CN113011985A - Financial product push data processing method and device - Google Patents
Financial product push data processing method and device Download PDFInfo
- Publication number
- CN113011985A CN113011985A CN202110503905.0A CN202110503905A CN113011985A CN 113011985 A CN113011985 A CN 113011985A CN 202110503905 A CN202110503905 A CN 202110503905A CN 113011985 A CN113011985 A CN 113011985A
- Authority
- CN
- China
- Prior art keywords
- user
- financial product
- data
- determining
- financial
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 13
- 238000000034 method Methods 0.000 claims abstract description 35
- 230000006870 function Effects 0.000 claims description 61
- 238000012545 processing Methods 0.000 claims description 33
- 238000004590 computer program Methods 0.000 claims description 13
- 238000012216 screening Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 abstract description 20
- 238000004422 calculation algorithm Methods 0.000 abstract description 13
- 230000007547 defect Effects 0.000 abstract description 7
- 238000005516 engineering process Methods 0.000 abstract description 6
- 238000006243 chemical reaction Methods 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 12
- 230000006399 behavior Effects 0.000 description 11
- 239000011159 matrix material Substances 0.000 description 11
- 238000004364 calculation method Methods 0.000 description 10
- 238000004891 communication Methods 0.000 description 7
- 238000012549 training Methods 0.000 description 6
- 239000000872 buffer Substances 0.000 description 4
- 230000008859 change Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 235000010469 Glycine max Nutrition 0.000 description 1
- 244000068988 Glycine max Species 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 239000008157 edible vegetable oil Substances 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/06—Asset management; Financial planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Development Economics (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Human Resources & Organizations (AREA)
- Operations Research (AREA)
- Technology Law (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a financial product push data processing method and device, relating to the field of finance, wherein the method comprises the following steps: acquiring transaction data of a financial product of a user; determining a similar user set of the current user according to the user financial product transaction data; and generating financial product pushing data of the current user according to the similar user set and a product pushing model determined in advance according to a position attenuation function. The method overcomes the defects in the prior collaborative filtering recommendation algorithm technology, provides an effective method, has higher recommendation accuracy, can effectively extract the characteristic attribute of the financial product by utilizing the context information capable of reflecting the user interest, and improves the conversion rate and click rate of the system by analyzing the user behavior data by combining the product push model determined by the similar user through the position attenuation function.
Description
Technical Field
The invention relates to a data processing technology, in particular to a financial product push data processing method and device.
Background
The collaborative filtering recommendation algorithm method is a personalized service quality prediction technology which is widely applied. The main idea of collaborative filtering is to determine a set of similar users or services based on pearson correlation coefficients. And then making a prediction based on the quality of service values provided by different users. In general, collaborative filtering can be divided into neighbor-based (or memory-based) collaborative filtering and model-based collaborative filtering. The memory-based collaborative filtering itself is divided into user-based collaborative filtering and project-based collaborative filtering. The collaborative filtering based on the users uses the Pearson correlation coefficient to find a group of nearest neighbor users with similar interests, and the collaborative filtering based on the items calculates the similarity of the items.
Based on the collaborative filtering algorithm of the users, when the users need personalized recommendation, other users similar to the users can be found first, similarity calculation is generally carried out on score value vectors of products which are evaluated together among the users, and products which are liked by the similar users and are unknown to the current users are recommended to the users.
Most of the existing recommendation systems recommend products such as movies and books, and data characteristics of clear scores of the products by users usually exist in the types of users and products, and the scoring characteristics can be directly used for calculation and prediction.
Disclosure of Invention
In order to solve at least one defect in the pushing of the financial products in the prior art, the invention provides a data processing method for pushing the financial products, which comprises the following steps:
acquiring transaction data of a financial product of a user;
determining a similar user set of the current user according to the user financial product transaction data;
and generating financial product pushing data of the current user according to the similar user set and a product pushing model determined in advance according to a position attenuation function.
In an embodiment of the present invention, the financial product transaction data includes: the method comprises the steps of purchasing financial product details by a user, calculating and recording recent earning rate, statistical data of transaction times and frequency of the financial product purchased by the user, a self-selected product list of the user, click and view times of the financial product by the user and browsing time length data.
In an embodiment of the present invention, the determining the set of similar users of the current user according to the user financial product transaction data includes:
determining a user financial product transaction score and a user financial product transaction average score according to the user financial product transaction data;
determining similarity between users by using a Pearson correlation coefficient according to the user financial product transaction score and the user financial product transaction average score;
and determining a similar user set of the current user according to the determined similarity between the users and a preset threshold value for selecting similar users.
In an embodiment of the present invention, the generating of the financial product push data of the current user according to the similar user set and the product push model determined in advance according to the position decay function includes:
acquiring distance data of a user;
determining a position attenuation function according to the distance data and a preset position attenuation coefficient;
determining a prediction score of the financial product according to the user financial product transaction score of the user, the user financial product transaction average score, the similarity of the users in the similar user set and the determined position attenuation function;
and generating the financial product pushing data of the current user according to the determined prediction scores.
