a processor 401, a memory 402, and a bus 403. The memory 402 stores machine-readable instructions executable by the processor 401 (e.g., execution instructions corresponding to the first determining unit 301, the acquiring unit 302, the second determining unit 303, and the third determining unit 304 in the apparatus of fig. 3, etc.), when the electronic device is running, the processor 401 communicates with the memory 402 through the bus 403, and when the machine-readable instructions are executed by the processor 401, the following processing is performed:
determining a plurality of saleable financial products corresponding to a target financial cabin in a current period, and acquiring product data corresponding to the saleable financial products respectively;
responding to login operation of a user to be recommended in the target financial cabin based on an account to be recommended, and acquiring real-time operation behavior data corresponding to the user to be recommended and historical financial product data corresponding to the account to be recommended; the account number to be recommended has a binding relation with the user to be recommended, the real-time operation behavior data are used for identifying the real-time operation behavior of the user to be recommended for a financial product interface in the target financial cabin, and the historical financial product data comprise product data corresponding to a warehouse-holding financial product corresponding to the account number to be recommended;
Taking the product data, the real-time operation behavior data and the historical financial product data which respectively correspond to the plurality of saleable financial products as input data of a prediction model, and determining product interest data corresponding to the account to be recommended through the prediction model; the product interest data is used for identifying the interest degree of the user to be recommended on each of the plurality of saleable financial products;
and determining the recommendation sequence corresponding to the plurality of saleable financial products based on the product interest data, and recommending the account to be recommended based on the recommendation sequence.
The embodiment of the application further provides a computer readable storage medium, and a computer program is stored on the computer readable storage medium, and when the computer program is executed by a processor, the steps of the financial product recommendation method for a financial cabin described in the embodiment of the method are executed. Wherein the storage medium may be a volatile or nonvolatile computer readable storage medium.
The embodiments of the present application further provide a computer program product, where the computer program product carries program code, and instructions included in the program code may be used to execute the steps of the financial product recommendation method for a financial cabin described in the foregoing method embodiments, and specifically reference may be made to the foregoing method embodiments, which are not repeated herein.
Wherein the above-mentioned computer program product may be realized in particular by means of hardware, software or a combination thereof. In an alternative embodiment, the computer program product is embodied as a computer storage medium, and in another alternative embodiment, the computer program product is embodied as a software product, such as a software development kit (Software Development Kit, SDK), or the like.
The various embodiments in this application are described in a progressive manner, and the same or similar portions of each embodiment may be found in each other, each embodiment focusing on differences from the other embodiments. In particular, for apparatus, devices and computer readable storage medium embodiments, the description thereof is simplified as it is substantially similar to the method embodiments, as relevant points may be found in part in the description of the method embodiments.
The apparatus, the device, and the computer readable storage medium provided in the embodiments of the present application are in one-to-one correspondence with the methods, and therefore, the apparatus, the device, and the computer readable storage medium also have similar beneficial technical effects as the corresponding methods, and since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the apparatus, the device, and the computer readable storage medium are not repeated here.
It will be apparent to those skilled in the art that embodiments of the present application may be embodied in methods and apparatus (devices or systems), or in computer-readable storage media. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer-readable storage medium embodied in one or more computer-usable storage media including, but not limited to, magnetic disk storage, compact disk read-only memory (CD-ROM), optical storage, and the like.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (devices or systems) and computer-readable storage media according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory, random Access Memory (RAM), and/or nonvolatile memory, such as Read Only Memory (ROM) or Flash memory (Flash RAM), among others, in a computer readable medium. Memory is an example of computer-readable media.
Computer-readable media include both permanent and non-permanent, removable and non-removable media, and information storage may be implemented by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer-readable 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, read only memory, electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, CD-ROM, digital Versatile Disks (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Furthermore, although the operations of the methods of the present application are depicted in the drawings in a particular order, this is not required to either imply that the operations must be performed in that particular order or that all of the illustrated operations be performed to achieve desirable results. In addition, some steps may be omitted, multiple steps may be combined into one step to be performed, and/or one step may be decomposed into multiple sub-steps to be performed.
