CN109146549A - Lottery user product participation prediction technique, system and equipment, storage medium - Google Patents
Lottery user product participation prediction technique, system and equipment, storage medium Download PDFInfo
- Publication number
- CN109146549A CN109146549A CN201810841269.0A CN201810841269A CN109146549A CN 109146549 A CN109146549 A CN 109146549A CN 201810841269 A CN201810841269 A CN 201810841269A CN 109146549 A CN109146549 A CN 109146549A
- Authority
- CN
- China
- Prior art keywords
- classifier
- participation
- user
- sub
- decision tree
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0203—Market surveys; Market polls
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Entrepreneurship & Innovation (AREA)
- Probability & Statistics with Applications (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of lottery user product participation prediction techniques, comprising: obtains original user data, after the original user data is extracted and converted, is loaded onto database with specified format classification;The original user data stored in the database is pre-processed, various dimensions user data is obtained;Predicted characteristics collection relevant to consumer products participation is obtained according to the various dimensions user data;By in predicted characteristics collection input fusion forecasting model trained in advance, consumer products participation is predicted;Wherein, the fusion forecasting model is at least merged by Bayes classifier, random forest grader and iteration decision tree classifier and is generated.Correspondingly, the invention also discloses a kind of lottery user product participation forecasting system and terminal devices, computer readable storage medium.It can reduce the prediction difficulty of lottery user product participation using technical solution of the present invention, and improve predictablity rate.
Description
Technical field
The present invention relates to data mining technology field more particularly to a kind of lottery user product participation prediction technique, it is
System and terminal device, computer readable storage medium.
Background technique
Lottery industry product category is numerous, and various products are different for the profit value of betting office, that is, is pumped into ratio
Example is divided into height.Betting office wishes the stake preference of discovery user, and user is attracted more to participate in the coloured silk of high profit margin
In ticket product, to bring more profits.Therefore, it is predicted just gradually for participation of the lottery user to high profit margin product
Paid attention to.
According to user to the participation of high profit margin product, user can be divided into two major classes, i.e., low participation user
With high participation user again, wherein high participation user can be subdivided into two groups, i.e. variation or throwing due to betting preference
It infuses total amount and promotes these two types of reasons as high participation user.
In the prior art, for predicting that the disaggregated model of consumer products participation mainly has the rule based on experience and statistics
Model, but such model is next pre- it is difficult to extract accurately rule is gone out when facing lottery industry magnanimity, multiplicity, the data of complexity
Survey the product participation of user;Regression analysis is also widely used in classification problem, but high to the quality requirement of training data,
It need to exclude the synteny problem in independent variable and reasonably handle exceptional value and default value, and lottery user data source is extensive
And it is complicated, often exist abnormal and default, simple regression analysis can not obtain accurate prediction result.In addition, nerve net
Network is also common prediction model, it is the I/O unit of one group of connection, wherein each connection has a weighted value,
The classificating knowledge of neural network embodies over network connections, is implicitly stored in the weight of connection.The study of neural network
Process is the process being constantly adjusted by interative computation to weight, and the target of study is exactly to make to input by the adjustment of weight
Tuple compares other common data mining technologies by correct label, and neural network has good for classification problem prediction
Predictive ability, but disadvantage also can not be ignored, for example, neural network itself black box, be not easy to explain and to calculating power
High request etc. causes the difficulty of prediction larger.
Summary of the invention
The technical problem to be solved by the embodiment of the invention is that providing a kind of lottery user product participation prediction side
Method, system and terminal device, computer readable storage medium can reduce the prediction difficulty of lottery user product participation, and
Improve predictablity rate.
In order to solve the above-mentioned technical problem, the embodiment of the invention provides a kind of lottery user product participation prediction sides
Method, comprising:
Original user data is obtained, after the original user data is extracted and converted, is added with specified format classification
It is loaded onto database;
The original user data stored in the database is pre-processed, various dimensions user data is obtained;Its
In, the pretreatment includes at least consistency treatment, removes processing again, data transformation and data reduction process;The various dimensions are used
User data includes at least the personal information of user, history stake information and history earnings information;
Predicted characteristics collection relevant to consumer products participation is obtained according to the various dimensions user data;
By in predicted characteristics collection input fusion forecasting model trained in advance, consumer products participation is carried out pre-
It surveys;Wherein, the fusion forecasting model is at least melted by Bayes classifier, random forest grader and iteration decision tree classifier
Symphysis at.
Further, described that predicted characteristics relevant to consumer products participation are obtained according to the various dimensions user data
Collection, specifically includes:
It is constructed from the various dimensions user data according to data statistic analysis relevant to consumer products participation potential
Feature set;
The potential feature set is adjusted, screened and combined according to iteration tests, obtains the predicted characteristics collection.
Further, the method is trained the fusion forecasting model by following steps:
The training characteristics collection relevant to consumer products participation being obtained ahead of time is divided into training set and verifying collection;
When the fusion forecasting model is by the Bayes classifier, the random forest grader and the iteration decision
When Tree Classifier fusion generates, it is based respectively on the Bayes classifier, the random forest grader and the iteration decision
Tree Classifier is modeled according to the training set, the corresponding at least two Bayes's sub-classifiers, at least two random gloomy of obtaining
Woods classifier and at least two iteration decision tree sub-classifiers;
Each Bayes's sub-classifier, each random forest sub-classifier are obtained respectively according to verifying collection
With the accuracy rate of each iteration decision tree sub-classifier;
Determine that accuracy rate is greater than Bayes's sub-classifier of preset first threshold value, accuracy rate is greater than default second respectively
The random forest sub-classifier and accuracy rate of threshold value are greater than the iteration decision tree sub-classifier of default third threshold value;
According to determining Bayes's sub-classifier, the random forest sub-classifier and the iteration decision tree point
The fusion of class device generates the fusion forecasting model.