In an embodiment of the present invention, the generating financial product push data of the current user according to the determined prediction score includes:
determining a financial product set to be pushed according to financial products purchased by a current user;
and determining the financial product pushing data of the current user according to the financial product set and the prediction scores of the financial products in the financial product set.
Meanwhile, the invention also provides a financial product push data processing device, which comprises:
the data acquisition module is used for acquiring the transaction data of the financial products of the user;
the similar set determining module is used for determining a similar user set of the current user according to the user financial product transaction data;
and the push data determining module is used for generating the financial product push data of the current user according to the similar user set and a product push model determined in advance according to a position attenuation function.
In the embodiment of the present invention, the similarity set determining module includes:
the scoring unit is used for determining a user financial product transaction score and a user financial product transaction average score according to the user financial product transaction data;
the similarity determining unit is used for determining the similarity between the users by using a Pearson correlation coefficient according to the user financial product transaction score and the user financial product transaction average score;
and the set selection unit is used for determining a similar user set of the current user according to the determined similarity between the users and a preset threshold value for selecting similar users.
In the embodiment of the present invention, the pushed data determining module includes:
a distance data acquisition unit for acquiring distance data of a user;
the attenuation function determining unit is used for determining a position attenuation function according to the distance data and a preset position attenuation coefficient;
the system comprises a prediction scoring unit, a position attenuation function determining unit and a position estimation unit, wherein the prediction scoring unit is used for determining the prediction scoring of the financial products according to the user financial product transaction scoring of the user, the user financial product transaction average scoring, the similarity of the users in the similar user set and the determined position attenuation function;
and the push data determining unit is used for generating the push data of the financial products of the current user according to the determined prediction scores.
In this embodiment of the present invention, the pushed data determining unit includes:
the screening unit is used for determining a financial product set to be pushed according to financial products purchased by a current user;
and the data processing unit is used for determining the financial product pushing data of the current user according to the financial product set and the prediction scores of the financial products in the financial product set.
Meanwhile, the invention also provides computer equipment which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor realizes the method when executing the computer program.
Meanwhile, the invention also provides a computer readable storage medium, and a computer program for executing the method is stored in the computer readable storage medium.
The financial product push data processing method and device provided by the invention are used for acquiring the transaction data of the financial product of a user; and determining a similar user set of the current user according to the financial product transaction data of the user, and generating the financial product pushing data of the current user according to the similar user set and a product pushing model determined in advance according to a position attenuation function. And analyzing user behavior data by combining a product pushing model determined by similar users through a position attenuation function, and improving the conversion rate and click rate of the system. The method overcomes the defect that the traditional collaborative filtering algorithm in the prior art lacks transitions which more objectively reflect the interests of the user in different contexts. The method and the device have the advantages that the defects in the conventional collaborative filtering recommendation algorithm technology are overcome, the recommendation accuracy is higher, context information capable of reflecting the user interest is utilized, and the characteristic attributes of the financial products can be effectively extracted.
In order to make the aforementioned and other objects, features and advantages of the invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart of a data processing method for pushing financial products according to the present invention;
FIG. 2 is a schematic flow chart of an embodiment of the present invention;
FIG. 3 is a block diagram of a financial product push data processing apparatus provided in the present invention;
fig. 4 is a schematic diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the prior art, when the user similarity is calculated, the user similarity is calculated by using a collaborative filtering algorithm based on users, and the calculation of the similarity of the users is greatly influenced by the context of the users, including time, place, mood and the like. Moreover, when large data sets and sparse data are faced, the similarity calculation is inaccurate due to the traditional collaborative filtering algorithm based on the user, and therefore the accuracy of the recommendation system is affected. At present, a common website or system collects the interest degrees of users in different projects through a mode that the users directly score the projects, and the obtained data scene is single; in addition, many websites or systems are unable to explicitly collect a user's direct rating of a project for business function reasons.
Aiming at the problems in the prior art, the method solves the problem of information overload, is widely applied to electronic commerce, movies, music and books, improves the conversion rate and click rate of a financial product pushing system by analyzing user behavior data, and overcomes the problem that the traditional collaborative filtering algorithm in the prior art lacks the transition which can more objectively reflect the interest of users in different contexts.
The invention provides a financial product push data processing method, as shown in fig. 1, the method of the invention comprises the following steps:
step S101, acquiring transaction data of a financial product of a user;
step S102, determining a similar user set of the current user according to the user financial product transaction data;
and step S103, generating financial product pushing data of the current user according to the similar user set and a product pushing model determined in advance according to a position attenuation function.