While the spirit and principles of the present application have been described above with reference to several embodiments, it should be understood that the application is not limited to the particular embodiments disclosed nor does the division of aspects mean that features in these aspects cannot be combined. The application is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.
Claims (11)
1. A financial product recommendation method for a financial cabin is characterized by comprising the following steps:
determining a plurality of saleable financial products corresponding to a target financial cabin in a current period, and acquiring product data corresponding to the saleable financial products respectively;
responding to login operation of a user to be recommended in the target financial cabin based on an account to be recommended, and acquiring real-time operation behavior data corresponding to the user to be recommended and historical financial product data corresponding to the account to be recommended; the account number to be recommended has a binding relation with the user to be recommended, the real-time operation behavior data are used for identifying the real-time operation behavior of the user to be recommended for a financial product interface in the target financial cabin, and the historical financial product data comprise product data corresponding to a warehouse-holding financial product corresponding to the account number to be recommended;
Taking the product data, the real-time operation behavior data and the historical financial product data which respectively correspond to the plurality of saleable financial products as input data of a prediction model, and determining product interest data corresponding to the account to be recommended through the prediction model; the product interest data is used for identifying the interest degree of the user to be recommended on each of the plurality of saleable financial products;
and determining the recommendation sequence corresponding to the plurality of saleable financial products based on the product interest data, and recommending the account to be recommended based on the recommendation sequence.
2. The method according to claim 1, wherein the predictive model is trained by:
acquiring product data corresponding to a plurality of financial products respectively;
responding to login operation of a sample user based on a sample account, and acquiring real-time operation behavior sample data corresponding to the sample user and historical financial product sample data corresponding to the sample account; the sample user has a binding relation with the sample account, the real-time operation behavior training data is used for identifying the real-time operation behavior of the sample user aiming at a financial product interface, and the historical financial product sample data comprises product data corresponding to a warehouse-holding financial product corresponding to the sample account;
Taking product data, the real-time operation behavior sample data and the historical financial product sample data corresponding to the plurality of financial products respectively as input data of an initial prediction model, and determining product interest sample data corresponding to the sample account through the initial prediction model; the product interest sample data is used for identifying the interest degree of the sample user on each financial product in the plurality of financial products respectively;
and training the initial prediction model based on the difference between the product interest sample data and the sample label corresponding to the sample account number to obtain the prediction model.
3. The method according to claim 2, wherein the method further comprises:
clustering product data corresponding to a plurality of financial products respectively to obtain a plurality of product data sets, and taking the plurality of product data sets as input data of the initial prediction model.
4. The method according to claim 2, wherein the method further comprises:
clustering the real-time operation behavior sample data respectively corresponding to a plurality of sample users to obtain a plurality of real-time operation behavior sample data sets, and taking the plurality of real-time operation behavior sample data sets as input data of the initial prediction model.
5. The method according to claim 2, wherein the method further comprises:
evaluating the prediction model according to a sample to be tested, and determining an accuracy index corresponding to the prediction model;
and if the accuracy index does not meet the qualification condition, adjusting model parameters of the prediction model.
6. The method of claim 1, wherein the real-time operational behavior data comprises primary real-time operational behavior data and secondary real-time operational behavior data.
7. The method according to claim 1, wherein the method further comprises:
and acquiring error reporting information received by the account to be recommended, and taking the error reporting information as input data of the prediction model.
8. The method according to claim 1, wherein the method further comprises:
carrying out data preprocessing on the product data, the real-time operation behavior data and the historical financial product data which respectively correspond to the plurality of saleable financial products; the data quality corresponding to the data after the data pretreatment is greater than the data quality corresponding to the data without the data pretreatment.