Further, described when the fusion forecasting model is by the Bayes classifier, the random forest grader
When merging generation with the iteration decision tree classifier, it is based respectively on the Bayes classifier, the random forest grader
It is modeled with the iteration decision tree classifier according to the training set, at least two Bayes's sub-classifiers of corresponding acquisition,
At least two random forest sub-classifiers and at least two iteration decision tree sub-classifiers, specifically include:
Different at least six groups of modeling parameters are chosen from the training set according to grid data service;Wherein, it is described at least
It include the first modeling parameters of at least two groups corresponding with the Bayes classifier and the random forest in six groups of modeling parameters
Corresponding the second modeling parameters of at least two groups of classifier and at least two groups third corresponding with the iteration decision tree classifier are built
Mould parameter;
It is modeled based on the Bayes classifier according to first modeling parameters of at least two groups, it is corresponding to obtain at least
Two Bayes's sub-classifiers;
It is modeled based on the random forest class device according to second modeling parameters of at least two groups, it is corresponding to obtain at least
Two random forest sub-classifiers;
It is modeled based on the iteration decision tree classifier according at least two groups third modeling parameters, it is corresponding to obtain
At least two iteration decision tree sub-classifiers.
Further, in the fusion forecasting model that predicted characteristics collection input is trained in advance, to consumer products
Participation is predicted, is specifically included:
The predicted characteristics collection is inputted in the fusion forecasting model, is obtained by way of ballot in preset time period
Interior consumer products participation scoring;Wherein, consumer products participation scoring include at least user preference change scoring and
User activity changes scoring.
Further, the method also includes:
The prediction result of consumer products participation is exported in a text form, and is shown in the form of WEB page.
Further, the method also includes:
Obtain actual user's product participation;
The accuracy rate of the fusion forecasting model is verified according to actual user's product participation;
The fusion forecasting model is corrected according to verification result.
In order to solve the above-mentioned technical problem, the embodiment of the invention also provides a kind of predictions of lottery user product participation is
System, comprising:
Data loading module, for obtaining original user data, after the original user data is extracted and is converted,
It is loaded onto database with specified format classification;
Data processing module is obtained for pre-processing to the original user data stored in the database
Various dimensions user data;Wherein, the pretreatment includes at least consistency treatment, removes processing again, data transformation and data regularization
Processing;The various dimensions user data includes at least the personal information of user, history stake information and history earnings information;
Characteristic extracting module, for obtaining prediction relevant to consumer products participation according to the various dimensions user data
Feature set;And
Participation prediction module, for by predicted characteristics collection input fusion forecasting model trained in advance, to
Family product participation is predicted;Wherein, the fusion forecasting model at least by Bayes classifier, random forest grader and
The fusion of iteration decision tree classifier generates.
In order to solve the above-mentioned technical problem, the embodiment of the invention also provides a kind of terminal devices, including processor, storage
Device and storage in the memory and are configured as the computer program executed by the processor, and the processor is being held
Lottery user product participation prediction technique described in any of the above embodiments is realized when the row computer program.
In order to solve the above-mentioned technical problem, described the embodiment of the invention also provides a kind of computer readable storage medium
Computer readable storage medium includes the computer program of storage;Wherein, the computer program controls the meter at runtime
Equipment where calculation machine readable storage medium storing program for executing executes lottery user product participation prediction technique described in any of the above embodiments.
Compared with prior art, the embodiment of the invention provides a kind of lottery user product participation prediction techniques, system
And terminal device, computer readable storage medium extract original user data and are turned by obtaining original user data
After changing, it is loaded onto database with specified format classification;The original user data stored in database is pre-processed, is obtained
Various dimensions user data, and predicted characteristics collection relevant to consumer products participation is obtained according to various dimensions user data;It will be pre-
It surveys in feature set input fusion forecasting model trained in advance, consumer products participation is predicted, can reduce lottery ticket use
The prediction difficulty of family product participation, and improve predictablity rate.
Detailed description of the invention
Fig. 1 is a kind of process of a preferred embodiment of lottery user product participation prediction technique provided by the invention
Figure;
Fig. 2 is that one of the step S13 of a kind of lottery user product participation prediction technique provided by the invention is preferred real
Apply the specific flow chart of example;
Fig. 3 is that one of the model training of a kind of lottery user product participation prediction technique provided by the invention is preferred real
Apply the specific flow chart of example;
Fig. 4 is that one of the step S22 of a kind of lottery user product participation prediction technique provided by the invention is preferred real
Apply the specific flow chart of example;
Fig. 5 is a kind of structure of a preferred embodiment of lottery user product participation forecasting system provided by the invention
Block diagram;
Fig. 6 is a kind of structural block diagram of a preferred embodiment of terminal device provided by the invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained all without creative efforts
Other embodiments shall fall within the protection scope of the present invention.
It should be strongly noted that " lottery ticket " in the embodiment of the present invention only refers in particular to meet legalizing for government operation
A kind of economic activity form.
It is shown in Figure 1, it is that one of a kind of lottery user product participation prediction technique provided by the invention is preferred real
Apply the flow chart of example, including step S11 to step S14:
Step S11, original user data is obtained, after the original user data is extracted and converted, to specify lattice
Formula classification is loaded onto database.
Specifically, step S11 after the original user data of lottery user is ready, identify and obtain do not load it is original
User data is carried out the extraction of necessary data and the conversion of data format to the original user data, and is classified with specified format
It stores in database, to realize that database loads.
It being designed by data pattern, original user data will be organized into multiple succinct, efficient, comprehensive tables of data, under
Face by original user data crucial table and critical field for be introduced.
For crucial table, being designed by data pattern, original user data is divided into two class tables and is converted and loaded,
Middle one kind is the history table of sustainable addition, and another kind of is the information reference list for needing full table replacement.For critical field,
It include the related content for the critical field being used in crucial table.As shown in table 1, a crucial table and its meaning are listed
Justice lists critical field account information change record (account_info_change_log) in crucial table as shown in table 2
And its meaning.