The financial product push data processing method provided by the invention determines a similar user set of a current user according to the financial product transaction data of the user, generates financial product push data of the current user according to the similar user set and a product push model determined in advance according to a position attenuation function, and analyzes user behavior data by combining the product push model determined by the similar user through the position attenuation function, thereby improving the conversion rate and click rate of the system.
In an embodiment of the present invention, the financial product transaction data includes: the method comprises the steps of purchasing financial product details by a user, calculating and recording recent earning rate, statistical data of transaction times and frequency of the financial product purchased by the user, a self-selected product list of the user, click and view times of the financial product by the user and browsing time length data.
The financial product recommendation method provided by the invention records the detail of financial products purchased by all users, calculates and records the recent income rate, counts the transaction times and frequency of the financial products purchased by the users, records the self-selected product list of the users, records the click check times of the users on the financial products, the browsing time length and other data, determines the similar user set of the current users according to the transaction data of the financial products of the users, and recommends the financial products which can create income for the clients as much as possible for the financial products through the similar users.
In an embodiment of the present invention, determining the set of similar users of the current user according to the user financial product transaction data includes:
determining a user financial product transaction score and a user financial product transaction average score according to the user financial product transaction data;
determining similarity between users by using a Pearson correlation coefficient according to the user financial product transaction score and the user financial product transaction average score;
and determining a similar user set of the current user according to the determined similarity between the users and a preset threshold value for selecting similar users.
The invention can select to purchase the same products more preferentially through similar users, and for the financial products, the aim of the scheme is to recommend the financial products which can create income for the customers as much as possible for the customers. And generating a financial product purchasing frequency score, a financial product purchasing income rate score, a financial product purchasing frequency score, a self-selected product list score, a click viewing frequency score and a browsing time length score according to the financial product purchasing record data. Determining a user financial product transaction score and a user financial product transaction average score according to the user financial product transaction data; determining similarity between users by using a Pearson correlation coefficient according to the transaction score of the user financial product and the average transaction score of the user financial product; and determining a similar user set of the current user according to the determined similarity between the users and a preset threshold value for selecting similar users.
Specifically, in the embodiment of the present invention, for example, by counting details of the financial products purchased by the user over a period of time, a recent profit rate, statistical data of transaction times and frequency of the financial products purchased by the user, a self-chosen product list of the user, click-to-view times of the financial products by the user, browsing time length data, and the like, the value of the number of times of rating of the financial products purchased by the user is determined by standardizing using a dimensionless amount processing interval scaling method, and the value of the number of times of purchasing the financial products, the score of the profit rate of purchasing the financial products, the score of frequency of purchasing the financial products, the score of the self-chosen product list, the score of the click-to-view times, and the score of browsing time length are determined, so that the user financial product transaction data determines the transaction score of.
Calculating the similarity of the two users by using a Pearson correlation coefficient formula (1) according to the determined scores;
where Sim (u, v) represents the similarity between user u and user v, and ru,iRepresents the user u's score, r, on product iv,iThe rating of the product i by the user v,
represents the average score of the user u score,
representing the average score of the user v-score.
According to the determined similarity between the users, a preset threshold value for selecting similar users is used for determining a similar user set of the current user, for example, the similar user set of the current user is determined according to the preset similarity threshold value and the determined similarity between the users.
In an embodiment of the present invention, the generating of the financial product push data of the current user according to the similar user set and the product push model determined in advance according to the position decay function includes:
acquiring distance data of a user;
determining a position attenuation function according to the distance data and a preset position attenuation coefficient, wherein the determined position attenuation function is as follows:
wherein, α is a set position attenuation coefficient, which represents the speed of the similarity varying with the position distance, and all the coefficients set by the user are the same. Δ d is the distance between the coordinates between the two users. The attenuation coefficient a may be obtained by training.
Determining a prediction score of the financial product according to the user financial product transaction score of the user, the user financial product transaction average score, the similarity of the users in the similar user set and the determined position attenuation function; specifically, in embodiments of the present invention, the predicted score for a financial product is determined according to the following equation:
wherein, P (r)u,i) Representing the predicted score of user u for product i;
sim (v, u) represents the similarity between user v and user u;
rv,irepresents the rating of user v for product i;
And S (u) represents a user set with the similarity most similar to the user u.
In an embodiment of the present invention, the generating financial product push data of the current user according to the determined prediction score includes:
determining a financial product set to be pushed according to financial products purchased by a current user;
and determining the financial product pushing data of the current user according to the financial product set and the prediction scores of the financial products in the financial product set.
For example, when recommending to the user a, first, according to the scoring record of the user on the financial products, the financial products which can be extracted by the user to have the characteristic "score" and the financial products which have not been "scored" are obtained, K users most similar to the user a are selected, a prediction function is used, K user sets X most similar to the user a are selected, products which have scores in the sets X but have no scores in the user a are selected to form a financial product set Y, the scores of the sets Y by the user a are calculated, then the scores are ranked, and the N items with the highest scores are recommended to the user.
