CN110276634A - Value of the product evaluation method, device and computer readable storage medium - Google Patents
Value of the product evaluation method, device and computer readable storage medium Download PDFInfo
- Publication number
- CN110276634A CN110276634A CN201910422084.0A CN201910422084A CN110276634A CN 110276634 A CN110276634 A CN 110276634A CN 201910422084 A CN201910422084 A CN 201910422084A CN 110276634 A CN110276634 A CN 110276634A
- Authority
- CN
- China
- Prior art keywords
- product
- value
- stage
- existing
- factor
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 17
- 238000000034 method Methods 0.000 claims abstract description 56
- 238000004458 analytical method Methods 0.000 claims description 32
- 238000004364 calculation method Methods 0.000 claims description 19
- 239000011159 matrix material Substances 0.000 claims description 14
- 230000006870 function Effects 0.000 claims description 12
- 230000006399 behavior Effects 0.000 claims description 9
- 238000012216 screening Methods 0.000 claims description 7
- 238000004519 manufacturing process Methods 0.000 claims description 2
- 238000003066 decision tree Methods 0.000 description 18
- 230000008569 process Effects 0.000 description 11
- 238000013528 artificial neural network Methods 0.000 description 10
- 238000012706 support-vector machine Methods 0.000 description 10
- 230000008901 benefit Effects 0.000 description 7
- 238000012549 training Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000000556 factor analysis Methods 0.000 description 4
- 210000005036 nerve Anatomy 0.000 description 4
- 238000010606 normalization Methods 0.000 description 4
- 238000000513 principal component analysis Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 3
- 239000010931 gold Substances 0.000 description 3
- 229910052737 gold Inorganic materials 0.000 description 3
- 102000003712 Complement factor B Human genes 0.000 description 2
- 108090000056 Complement factor B Proteins 0.000 description 2
- 241001269238 Data Species 0.000 description 2
- 101000629361 Homo sapiens Paraplegin Proteins 0.000 description 2
- 102100027006 Paraplegin Human genes 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 210000004556 brain Anatomy 0.000 description 2
- 239000006185 dispersion Substances 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000008676 import Effects 0.000 description 2
- 230000010365 information processing Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 230000035800 maturation Effects 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000013138 pruning Methods 0.000 description 2
- 210000000225 synapse Anatomy 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
- G06Q30/0278—Product appraisal
-
- 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
- G06Q40/02—Banking, e.g. interest calculation or account maintenance
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Technology Law (AREA)
- Entrepreneurship & Innovation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention relates to big data technical fields, disclose a kind of value of the product evaluation method, this method comprises: each stage according to existing product in life cycle makes profits, carry out weight assignment to the value in each stage；The historical yield data of the preset time period of the existing product are obtained, and according to the weight in each stage, estimate the prospective earnings in existing product future；The existing product is subjected to category division and estimates the operation income of each category product according to the prospective earnings of the existing product；And when opening new product, according to the feature of the product, by the product assortment in above-mentioned classification, and according to the operation income of category product, value assessment is carried out to the new product.The present invention also proposes a kind of value of the product estimation device and a kind of computer readable storage medium.The present invention can estimate the value of newly developed product.
Description
Technical field
The present invention relates to big data technical fields more particularly to a kind of value of the product evaluation method, device and computer can
Read storage medium.
Background technique
Currently, banking is when calculating the customer value contribution degree of a certain product, not enough intuitively, simply, be primarily present with
Lower problem: 1, only consider the whole customer value of product, be not finely divided customer value by customer life cycle；2, only consider
Existing customer value, the client comprehensive that do not look to the future are made profits；3, traditional financial bore is according to assets/debt earning rate * AUM/
LUM assets year, average daily mode carried out single AUM/LUM revenue calculation, cannot intuitively calculate client's income of product.
Summary of the invention
The present invention provides a kind of value of the product evaluation method, device and computer readable storage medium, main purpose and exists
In providing a kind of mechanism of selecting stocks of subjective experience independent of analyst, effect of selecting stocks is promoted.
To achieve the above object, a kind of value of the product evaluation method provided by the invention, comprising:
S1, each stage according to existing product in life cycle make profits, and weigh to the value in each stage
Reassignment；
The historical yield data of the preset time period of S2, the acquisition existing product, and according to the power in each stage
Weight, estimates the prospective earnings in existing product future；
S3, existing product progress category division is estimated into each classification according to the prospective earnings of the existing product
The operation income of product；And
S4, when opening new product, according to the feature of the product, by the product assortment in above-mentioned classification, and according to this
The operation income of category product carries out value assessment to the new product.
Optionally, the S1 includes:
One or more kinds of existing products are selected, the historical data of selected product is obtained；
The historical data is pre-processed；
The pretreated data are imported into preset table, wherein the behavior property value in table, the column in table
For each stage of life cycle；
According to the stage included by the life cycle, the sample average in each stage is sought respectively；
The matrix of different dimensions is set according to sample average for the different phase of life cycle；
The characteristic value of the matrix in life cycle each stage is calculated separately, vector is constituted；
With factorial analysis flexible strategy algorithm, factor loading battle array is sought, on the basis of factor loading battle array, finds common factor
Number；
By factorial analysis flexible strategy model, the contribution rate of each factor in each stage factor load battle array of step by step calculation, setting
Contribution rate threshold value comes out the factor screening that the sum of contribution rate is greater than threshold value, composing indexes factor set；
Weigh algorithm using the tax in factorial analysis flexible strategy model, according to the index factor collection, to each stage into
Row assigns power.