The crucial table of table 1 and its meaning
Table | Meaning |
account_info_change_log | Account information change record |
fund_transfer_log | Account supplements record of withdrawing deposit with money |
balance_log | Account balance historical record |
betting_log | Account bets historical record |
customer_info | Userspersonal information's table |
event_schedule | Schedule table |
bet_type | Bet type table |
account_info | Account up-to-date information table |
2 account information change record of table and its meaning
It should be noted that the original user data comprising necessary information in a manner of " data category+time range " into
Row is sorted out, and is uniformly placed in HDFS (Hadoop Distributed File System, Hadoop distributed file system)
Specified path under, newly-increased original user data will periodically be added to the path, to carry out the update of prediction model.
Step S12, the original user data stored in the database is pre-processed, obtains various dimensions user
Data;Wherein, the pretreatment includes at least consistency treatment, removes processing again, data transformation and data reduction process;It is described more
Dimension user data includes at least the personal information of user, history stake information and history earnings information.
It should be noted that typically, original user data there are it is inconsistent, repeat, dimension is high the problems such as, original
After the completion of user data load, need to pre-process original user data, to solve the problems, such as to exist.
Specifically, step S12 carries out consistency treatment to the original user data stored in database, except processing, number again
According to transformation and the pretreatment such as data reduction process, to obtain various dimensions user data, which includes but not
It is limited to userspersonal information, user's history stake information and the user's history earnings information of desensitization.
Wherein, the situation inconsistent for data can be accepted or rejected: 1) newest with the time according to following several standards
Data are excellent (such as membership information data);2) with the stronger data of reliability be it is excellent (such as the same information involved in multiple tables,
The data being subject in more reliable table);3) value that can be calculated actively calculates acquisition, and (such as the age can be calculated by the date of birth
It obtains);If there is the inconsistent situation of serious data (few to occur), which can be considered as to abnormal user and ignored.Needle
To the duplicate situation of data, can carry out filtering duplicate data except handling again.It, can be with for the higher situation of data dimension
Data transformation and the data reduction process such as assembled, standardized to original user data.
Step S13, predicted characteristics collection relevant to consumer products participation is obtained according to the various dimensions user data.
It should be noted that Feature Engineering is the process for initial data being transformed into feature, these features should be able to be very
The model for describing data well, and being established using them can reaction model target well, therefore, in the present embodiment,
Feature set needs to reflect lottery user product participation, in conjunction with lottery industry feature, provides the product ginseng suitable for lottery user
It is defined as follows with degree prediction:
At a given time period in T, in all users for participating in lottery ticket, stake increases on year-on-year basis in high profit margin product total degree
Length is greater than 10%, and bets and be not less than 10% user, definition in high profit margin product number and stake total degree ratio growth
For the user (hereinafter referred to as A class user) for promoting participation because betting preference and changing;In all users for participating in lottery ticket, stake
Increase by a year-on-year basis in high profit margin product total degree greater than 10%, and bets in high profit margin product number and stake total degree ratio
Increase the user lower than 10%, is defined as promoting the user (hereinafter referred to as B class user) of participation because betting liveness and being promoted;
Remaining user is defined as low participation user (hereinafter referred to as C class user).
Specifically, the various dimensions user data obtained after pre-processing to original user data includes but is not limited to desensitize
Userspersonal information, user's history stake information and user's history earnings information, step S13 is then according to the various dimensions number of users
According to acquisition predicted characteristics collection relevant to consumer products participation.
Step S14, in the fusion forecasting model for training predicted characteristics collection input in advance, to consumer products participation
It is predicted;Wherein, the fusion forecasting model is at least by Bayes classifier, random forest grader and iteration decision tree point
The fusion of class device generates.
Specifically, the present invention has been previously-completed the training to fusion forecasting model, obtaining and consumer products participation phase
After the predicted characteristics collection of pass, the predicted characteristics collection is input in the fusion forecasting model after training by step S14, with right
Consumer products participation is predicted.
A kind of lottery user product participation prediction technique, passes through the original to lottery user provided by the embodiment of the present invention
Beginning user data carries out fusion of the respective handling to obtain predicted characteristics collection relevant to consumer products participation, after combined training
Prediction model realizes the prediction to consumer products participation, reduces the prediction difficulty of lottery user product participation, and improve
The accuracy rate of consumer products participations prediction.In addition, since fusion forecasting model is at least by Bayes classifier, random forest
Classifier and the fusion of iteration decision tree classifier generate, and standard can not be obtained by solving the model commonly based on the training of single algorithm
The problem of true prediction result, so that it is more accurate according to the prediction result that fusion forecasting model obtains, therefore further increase
The precision of predictions of consumer products participations.
It is shown in Figure 2, it is the one of the step S13 of a kind of lottery user product participation prediction technique provided by the invention
The specific flow chart of a preferred embodiment, it is described relevant to consumer products participation according to various dimensions user data acquisition
Predicted characteristics collection specifically includes step S1301 to step S1302:
Step S1301, it is constructed from the various dimensions user data according to data statistic analysis and consumer products participation
Relevant potential feature set;
Step S1302, the potential feature set is adjusted, screened and combined according to iteration tests, obtained described pre-
Survey feature set.
In the present embodiment, according to all kinds of statistical analysis of the study of domain knowledge early period and lottery user data, from more
Many potential feature sets relevant to consumer products participation (such as lottery user nearest one has been constructed in dimension user data
Phase return rate), then by constantly iteration tests, the parameter in potential feature set is adjusted, screened and combined, is reached
Optimal effect, to obtain final predicted characteristics collection.
When it is implemented, can be by operation characteristic processor (Feature Processor), in all various dimensions users
The feature filtered out is constructed one by one on the basis of data;Feature Processor can be understood as being responsible for generating special
The driver of sign can correspond to acquisition one when every feature executed under cubbyhole feature-maker generates code file
Category feature has feature set scalability;After the driver end of run, so that it may obtain the feature formed after new data is added
Collection.Table 3 lists userspersonal information's feature set, user's history transaction feature collection and user to table 5 in table form respectively
Trade mode feature set.