The system is widely applied to electronic commerce, movies, music and books for solving the problem of information overload, and the conversion rate and click rate of a financial product pushing system are improved by analyzing user behavior data. The method overcomes the defect that the traditional collaborative filtering algorithm lacks the defect of reflecting the change of the interest of the user in different contexts more objectively. The invention overcomes the defects of the prior collaborative filtering recommendation algorithm technology, and provides a method which is effective, has higher recommendation accuracy, utilizes context information capable of reflecting the user interest, and can effectively extract the characteristic attribute of the financial product.
The technical solution of the present invention is further described in detail with reference to the following specific examples.
The embodiment of the invention is obtained by the user purchasing behavior, statistics and calculation acquired by a bank system so as to adapt to common financial products. The embodiment of the invention constructs a financial product recommendation system which is integrated into the position context and is based on a user collaborative filtering algorithm. The financial product recommendation system provided by the embodiment comprises:
the system comprises a feature extraction module, a user financial product scoring matrix module, a user financial product scoring module, a training position attenuation coefficient determination module and a prediction scoring function prediction recommendation module for the user similarity blended into the position attenuation function. The following is specifically described:
the system disclosed by the embodiment of the invention specifically comprises the following processing procedures:
1. extracting characteristics, namely extracting scores of financial products by a user;
the present invention aims to make it more likely that similar users will choose to purchase the same product, whereas for financial products, the present recommendation system aims to recommend to the customer financial products that will create as much revenue as possible for the customer. Based on this objective, the following rules of recording, collecting, and statistical calculation are set in the embodiment of the present invention to perform feature extraction.
In the user transaction process, the recommendation system of the embodiment records the details of financial products purchased by all users, calculates and records the recent income rate, counts the transaction times and frequency of the financial products purchased by the users, records the optional product list of the users, records the click and view times of the financial products by the users, the browsing time length and the like.
(1) Counting the times of all users for purchasing the financial products within a period of time to obtain a scoring value a;
specifically, the scoring steps provided in an embodiment of the present invention are as follows:
user U1 purchased financial product I1 10 times a year, financial product I2 100 times a year, and financial product I3 2 times a year;
user U2 purchased financial product I1 5 times a year, financial product I3 30 times a year, and financial product I4 80 times a year;
the user U3 has no purchasing behavior within one year.
The matrix can be derived:
standardizing the score value a by using a dimensionless processing interval scaling method; wherein, a' represents the number of times of the user U to purchase the financial product I in a period of time of a certain user to a certain financial product, max represents the maximum number of times of the user to purchase the financial product, and min represents the minimum number of times of the user to purchase the financial product.
a＝(a′-Min)/(Max-Min)
Obtaining a scoring item a matrix A:
| I1 | I2 | I3 | I4 | …… | |
| U1 | 0.1 | 1 | 0.02 | 0 | |
| U2 | 0.05 | 0.3 | 0 | 0.8 | |
| U3 | 0 | 0 | 0 | 0 | |
| …… |
(2) counting the receiving s-benefit rate scoring value b of all users on the purchased financial products in a period of time
And (3) obtaining a score value B and a score matrix B by using the standardized data in the method for calculating the number of times score value in the step (1).
Examples are:
the user U1 has the financial product I1 purchased with a one-month profitability of 0.3, the financial product I2 purchased with a one-month profitability of 0.6, and the financial product I3 purchased with a one-month profitability of 0.1;
the user U2 has a financial product I1 one month rate of return 0.9, a financial product I2 one month rate of return 0.7, and a financial product I4 one month rate of return 2;
the user U3 has no purchasing behavior within one month.
The matrix can be derived:
| I1 | I2 | I3 | I4 | …… | |
| U1 | 0.3 | 0.6 | 0.1 | 0 | |
| U2 | 0.9 | 0.7 | 0 | 2 | |
| U3 | 0 | 0 | 0 | 0 | |
| …… |
standardizing the score value b by a dimensionless processing interval scaling method (b' represents the rate of return of a user U to a purchased financial product I within a period of time of a user to a financial product):
b＝(b'-Min)/(Max-Min)
and (3) obtaining a scoring item B matrix B:
| I1 | I2 | I3 | I4 | …… | |
| U1 | 0.15 | 0.3 | 0.05 | 0 | |
| U2 | 0.45 | 0.35 | 0 | 1 | |
| U3 | 0 | 0 | 0 | 0 | |
| …… |
similarly, using the calculation methods similar to (1) and (2), the corresponding scoring item matrix C, D, E … … of frequency, self-chosen product list, click-to-view times and browsing time length is obtained.