9. A financial product recommendation device for a financial cabin, comprising:
The first determining unit is used for determining a plurality of saleable financial products corresponding to the target financial cabin in the current period and acquiring product data corresponding to the saleable financial products respectively;
the acquisition unit is used for responding to the login operation of the user to be recommended based on the account to be recommended in the target financial cabin, and acquiring real-time operation behavior data corresponding to the user to be recommended and historical financial product data corresponding to the account to be recommended; the account number to be recommended has a binding relation with the user to be recommended, the real-time operation behavior data are used for identifying the real-time operation behavior of the user to be recommended for a financial product interface in the target financial cabin, and the historical financial product data comprise product data corresponding to a warehouse-holding financial product corresponding to the account number to be recommended;
the second determining unit is used for taking the product data, the real-time operation behavior data and the historical financial product data corresponding to the plurality of saleable financial products as input data of a prediction model, and determining the product interest data corresponding to the account to be recommended through the prediction model; the product interest data is used for identifying the interest degree of the user to be recommended on each of the plurality of saleable financial products;
And the third determining unit is used for determining the recommendation sequence corresponding to the plurality of saleable financial products based on the product interest data and recommending the account to be recommended based on the recommendation sequence.
10. An electronic device, comprising: a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory in communication over the bus when the electronic device is running, the machine-readable instructions when executed by the processor performing the financial product recommendation method for a financial compartment of any one of claims 1 to 8.
11. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a computer program which, when executed by a processor, performs the financial product recommendation method for a financial compartment according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311708989.7A CN117893273A (en) | 2023-12-11 | 2023-12-11 | Financial product recommendation method and related device for financial cabin |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311708989.7A CN117893273A (en) | 2023-12-11 | 2023-12-11 | Financial product recommendation method and related device for financial cabin |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117893273A true CN117893273A (en) | 2024-04-16 |
Family
ID=90651394
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311708989.7A Pending CN117893273A (en) | 2023-12-11 | 2023-12-11 | Financial product recommendation method and related device for financial cabin |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117893273A (en) |
-
2023
- 2023-12-11 CN CN202311708989.7A patent/CN117893273A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Barigozzi et al. | Do euro area countries respond asymmetrically to the common monetary policy? | |
| US20180268318A1 (en) | Training classification algorithms to predict end-user behavior based on historical conversation data | |
| WO2021174811A1 (en) | Prediction method and prediction apparatus for traffic flow time series | |
| Orlando et al. | Forecasting interest rates through Vasicek and CIR models: A partitioning approach | |
| Breitung et al. | A canonical correlation approach for selecting the number of dynamic factors | |
| Mizen et al. | Forecasting US bond default ratings allowing for previous and initial state dependence in an ordered probit model | |
| Wegener et al. | Forecasting government bond yields with neural networks considering cointegration | |
| CN113627566A (en) | Early warning method and device for phishing and computer equipment | |
| CN112017056A (en) | Intelligent double-recording method and system | |
| CA2845645A1 (en) | In the market model systems and methods | |
| CN113837596A (en) | Fault determination method and device, electronic equipment and storage medium | |
| CN111181757B (en) | Information security risk prediction method and device, computing equipment and storage medium | |
| Melecky et al. | Placing bank supervision in the central bank: Implications for financial stability based on evidence from the global crisis | |
| Molinari | Joint analysis of the non-linear debt–growth nexus and cash-flow sensitivity: New evidence from Italy | |
| Arčabić | Technology, employment and the business cycle in post-transition countries of the EU | |
| CN117893273A (en) | Financial product recommendation method and related device for financial cabin | |
| Berteloot et al. | A novel credit rating migration modeling approach using macroeconomic indicators | |
| Flores-Jimeno et al. | Dynamic analysis of different business failure process | |
| US11715037B2 (en) | Validation of AI models using holdout sets | |
| CN111143220B (en) | Training system and method for software test | |
| Aimer et al. | The asymmetric impact of oil price shocks on economic uncertainty: evidence from the asymmetric NARDL model | |
| Bustamante et al. | Predictive academic performance model to support, prevent and decrease the university dropout rate | |
| CN112200602A (en) | Neural network model training method and device for advertisement recommendation | |
| Kang | Fraud Detection in Mobile Money Transactions Using Machine Learning | |
| Kohvakka | Forecasting univariate time series–comparison of statistical methods and software resources available to undergraduate students |
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 |