3 userspersonal information's feature set of table
Feature | Description |
GENDER | Lottery user gender |
AGE | The lottery user age |
MAJOR_CHANNEL | Lottery user mainly bets channel |
BET_YEAR | Lottery user participates in stake time (as unit of year) |
4 user's history transaction feature collection of table
5 customer transaction pattern feature collection of table
Feature | Description |
INV1 | The nearest phase stake total value of lottery user is (if do not bet, then for 0) |
INV2 | The nearest second phase stake total value of lottery user is (if do not bet, then for 0) |
INV3 | The nearest third phase stake total value of lottery user is (if do not bet, then for 0) |
··· | ··· |
INV60 | The nearest 60th phase stake total value of lottery user is (if do not bet, then for 0) |
INV_TIMES1 | The nearest phase stake total degree of lottery user is (if do not bet, then for 0) |
INV_TIMES2 | The nearest second phase stake total degree of lottery user is (if do not bet, then for 0) |
INV_TIMES3 | The nearest third phase stake total degree of lottery user is (if do not bet, then for 0) |
··· | ··· |
INV_TIMES60 | The nearest 60th phase stake total degree of lottery user is (if do not bet, then for 0) |
RECOVERY_RATE1 | The nearest phase return rate of lottery user |
RECOVERY_RATE2 | The nearest second phase return rate of lottery user |
RECOVERY_RATE3 | The nearest third phase return rate of lottery user |
··· | ··· |
RECOVERY_RATE60 | The nearest 60th phase return rate of lottery user |
It should be noted that table 3 listed above to table 5 is only pre- using the lottery user product participation of invention offer
The extracted Partial Feature collection of survey method, the present invention can also generate other feature sets in addition to this, example according to actual needs
It is numerous to list herein such as user account information characteristic set derivative feature collection.
It is shown in Figure 3, it is a kind of model training of lottery user product participation prediction technique provided by the invention
The specific flow chart of one preferred embodiment, the method carry out the fusion forecasting model by step S21 to step S25
Training:
Step S21, the training characteristics collection relevant to consumer products participation being obtained ahead of time is divided into training set and tested
Card collection;
Step S22, when the fusion forecasting model is by the Bayes classifier, the random forest grader and described
When the fusion of iteration decision tree classifier generates, it is based respectively on the Bayes classifier, the random forest grader and described
Iteration decision tree classifier is modeled according to the training set, corresponding to obtain at least two Bayes's sub-classifiers, at least two
A random forest sub-classifier and at least two iteration decision tree sub-classifiers;
Step S23, each Bayes's sub-classifier, each random forest are obtained according to verifying collection respectively
The accuracy rate of sub-classifier and each iteration decision tree sub-classifier;
Step S24, determine that accuracy rate is greater than Bayes's sub-classifier of preset first threshold value, accuracy rate is greater than respectively
The random forest sub-classifier and accuracy rate of default second threshold are greater than the iteration decision tree of default third threshold value
Classifier;
Step S25, it is determined according to determining Bayes's sub-classifier, the random forest sub-classifier and the iteration
Plan tree Multiple Classifier Fusion generates the fusion forecasting model.
Specifically, in modeling, first by the data complete or collected works by pretreatment and Feature Engineering treated training characteristics collection
It is divided, for example, being based on time dimension, before the data complete or collected works of training characteristics collection 70% data is formed into training set
Train-set, by rear 30% data composition verifying collection Validation-set;When fusion forecasting model is only by Bayes's classification
When device, random forest grader and the fusion of iteration decision tree classifier generate, Bayes classifier is based respectively on according to training set
Train-set is modeled and is established at least two Bayes's sub-classifiers, based on random forest grader according to training set
Train-set is modeled and is established at least two random forest sub-classifiers, based on iteration decision tree classifier according to training
Collection Train-set is modeled and is established at least two iteration decision tree sub-classifiers;Collect Validation-set according to verifying
Respectively on each Bayes's sub-classifier, each random forest sub-classifier and each iteration decision tree sub-classifier
Observing and nursing effect obtains the corresponding accuracy rate of each sub-classifier;It is determined in all Bayes's sub-classifiers respectively quasi-
True rate is greater than Bayes's sub-classifier of pre-set first threshold (such as 70%), in all random forest sub-classifiers
Middle determining accuracy rate is greater than the random forest sub-classifier of pre-set second threshold (such as 80%), determines in all iteration
Determine that accuracy rate is greater than the iteration decision tree sub-classifier of pre-set third threshold value (such as 75%) in plan tree classifier;
According to determining Bayes's sub-classifier, random forest sub-classifier and iteration decision tree sub-classifier, using Model Fusion skill
Art generates corresponding fusion forecasting model.
It should be noted that being predicted in the acquisition methods and above-described embodiment of training characteristics collection used in the present embodiment special
The acquisition methods of collection are identical.
It should be understood that accuracy rate is greater than the possible more than one of sub-classifier of preset threshold, i.e., in fusion forecasting model
It may include more than one Bayes sub-classifier, more than one random forest sub-classifier and more than one iteration decision tree
Classifier.
As shown in connection with fig. 4, be a kind of lottery user product participation prediction technique provided by the invention step S22 one
The specific flow chart of a preferred embodiment, it is described when the fusion forecasting model is by the Bayes classifier, described random gloomy
When woods classifier and iteration decision tree classifier fusion generate, it is based respectively on the Bayes classifier, described random gloomy
Woods classifier and the iteration decision tree classifier are modeled according to the training set, corresponding to obtain at least two Bayes
Classifier, at least two random forest sub-classifiers and at least two iteration decision tree sub-classifiers, specifically include step S2201
To step S2204:
Step S2201, different at least six groups of modeling parameters are chosen from the training set according to grid data service;Its
In, include at least six groups of modeling parameters the first modeling parameters of at least two groups corresponding with the Bayes classifier, with
Corresponding the second modeling parameters of at least two groups of the random forest grader and corresponding extremely with the iteration decision tree classifier
Few two groups of third modeling parameters;
Step S2202, it is modeled based on the Bayes classifier according to first modeling parameters of at least two groups, it is right
At least two Bayes's sub-classifiers should be obtained;
Step S22023, it is modeled based on the random forest class device according to second modeling parameters of at least two groups,
It is corresponding to obtain at least two random forest sub-classifiers;
Step S2204, it is built based on the iteration decision tree classifier according at least two groups third modeling parameters
Mould, it is corresponding to obtain at least two iteration decision tree sub-classifiers.