2. Establishing a user and financial product scoring matrix Score:
Score＝λ1A+λ2B+λ3C+…λnN
λ1+λ2+λ3+…+λn＝1
wherein lambda is a constant and can be weighted according to the importance degree of the scoring item.
3. Calculating the average score value of the user:
the operation habits and preferences of different users are different, for example, the user has a high tolerance when scoring the movie and has a high general score for the movie; users are used to view financial products frequently and for a long time, and the obtained scores may be high. In order to reflect the "score" difference of different users, in this embodiment, the average score of the scores obtained by the user behavior statistics is introduced
Representing the difference between different persons. As one of the following prediction functions.
The Score matrix obtained by the method is that I is an item set with scores for the user pair, n is the number of the item sets, and r isu,iScoring of i items for user u, so the average score of user u
The calculation method comprises the following steps:
4. training position attenuation coefficient:
generally speaking, the farther the distance between users is, the lower the similarity of users is considered, for example, where the industry mainly produces edible oil, local enterprise customers generally pay more attention to financial derivatives of long-term soybean products.
Setting a position attenuation function f (delta d) which shows that the similarity changes along with the change of the position distance; and setting a position attenuation coefficient alpha, which represents the speed of the similarity changing along with the position distance, wherein the coefficients set by all users are the same. Δ d is the distance between the coordinates between the two users. The attenuation coefficient a may be obtained by training. Distinguishing a data training set from a data testing set, minimizing a prediction score value and a testing set score value into a target function, using a Root Mean Square Error (RMSE) evaluation standard, and obtaining an optimal position attenuation coefficient alpha through a random gradient descent algorithm under a certain step length and iteration times:
5. prediction scoring function P (r) of user similarity blended into position attenuation functionu,i) Making predictive recommendations
Calculating the similarity of two users by using a Pearson correlation coefficient formula;
wherein Sim (u, v) represents the similarity between user u and user v;
ru,irepresents the user u's score for product i;
directly multiplying the fused position attenuation function by the similarity prediction function to obtain a prediction score;
wherein, P (r)u,i) Representing the predicted score of user u for product i;
sim (v, u) represents the similarity between user v and user u;
rv,irepresents the rating of user v for product i;
And S (u) represents a user set with the similarity most similar to the user u.
When recommending to a user A, firstly, according to the scoring records of the user on financial products, obtaining the financial products of which the characteristics can be extracted by the user to be scored and the financial products which are not scored, selecting K users most similar to the user A, selecting K user sets X most similar to the user A by using a prediction function, selecting the products which are scored in the sets X and are not scored by the user A to form a financial product set Y, calculating the scoring of the set Y by the user A, then ranking the scoring, and recommending the N items with the highest scoring to the user. As shown in fig. 2, a schematic flow chart of implementing product recommendation for this embodiment is shown.
Recording user behaviors, establishing a user behavior database, extracting behavior data and features, establishing a feature matrix and a scoring matrix, establishing a similarity calculation model to calculate the similarity between users, training an attenuation coefficient and determining a prediction function;
and simultaneously, selecting K users most similar to the user A by using the established similarity calculation model, predicting by using a prediction function to determine prediction scores, sequencing the scores, generating recommendation data and pushing the recommendation data to the users.
The embodiment of the invention is used for recommending financial products which cannot explicitly collect the scores of the products by users by using a basic traditional recommendation system algorithm. Aiming at the characteristics of financial products, effective and meaningful rules are put forward, and product characteristics are extracted; and a position context is introduced, a distance attenuation function is provided, and the position context can effectively improve the accuracy of the recommendation system.
Meanwhile, the present invention also provides a financial product push data processing apparatus, as shown in fig. 3, which includes:
a data acquisition module 301, configured to acquire user financial product transaction data;
a similar set determining module 302, configured to determine a similar user set of the current user according to the user financial product transaction data;
the pushing data determining module 303 is configured to generate financial product pushing data of the current user according to the similar user set and a product pushing model determined in advance according to a position attenuation function.
In this embodiment of the present invention, the similarity set determining module 302 includes:
the scoring unit is used for determining a user financial product transaction score and a user financial product transaction average score according to the user financial product transaction data;
the similarity determining unit is used for determining the similarity between the users by using a Pearson correlation coefficient according to the user financial product transaction score and the user financial product transaction average score;
and the set selection unit is used for determining a similar user set of the current user according to the determined similarity between the users and a preset threshold value for selecting similar users.
In the embodiment of the present invention, the pushed data determining module includes:
a distance data acquisition unit for acquiring distance data of a user;
the attenuation function determining unit is used for determining a position attenuation function according to the distance data and a preset position attenuation coefficient;
the system comprises a prediction scoring unit, a position attenuation function determining unit and a position estimation unit, wherein the prediction scoring unit is used for determining the prediction scoring of the financial products according to the user financial product transaction scoring of the user, the user financial product transaction average scoring, the similarity of the users in the similar user set and the determined position attenuation function;
and the push data determining unit is used for generating the push data of the financial products of the current user according to the determined prediction scores.
In this embodiment of the present invention, the pushed data determining unit includes:
the screening unit is used for determining a financial product set to be pushed according to financial products purchased by a current user;
and the data processing unit is used for determining the financial product pushing data of the current user according to the financial product set and the prediction scores of the financial products in the financial product set.
The financial product push data processing device provided by the embodiment of the invention acquires the transaction data of the financial product of a user; and determining a similar user set of the current user according to the financial product transaction data of the user, and generating the financial product pushing data of the current user according to the similar user set and a product pushing model determined in advance according to a position attenuation function. The method and the device are effective, have higher recommendation accuracy, utilize context information capable of reflecting user interests and can effectively extract the characteristic attributes of financial products.
For those skilled in the art, the implementation of the data processing apparatus for pushing financial products provided by the present invention can be clearly understood through the foregoing description of the embodiments, and will not be described herein again.
It should be noted that the method and the device for processing the financial product pushed data disclosed by the disclosure can be used for processing the financial product pushed data in the financial field, and can also be used for pushing products in any fields except the financial field.
The present embodiment also provides an electronic device, which may be a desktop computer, a tablet computer, a mobile terminal, and the like, but is not limited thereto. In this embodiment, the electronic device may refer to the embodiments of the method and the apparatus, and the contents thereof are incorporated herein, and repeated descriptions are omitted.
Fig. 4 is a schematic block diagram of a system configuration of an electronic apparatus 600 according to an embodiment of the present invention. As shown in fig. 4, the electronic device 600 may include a central processor 100 and a memory 140; the memory 140 is coupled to the central processor 100. Notably, this diagram is exemplary; other types of structures may also be used in addition to or in place of the structure to implement telecommunications or other functions.
In one embodiment, the financial product push data processing function may be integrated into the central processor 100. The central processor 100 may be configured to control as follows:
acquiring transaction data of a financial product of a user;
determining a similar user set of the current user according to the user financial product transaction data;
and generating financial product pushing data of the current user according to the similar user set and a product pushing model determined in advance according to a position attenuation function.
In another embodiment, the financial product push data processing apparatus may be configured separately from the central processor 100, for example, the financial product push data processing apparatus may be configured as a chip connected to the central processor 100, and the financial product push data processing function is realized by the control of the central processor.
As shown in fig. 4, the electronic device 600 may further include: communication module 110, input unit 120, audio processing unit 130, display 160, power supply 170. It is noted that the electronic device 600 does not necessarily include all of the components shown in fig. 4; furthermore, the electronic device 600 may also comprise components not shown in fig. 4, which may be referred to in the prior art.
As shown in fig. 4, the central processor 100, sometimes referred to as a controller or operational control, may include a microprocessor or other processor device and/or logic device, the central processor 100 receiving input and controlling the operation of the various components of the electronic device 600.
The memory 140 may be, for example, one or more of a buffer, a flash memory, a hard drive, a removable media, a volatile memory, a non-volatile memory, or other suitable device. The information relating to the failure may be stored, and a program for executing the information may be stored. And the central processing unit 100 may execute the program stored in the memory 140 to realize information storage or processing, etc.
The input unit 120 provides input to the cpu 100. The input unit 120 is, for example, a key or a touch input device. The power supply 170 is used to provide power to the electronic device 600. The display 160 is used to display an object to be displayed, such as an image or a character. The display may be, for example, an LCD display, but is not limited thereto.
The memory 140 may be a solid state memory such as Read Only Memory (ROM), Random Access Memory (RAM), a SIM card, or the like. There may also be a memory that holds information even when power is off, can be selectively erased, and is provided with more data, an example of which is sometimes called an EPROM or the like. The memory 140 may also be some other type of device. Memory 140 includes buffer memory 141 (sometimes referred to as a buffer). The memory 140 may include an application/function storage section 142, and the application/function storage section 142 is used to store application programs and function programs or a flow for executing the operation of the electronic device 600 by the central processing unit 100.
The memory 140 may also include a data store 143, the data store 143 for storing data, such as contacts, digital data, pictures, sounds, and/or any other data used by the electronic device. The driver storage portion 144 of the memory 140 may include various drivers of the electronic device for communication functions and/or for performing other functions of the electronic device (e.g., messaging application, address book application, etc.).
The communication module 110 is a transmitter/receiver 110 that transmits and receives signals via an antenna 111. The communication module (transmitter/receiver) 110 is coupled to the central processor 100 to provide an input signal and receive an output signal, which may be the same as in the case of a conventional mobile communication terminal.