Specifically, grid data service (grid can be used since modeling process is related to the selection of many modeling parameters
Search one group of optimal parameter) is searched out from the total data of training set, and by repeatedly attempting to select different parameters
It is combined, obtains multiple groups modeling parameters, for Bayes classifier, select the first modeling parameters of at least two groups, and be based on shellfish
This classifier of leaf is modeled according to the first modeling parameters of multiple groups, to establish multiple Bayes's sub-classifiers;For random
Forest classified device selects the second modeling parameters of at least two groups, and based on random forest grader according to the second modeling parameters of multiple groups
It is modeled, to establish multiple random forest sub-classifiers;For iteration decision tree classifier, at least two groups third is selected
Modeling parameters, and modeled based on iteration decision tree classifier according to multiple groups third modeling parameters, to establish multiple change
For decision tree sub-classifier;Wherein, one sub-classifier of each group of modeling parameters correspondence establishment.
For example, including 1~feature of feature 5 in training set, for Bayes classifier, selected characteristic 1 and feature 2 are used as one
The first modeling parameters of group, one Bayes classifier of correspondence establishment, selected characteristic 1 and feature 3 are joined as one group of first modeling
Number, correspondence establishment another Bayes classifier, such single classifier are known as sub-classifier;Other sub-classifiers are built
Mold process similarly,
In a further advantageous embodiment, the fusion forecasting model that predicted characteristics collection input is trained in advance
In, consumer products participation is predicted, is specifically included:
The predicted characteristics collection is inputted in the fusion forecasting model, is obtained by way of ballot in preset time period
Interior consumer products participation scoring;Wherein, consumer products participation scoring include at least user preference change scoring and
User activity changes scoring.
Specifically, after the predicted characteristics collection corresponding to the original user data for extracting lottery user, after training
Fusion forecasting model, user of the user in pre-set period (such as following 30 days) is obtained by way of ballot and is produced
Product participation scoring, wherein the scoring of consumer products participation includes at least user preference change scoring and user activity changes
Scoring, user preference, which changes scoring, indicates that user is likely to become the probability of A class user, and user activity, which changes scoring, indicates user
It may be known as the probability of B class user.
It should be noted that since fusion forecasting model is at least by Bayes classifier, random forest grader and iteration
Decision tree classifier fusion generates, and the mode for first passing through ballot predicts that a certain user is that A class user, B class user or C class are used
Family after obtaining consumer products participation scoring k, with k and will preset the when it is implemented, for Bayes classifier
One scoring threshold value k1 and the second scoring threshold value k2 are compared, if k >=k1, determine user for A class user;If k2≤k <
K1 then determines user for B class user;If k < k2, determine user for C class user;For random forest grader and iteration
Decision tree classifier, determination method is similarly;In conjunction with above-described embodiment, it is assumed that fusion forecasting model includes 5 Bayes's subclassifications
Device, 6 random forest sub-classifiers and 7 iteration decision tree sub-classifiers, the process of ballot are exactly for a prediction object
Input, this 18 sub-classifier can correspond to 18 outputs of generation, for example prediction output is that A class user has 10 subclassifications
Device, prediction output have 8 sub-classifiers for B class user, are equivalent to 18 individual votes, as a result 10 person, 1,8 person 2 is exactly
The minority is subordinate to the majority, and voting results are 1, and the output of corresponding final fusion forecasting model is exactly A class user, and prediction result is corresponding
Change for user preference and scores.
In another preferred embodiment, the method also includes:
The prediction result of consumer products participation is exported in a text form, and is shown in the form of WEB page.
Specifically, after the prediction result for obtaining consumer products participation according to fusion forecasting model, by prediction result
It provides, and is presented in the form of WEB page in the form of text.
It should be understood that being directed to each lottery user, consumer products participation can be carried out through the embodiment of the present invention
The prediction of degree can show the corresponding prediction result of each user by WEB page, as user bets in a few days at following 30
Probability as A class user or B class user, it is preferable that can also provide and be scored according to consumer products participation to all users
Carry out the function of positive sequence or/and Bit-reversed.
In another preferred embodiment, the method also includes:
Obtain actual user's product participation;
The accuracy rate of the fusion forecasting model is verified according to actual user's product participation;
The fusion forecasting model is corrected according to verification result.
It should be noted that the case where actual user's product participation, can obtain from new user data, and with text
This form uploads, and therefore, the present invention can verify the accuracy rate of consumer products participation prediction, and be fusion according to verification result
The successive iterations of prediction model, which are improved, provides guidance.
A kind of lottery user product participation prediction technique provided by the embodiment of the present invention, according to the reality of lottery user
Consumer products participation is corrected fusion forecasting model, can be further improved the accuracy rate of prediction.
The embodiment of the invention also provides a kind of lottery user product participation forecasting systems, can be realized any of the above-described reality
Apply all processes of the lottery user product participation prediction technique in example, the effect of modules, unit in system and
The technical effect of realization respectively with the step of the lottery user product participation prediction technique in above-described embodiment effect and
The technical effect of realization corresponds to identical, and which is not described herein again.
It is shown in Figure 5, it is that one of a kind of lottery user product participation forecasting system provided by the invention is preferred real
Apply the structural block diagram of example, comprising:
Data loading module 11 is extracted and is converted to the original user data for obtaining original user data
Afterwards, it is loaded onto database with specified format classification;
Data processing module 12 is obtained for pre-processing to the original user data stored in the database
Obtain various dimensions user data;Wherein, the pretreatment includes at least consistency treatment, except processing, data transformation and data are returned again
About handle;The various dimensions user data includes at least the personal information of user, history stake information and history earnings information;
Characteristic extracting module 13, it is relevant to consumer products participation pre- for being obtained according to the various dimensions user data
Survey feature set;And
Participation prediction module 14 is right for inputting the predicted characteristics collection in fusion forecasting model trained in advance
Consumer products participation is predicted;Wherein, the fusion forecasting model is at least by Bayes classifier, random forest grader
It merges and generates with iteration decision tree classifier.
Preferably, the characteristic extracting module specifically includes:
Potential feature extraction unit, for being constructed from the various dimensions user data according to data statistic analysis and user
The relevant potential feature set of product participation;And
Predicted characteristics extraction unit, for the potential feature set to be adjusted, screens and is combined according to iteration tests,
Obtain the predicted characteristics collection.
Preferably, the lottery user product participation forecasting system further include:
Feature set division module, the training characteristics collection relevant to consumer products participation for that will be obtained ahead of time are divided into
Training set and verifying collection;
Sub-classifier establishes module, for when the fusion forecasting model is by the Bayes classifier, described random gloomy
When woods classifier and iteration decision tree classifier fusion generate, it is based respectively on the Bayes classifier, described random gloomy
Woods classifier and the iteration decision tree classifier are modeled according to the training set, corresponding to obtain at least two Bayes
Classifier, at least two random forest sub-classifiers and at least two iteration decision tree sub-classifiers;
Sub-classifier authentication module, for obtaining each Bayes's sub-classifier, every respectively according to verifying collection
The accuracy rate of the one random forest sub-classifier and each iteration decision tree sub-classifier;
Sub-classifier determining module, for determining that accuracy rate is greater than Bayes's subclassification of preset first threshold value respectively
Device, accuracy rate are greater than the random forest sub-classifier of default second threshold and accuracy rate is greater than the described of default third threshold value
Iteration decision tree sub-classifier;And
Model Fusion module, for according to determining Bayes's sub-classifier, the random forest sub-classifier and
The iteration decision tree sub-classifier fusion generates the fusion forecasting model.
Preferably, the sub-classifier is established module and is specifically included:
Modeling parameters acquiring unit is set up for choosing different at least six from the training set according to grid data service
Mould parameter;It wherein, include that at least two groups first corresponding with the Bayes classifier are built at least six groups of modeling parameters
Mould parameter, the second modeling parameters of at least two groups corresponding with the random forest grader and with the iteration decision tree classifier
Corresponding at least two groups third modeling parameters;
First sub-classifier establishes unit, for being modeled based on the Bayes classifier according at least two groups first
Parameter is modeled, corresponding to obtain at least two Bayes's sub-classifiers;
Second sub-classifier establishes unit, for being modeled based on the random forest class device according at least two groups second
Parameter is modeled, corresponding to obtain at least two random forest sub-classifiers;And
Third sub-classifier establishes unit, for being based on the iteration decision tree classifier according at least two groups third
Modeling parameters are modeled, corresponding to obtain at least two iteration decision tree sub-classifiers.
Preferably, the participation prediction module specifically includes:
Participation scoring acquiring unit passes through throwing for inputting the predicted characteristics collection in the fusion forecasting model
The mode of ticket obtains the scoring of consumer products participation within a preset period of time;Wherein, the consumer products participation score to
It less include that user preference changes scoring and user activity change scoring.
Preferably, the lottery user product participation forecasting system further include:
Prediction result display module, for the prediction result of consumer products participation to be exported in a text form, and with
The form of WEB page is shown.
As an improvement of the above scheme, it can intuitively be mentioned to user in a manner of visual by the way that user interface is arranged
For system function and prediction result, user information reading is realized.For example, system can pass through instrument board (Dashboard), Xiang Ye
Business personnel provide intuitive statistical graph, the recent basic statistics information of reflection user group, so that the behavior for holding group becomes
Gesture.Specific statistical graph includes but is not limited to that user preference changes distribution of scoring, user activity changes scoring distribution and respectively produces
Product wager amount ratio pie chart.
Preferably, the lottery user product participation forecasting system further include:
Actual participation degree obtains module, for obtaining actual user's product participation;
Prediction model accuracy rate authentication module, for verifying the fusion forecasting according to actual user's product participation
The accuracy rate of model;And
Prediction model correction module, for being corrected according to verification result to the fusion forecasting model.
It is shown in Figure 6 the embodiment of the invention also provides a kind of terminal device, it is that a kind of terminal provided by the invention is set
The structural block diagram of a standby preferred embodiment, including processor 10, memory 20 and be stored in the memory 20 and
It is configured as the computer program executed by the processor 10, the processor 10 is realized when executing the computer program
Lottery user product participation prediction technique described in any of the above-described embodiment.
Preferably, the computer program can be divided into one or more module/units (such as computer program 1, meter
Calculation machine program 2), one or more of module/units are stored in the memory 20, and by
The processor 10 executes, to complete the present invention.One or more of module/units, which can be, can complete specific function
Series of computation machine program instruction section, the instruction segment is for describing execution of the computer program in the terminal device
Journey.
The processor 10 can be central processing unit (Central Processing Unit, CPU), can also be
Other general processors, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc., general processor can be microprocessor or the processor 10 is also possible to any conventional place
Device is managed, the processor 10 is the control centre of the terminal device, utilizes terminal device described in various interfaces and connection
Various pieces.
The memory 20 mainly includes program storage area and data storage area, wherein program storage area can store operation
Application program needed for system, at least one function etc., data storage area can store related data etc..In addition, the memory
20 can be high-speed random access memory, can also be nonvolatile memory, such as plug-in type hard disk, intelligent memory card
(Smart Media Card, SMC), secure digital (Secure Digital, SD) card and flash card (Flash Card) etc., or
The memory 20 is also possible to other volatile solid-state parts.