Based on different communication technologies, a plurality of communication modules 110, such as a cellular network module, a bluetooth module, and/or a wireless local area network module, may be provided in the same electronic device. The communication module (transmitter/receiver) 110 is also coupled to a speaker 131 and a microphone 132 via an audio processor 130 to provide audio output via the speaker 131 and receive audio input from the microphone 132 to implement general telecommunications functions. Audio processor 130 may include any suitable buffers, decoders, amplifiers and so forth. In addition, an audio processor 130 is also coupled to the central processor 100, so that recording on the local can be enabled through a microphone 132, and so that sound stored on the local can be played through a speaker 131.
Embodiments of the present invention also provide a computer-readable program, where when the program is executed in an electronic device, the program causes a computer to execute the financial product push data processing method according to the above embodiments in the electronic device.
An embodiment of the present invention further provides a storage medium storing a computer-readable program, where the computer-readable program enables a computer to execute the financial product push data processing described in the above embodiment in an electronic device.
The preferred embodiments of the present invention have been described above with reference to the accompanying drawings. The many features and advantages of the embodiments are apparent from the detailed specification, and thus, it is intended by the appended claims to cover all such features and advantages of the embodiments that fall within the true spirit and scope thereof. Further, since numerous modifications and changes will readily occur to those skilled in the art, it is not desired to limit the embodiments of the invention to the exact construction and operation illustrated and described, and accordingly, all suitable modifications and equivalents may be resorted to, falling within the scope thereof.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams 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 flow or flows 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 flow or flows 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 flow or flows and/or block diagram block or blocks.
The principle and the implementation mode of the invention are explained by applying specific embodiments in the invention, and the description of the embodiments is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (12)
1. A financial product push data processing method is characterized by comprising the following steps:
acquiring transaction data of a financial product of a user;
determining a similar user set of the current user according to the user financial product transaction data;
and generating financial product pushing data of the current user according to the similar user set and a product pushing model determined in advance according to a position attenuation function.
2. The financial product push data processing method of claim 1, wherein said financial product transaction data includes: the method comprises the steps of purchasing financial product details by a user, calculating and recording recent earning rate, statistical data of transaction times and frequency of the financial product purchased by the user, a self-selected product list of the user, click and view times of the financial product by the user and browsing time length data.
3. The financial product push data processing method of claim 1, wherein said determining a set of similar users for a current user based on said user financial product transaction data comprises:
determining a user financial product transaction score and a user financial product transaction average score according to the user financial product transaction data;
determining similarity between users by using a Pearson correlation coefficient according to the user financial product transaction score and the user financial product transaction average score;
and determining a similar user set of the current user according to the determined similarity between the users and a preset threshold value for selecting similar users.
4. The method as claimed in claim 3, wherein the step of generating the financial product push data of the current user according to the similar users and the product push model determined in advance according to the location decay function comprises:
acquiring distance data of a user;
determining a position attenuation function according to the distance data and a preset position attenuation coefficient;
determining a prediction score of the financial product according to the user financial product transaction score of the user, the user financial product transaction average score, the similarity of the users in the similar user set and the determined position attenuation function;
and generating the financial product pushing data of the current user according to the determined prediction scores.
5. The method of claim 4, wherein the generating financial product push data for the current user based on the determined prediction score comprises:
determining a financial product set to be pushed according to financial products purchased by a current user;
and determining the financial product pushing data of the current user according to the financial product set and the prediction scores of the financial products in the financial product set.
6. A financial product push data processing apparatus, said apparatus comprising:
the data acquisition module is used for acquiring the transaction data of the financial products of the user;
the similar set determining module is used for determining a similar user set of the current user according to the user financial product transaction data;
and the push data determining module is used for generating the financial product push data of the current user according to the similar user set and a product push model determined in advance according to a position attenuation function.
7. The financial product push data processing apparatus of claim 6, wherein said financial product transaction data includes: the method comprises the steps of purchasing financial product details by a user, calculating and recording recent earning rate, statistical data of transaction times and frequency of the financial product purchased by the user, a self-selected product list of the user, click and view times of the financial product by the user and browsing time length data.
8. The financial product push data processing apparatus of claim 6, wherein said similarity set determination module comprises:
the scoring unit is used for determining a user financial product transaction score and a user financial product transaction average score according to the user financial product transaction data;
the similarity determining unit is used for determining the similarity between the users by using a Pearson correlation coefficient according to the user financial product transaction score and the user financial product transaction average score;
and the set selection unit is used for determining a similar user set of the current user according to the determined similarity between the users and a preset threshold value for selecting similar users.
9. The financial product push data processing apparatus of claim 8, wherein said push data determination module comprises:
a distance data acquisition unit for acquiring distance data of a user;
the attenuation function determining unit is used for determining a position attenuation function according to the distance data and a preset position attenuation coefficient;
the system comprises a prediction scoring unit, a position attenuation function determining unit and a position estimation unit, wherein the prediction scoring unit is used for determining the prediction scoring of the financial products according to the user financial product transaction scoring of the user, the user financial product transaction average scoring, the similarity of the users in the similar user set and the determined position attenuation function;
and the push data determining unit is used for generating the push data of the financial products of the current user according to the determined prediction scores.