It should be noted that above-mentioned terminal device may include, but it is not limited only to, processor, memory, those skilled in the art
Member is appreciated that Fig. 6 structural block diagram is only the example of above-mentioned terminal device, does not constitute the restriction to above-mentioned terminal device,
It may include perhaps combining certain components or different components than illustrating more or fewer components.
The embodiment of the invention also provides a kind of computer readable storage medium, the computer readable storage medium includes
The computer program of storage;Wherein, where the computer program controls the computer readable storage medium at runtime
Equipment executes lottery user product participation prediction technique described in any of the above-described embodiment.
To sum up, a kind of lottery user product participation prediction technique, system provided by the embodiment of the present invention and terminal are set
Standby, computer readable storage medium, using the various dimensions user data of lottery user, such as personal information, historical trading and profit
Situation etc. identifies that user for the preference profile of inhomogeneity lottery products, predicts user to product using Model Fusion algorithm
Participation, can reduce the prediction difficulty of lottery user product participation, and improve predictablity rate, so that operation personnel can
To take corresponding customer relation management measure in time, more high profit can be won for betting office by attracting user more to participate in
Stake in.
The above is only a preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, without departing from the technical principles of the invention, several improvement and deformations can also be made, these improvement and deformations
Also it should be regarded as protection scope of the present invention.
Claims (10)
1. a kind of lottery user product participation prediction technique characterized by comprising
Original user data is obtained, after the original user data is extracted and converted, is loaded into specified format classification
In database;
The original user data stored in the database is pre-processed, various dimensions user data is obtained;Wherein, institute
Pretreatment is stated to include at least consistency treatment, remove processing again, data transformation and data reduction process;The various dimensions user data
Information and history earnings information are bet including at least personal information, the history of user;
Predicted characteristics collection relevant to consumer products participation is obtained according to the various dimensions user data;
By in predicted characteristics collection input fusion forecasting model trained in advance, consumer products participation is predicted;Its
In, the fusion forecasting model, which is at least merged by Bayes classifier, random forest grader and iteration decision tree classifier, gives birth to
At.
2. lottery user product participation prediction technique as described in claim 1, which is characterized in that described according to the multidimensional
It spends user data and obtains predicted characteristics collection relevant to consumer products participation, specifically include:
Potential feature relevant to consumer products participation is constructed from the various dimensions user data according to data statistic analysis
Collection;
The potential feature set is adjusted, screened and combined according to iteration tests, obtains the predicted characteristics collection.
3. lottery user product participation prediction technique as described in claim 1, which is characterized in that the method passes through following
Step is trained the fusion forecasting model:
The training characteristics collection relevant to consumer products participation being obtained ahead of time is divided into training set and verifying collection;
When the fusion forecasting model is by the Bayes classifier, the random forest grader and the iteration decision tree point
When the fusion of class device generates, it is based respectively on the Bayes classifier, the random forest grader and the iteration decision tree point
Class device is modeled according to the training set, corresponding to obtain at least two Bayes's sub-classifiers, at least two random forests
Classifier and at least two iteration decision tree sub-classifiers;
Each Bayes's sub-classifier, each random forest sub-classifier and every are obtained respectively according to verifying collection
The accuracy rate of the one iteration decision tree sub-classifier;
Determine that accuracy rate is greater than Bayes's sub-classifier of preset first threshold value, accuracy rate is greater than default second threshold respectively
The random forest sub-classifier and accuracy rate be greater than the iteration decision tree sub-classifier of default third threshold value;
According to determining Bayes's sub-classifier, the random forest sub-classifier and the iteration decision tree sub-classifier
Fusion generates the fusion forecasting model.
4. lottery user product participation prediction technique as claimed in claim 2, which is characterized in that described when the fusion is pre-
When surveying model by the fusion generation of the Bayes classifier, the random forest grader and the iteration decision tree classifier,
The Bayes classifier, the random forest grader and the iteration decision tree classifier are based respectively on according to the training
Collection is modeled, corresponding to obtain at least two Bayes's sub-classifiers, at least two random forest sub-classifiers and at least two
Iteration decision tree sub-classifier, specifically includes:
Different at least six groups of modeling parameters are chosen from the training set according to grid data service;Wherein, described at least six groups
It include that the first modeling parameters of at least two groups corresponding with the Bayes classifier and the random forest are classified in modeling parameters
Corresponding the second modeling parameters of at least two groups of device and at least two groups third corresponding with iteration decision tree classifier modeling ginseng
Number;
It is modeled based on the Bayes classifier according to first modeling parameters of at least two groups, it is corresponding to obtain at least two
Bayes's sub-classifier;
It is modeled based on the random forest class device according to second modeling parameters of at least two groups, it is corresponding to obtain at least two
The random forest sub-classifier;
It is modeled based on the iteration decision tree classifier according at least two groups third modeling parameters, it is corresponding to obtain at least
Two iteration decision tree sub-classifiers.
5. lottery user product participation prediction technique as described in claim 1, which is characterized in that described that the prediction is special
In collection input fusion forecasting model trained in advance, consumer products participation is predicted, is specifically included:
The predicted characteristics collection is inputted in the fusion forecasting model, is obtained within a preset period of time by way of ballot
The scoring of consumer products participation;Wherein, the consumer products participation scoring includes at least user preference change scoring and user
Liveness changes scoring.
6. lottery user product participation prediction technique as described in claim 1, which is characterized in that the method also includes:
The prediction result of consumer products participation is exported in a text form, and is shown in the form of WEB page.
7. lottery user product participation prediction technique as described in claim 1, which is characterized in that the method also includes:
Obtain actual user's product participation;
The accuracy rate of the fusion forecasting model is verified according to actual user's product participation;
The fusion forecasting model is corrected according to verification result.
8. a kind of lottery user product participation forecasting system characterized by comprising
Data loading module, for obtaining original user data, after the original user data is extracted and converted, to refer to
Determine format classification to be loaded onto database;
Data processing module obtains multidimensional for pre-processing to the original user data stored in the database
Spend user data;Wherein, the pretreatment includes at least consistency treatment, removes processing again, data transformation and data reduction process;
The various dimensions user data includes at least the personal information of user, history stake information and history earnings information;
Characteristic extracting module, for obtaining predicted characteristics relevant to consumer products participation according to the various dimensions user data
Collection;And
Participation prediction module, for being produced to user by predicted characteristics collection input fusion forecasting model trained in advance
Product participation is predicted;Wherein, the fusion forecasting model is at least by Bayes classifier, random forest grader and iteration
Decision tree classifier fusion generates.
9. a kind of terminal device, which is characterized in that including processor, memory and store in the memory and be configured
For the computer program executed by the processor, the processor realizes such as claim when executing the computer program
Lottery user product participation prediction technique described in any one of 1 to 7.
10. a kind of computer readable storage medium, which is characterized in that the computer readable storage medium includes the calculating of storage
Machine program;Wherein, the equipment where the computer program controls the computer readable storage medium at runtime executes such as
Lottery user product participation prediction technique described in any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810841269.0A CN109146549A (en) | 2018-07-26 | 2018-07-26 | Lottery user product participation prediction technique, system and equipment, storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810841269.0A CN109146549A (en) | 2018-07-26 | 2018-07-26 | Lottery user product participation prediction technique, system and equipment, storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109146549A true CN109146549A (en) | 2019-01-04 |
Family
ID=64798236
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810841269.0A Pending CN109146549A (en) | 2018-07-26 | 2018-07-26 | Lottery user product participation prediction technique, system and equipment, storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109146549A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111652430A (en) * | 2020-05-29 | 2020-09-11 | 蚌埠学院 | Internet financial platform default rate prediction method and system |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101276492A (en) * | 2008-05-05 | 2008-10-01 | 中兴通讯股份有限公司 | Apparatus and method for processing lottery historical data |
CN105631538A (en) * | 2015-12-23 | 2016-06-01 | 北京奇虎科技有限公司 | User activity prediction method and device, and application method and system thereof |
CN106097111A (en) * | 2016-06-20 | 2016-11-09 | 重庆房慧科技有限公司 | A kind of public opinion prediction method based on the big data of intelligence community network |
CN106600423A (en) * | 2016-11-18 | 2017-04-26 | 云数信息科技(深圳)有限公司 | Machine learning-based car insurance data processing method and device and car insurance fraud identification method and device |
CN106997493A (en) * | 2017-02-14 | 2017-08-01 | 云数信息科技(深圳)有限公司 | Lottery user attrition prediction method and its system based on multi-dimensional data |
-
2018
- 2018-07-26 CN CN201810841269.0A patent/CN109146549A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101276492A (en) * | 2008-05-05 | 2008-10-01 | 中兴通讯股份有限公司 | Apparatus and method for processing lottery historical data |
CN105631538A (en) * | 2015-12-23 | 2016-06-01 | 北京奇虎科技有限公司 | User activity prediction method and device, and application method and system thereof |
CN106097111A (en) * | 2016-06-20 | 2016-11-09 | 重庆房慧科技有限公司 | A kind of public opinion prediction method based on the big data of intelligence community network |
CN106600423A (en) * | 2016-11-18 | 2017-04-26 | 云数信息科技(深圳)有限公司 | Machine learning-based car insurance data processing method and device and car insurance fraud identification method and device |
CN106997493A (en) * | 2017-02-14 | 2017-08-01 | 云数信息科技(深圳)有限公司 | Lottery user attrition prediction method and its system based on multi-dimensional data |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111652430A (en) * | 2020-05-29 | 2020-09-11 | 蚌埠学院 | Internet financial platform default rate prediction method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106997493A (en) | Lottery user attrition prediction method and its system based on multi-dimensional data | |
CN109508807A (en) | Lottery user liveness prediction technique, system and terminal device, storage medium | |
CN103370722B (en) | The system and method that actual volatility is predicted by small echo and nonlinear kinetics | |
Ollech et al. | A random forest-based approach to identifying the most informative seasonality tests | |
CN113537807B (en) | Intelligent wind control method and equipment for enterprises | |
Liu et al. | Patent analysis and classification prediction of biomedicine industry: SOM-KPCA-SVM model | |
CN111950622A (en) | Behavior prediction method, behavior prediction device, behavior prediction terminal and storage medium based on artificial intelligence | |
CN106294882A (en) | Data digging method and device | |
Sun et al. | Classifier selection and ensemble model for multi-class imbalance learning in education grants prediction | |
CN111639706A (en) | Personal risk portrait generation method based on image set and related equipment | |
Wu et al. | Equity2vec: End-to-end deep learning framework for cross-sectional asset pricing | |
Pahmi et al. | Implementation of CART (classification and regression trees) algorithm for determining factors affecting employee performance | |
EP3223227A1 (en) | System and method for predicting financial and / or market data | |
Aviad et al. | A decision support method, based on bounded rationality concepts, to reveal feature saliency in clustering problems | |
Glauner | Artificial intelligence for the detection of electricity theft and irregular power usage in emerging markets | |
Xie et al. | Evaluating performance of super-efficiency models in ranking efficient decision-making units based on Monte Carlo simulations | |
CN109146549A (en) | Lottery user product participation prediction technique, system and equipment, storage medium | |
CN109840536A (en) | A kind of power grid power supply reliability horizontal clustering method and system | |
Mari et al. | Gaussian clustering and jump-diffusion models of electricity prices: a deep learning analysis | |
Marechal et al. | Whose preferences matter for redistribution: Cross-country evidence | |
Bharathy et al. | Applications of social systems modeling to political risk management | |
CN113987351A (en) | Artificial intelligence based intelligent recommendation method and device, electronic equipment and medium | |
CN113706258A (en) | Product recommendation method, device, equipment and storage medium based on combined model | |
CN113656692B (en) | Product recommendation method, device, equipment and medium based on knowledge migration algorithm | |
Zain et al. | Tri-model ensemble with grid search optimization for bipolar disorder diagnosis |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190104 |
|
RJ01 | Rejection of invention patent application after publication |