10. The financial product push data processing apparatus of claim 9, wherein said push data determining unit comprises:
the screening unit is used for determining a financial product set to be pushed according to financial products purchased by a current user;
and the data processing unit is used for determining the financial product pushing data of the current user according to the financial product set and the prediction scores of the financial products in the financial product set.
11. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method of any of claims 1 to 5 when executing the computer program.
12. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program for executing the method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110503905.0A CN113011985A (en) | 2021-05-10 | 2021-05-10 | Financial product push data processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110503905.0A CN113011985A (en) | 2021-05-10 | 2021-05-10 | Financial product push data processing method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113011985A true CN113011985A (en) | 2021-06-22 |
Family
ID=76380876
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110503905.0A Pending CN113011985A (en) | 2021-05-10 | 2021-05-10 | Financial product push data processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113011985A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113781239A (en) * | 2021-09-10 | 2021-12-10 | 未鲲(上海)科技服务有限公司 | Policy determination method and device, electronic equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104391849A (en) * | 2014-06-30 | 2015-03-04 | 浙江大学苏州工业技术研究院 | Collaborative filtering recommendation method for integrating time contextual information |
| CN107766547A (en) * | 2017-10-31 | 2018-03-06 | 掌阅科技股份有限公司 | E-book recommends method, electronic equipment and computer-readable storage medium |
| CN112418956A (en) * | 2020-12-16 | 2021-02-26 | 国网雄安金融科技集团有限公司 | Financial product recommendation method and device |
-
2021
- 2021-05-10 CN CN202110503905.0A patent/CN113011985A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104391849A (en) * | 2014-06-30 | 2015-03-04 | 浙江大学苏州工业技术研究院 | Collaborative filtering recommendation method for integrating time contextual information |
| CN107766547A (en) * | 2017-10-31 | 2018-03-06 | 掌阅科技股份有限公司 | E-book recommends method, electronic equipment and computer-readable storage medium |
| CN112418956A (en) * | 2020-12-16 | 2021-02-26 | 国网雄安金融科技集团有限公司 | Financial product recommendation method and device |
Non-Patent Citations (2)
| Title |
|---|
| 李欣璐;刘鲁;: "基于协同过滤的银行产品推荐系统建模", 计算机与数字工程, no. 09, 20 September 2007 (2007-09-20), pages 6 - 8 * |
| 陈燕;马兴敏;宿媛媛;: "协同过滤推荐系统在银行产品个性化服务中的应用", 数字通信世界, no. 06, 1 June 2018 (2018-06-01) * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113781239A (en) * | 2021-09-10 | 2021-12-10 | 未鲲(上海)科技服务有限公司 | Policy determination method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101871747B1 (en) | Similarity tendency based user-sightseeing recommendation system and method thereof | |
| JP4524709B2 (en) | Information processing apparatus and method, and program | |
| JP6261547B2 (en) | Determination device, determination method, and determination program | |
| US20150324811A1 (en) | Scoring Tool for Research Surveys Deployed in a Mobile Environment | |
| US20190266619A1 (en) | Behavior pattern search system and behavior pattern search method | |
| CN105095431A (en) | Method and device for pushing videos based on behavior information of user | |
| CA3070612A1 (en) | Click rate estimation | |
| TW201408993A (en) | Systems and methods for presenting point of interest (POI) information map, and storage medium thereof | |
| EP2113849A2 (en) | Information processing apparatus and presenting method of related items | |
| CN103678518A (en) | Method and device for adjusting recommendation lists | |
| CN110334356A (en) | Article matter method for determination of amount, article screening technique and corresponding device | |
| KR20090017268A (en) | Method for updating interest keyword of user and system for executing the method | |
| CN111611496A (en) | Product recommendation method and device | |
| CN111311332A (en) | User data processing method and device | |
| JP2017201535A (en) | Determination device, learning device, determination method, and determination program | |
| CN111861605A (en) | Business object recommendation method | |
| US20150278907A1 (en) | User Inactivity Aware Recommendation System | |
| KR20130038889A (en) | Object customization and management system | |
| CN113011985A (en) | Financial product push data processing method and device | |
| KR100901782B1 (en) | Method and System for Generating Marketing Information | |
| CN117474631A (en) | Recommendation algorithm for data mining and emotion analysis based on e-commerce platform comments | |
| CN111210274A (en) | Advertisement recommendation method and system | |
| KR102028356B1 (en) | Advertisement recommendation apparatus and method based on comments | |
| CN112015970A (en) | Product recommendation method, related equipment and computer storage medium | |
| CN112287208A (en) | User portrait generation method and device, electronic 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 |