Optionally, this method estimates the prospective earnings in the existing product future using following functions:
Prospective earnings=α (First Year capital × earning rate × time limit/365)+β (second year capital × expected yield ×
Time limit/365)+γ (third year capital × expected yield × time limit/365),
Wherein, described α, β, γ are the weight in the life cycle each stage, and alpha+beta+γ=1, the second year sheet
Gold=First Year capital+income, third year capital=second year capital+income.
Optionally, the S3 includes:
Obtain the customer data of existing product；
One or more kinds of classifying methods are selected, the classification of the existing product is calculated using the customer data；
According to the classification calculated, class label is marked to each client of the existing product；
According to the prospective earnings of the client of mark class label, received using the operation that following formula calculates category product
Benefit:
Wherein, YiFor the i-th class product, N is the customer quantity for having bought such product, it is contemplated that income is to buy such product
Client prospective earnings.
Optionally, the S4 includes:
Signature analysis is carried out to the new product, and according to the feature, by the product assortment in above-mentioned classification；
According to the estimated customer quantity of the operation income of category product and the product, the expection of the budget new product
Income, and using this as the value of the new product, calculation formula are as follows:
Vi=Yi×M
Wherein, ViFor incorporate into i classification new product estimated value, YiFor the operation income of category product, M is should
The expection customer quantity of new product.
In addition, to achieve the above object, the present invention also provides a kind of values of the product to estimate device, which includes memory
And processor, the value of the product estimation program that can be run on the processor, the product valence are stored in the memory
Value estimation program realizes following steps when being executed by the processor:
S1, each stage according to existing product in life cycle make profits, and weigh to the value in each stage
Reassignment；
The historical yield data of the preset time period of S2, the acquisition existing product, and according to the power in each stage
Weight, estimates the prospective earnings in existing product future；
S3, existing product progress category division is estimated into each classification according to the prospective earnings of the existing product
The operation income of product；And
S4, when opening new product, according to the feature of the product, by the product assortment in above-mentioned classification, and according to this
The operation income of category product carries out value assessment to the new product.
Optionally, the S1 includes:
One or more kinds of existing products are selected, the historical data of selected product is obtained；
The historical data is pre-processed；
The pretreated data are imported into preset table, wherein the behavior property value in table, the column in table
For each stage of life cycle；
According to the stage included by the life cycle, the sample average in each stage is sought respectively；
The matrix of different dimensions is set according to sample average for the different phase of life cycle；
The characteristic value of the matrix in life cycle each stage is calculated separately, vector is constituted；
With factorial analysis flexible strategy algorithm, factor loading battle array is sought, on the basis of factor loading battle array, finds common factor
Number；
By factorial analysis flexible strategy model, the contribution rate of each factor in each stage factor load battle array of step by step calculation, setting
Contribution rate threshold value comes out the factor screening that the sum of contribution rate is greater than threshold value, composing indexes factor set；
Weigh algorithm using the tax in factorial analysis flexible strategy model, according to the index factor collection, to each stage into
Row assigns power.
Optionally, the prospective earnings in the estimation existing product future use such as minor function:
Prospective earnings=α (First Year capital × earning rate × time limit/365)+β (second year capital × expected yield ×
Time limit/365)+γ (third year capital × expected yield × time limit/365),
Wherein, described α, β, γ are the weight in the life cycle each stage, and alpha+beta+γ=1, the second year sheet
Gold=First Year capital+income, third year capital=second year capital+income.
Optionally, the S3 includes:
Obtain the customer data of existing product；
One or more kinds of classifying methods are selected, the classification of the existing product is calculated using the customer data；
According to the classification calculated, class label is marked to each client of the existing product；
According to the prospective earnings of the client of mark class label, received using the operation that following formula calculates category product
Benefit:
Wherein, YiFor the i-th class product, N is the customer quantity for having bought such product, it is contemplated that income is to buy such product
Client prospective earnings.
In addition, to achieve the above object, it is described computer-readable the present invention also provides a kind of computer readable storage medium
Value of the product estimation program is stored on storage medium, the value of the product estimation program can be held by one or more processor
Row, the step of to realize value of the product evaluation method as described above.
Value of the product evaluation method, device and computer readable storage medium proposed by the present invention are by drawing existing product
It is divided into different life cycle phases, and assigns weight to each stage, estimates the prospective earnings of existing product and to existing product
Classify, calculate the operation income of every a kind of product, thus realize it is different classes of under new product value assessment.
Detailed description of the invention
Fig. 1 is the flow diagram for the value of the product evaluation method that one embodiment of the invention provides；
Fig. 2 is the schematic diagram of internal structure that the value of the product that one embodiment of the invention provides estimates device；
Fig. 3 is the module signal that the value of the product that one embodiment of the invention provides estimates value of the product estimation program in device
Figure.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that described herein, specific examples are only used to explain the present invention, not
For limiting the present invention.Based on the embodiments of the present invention, those of ordinary skill in the art are not before making creative work
Every other embodiment obtained is put, shall fall within the protection scope of the present invention.
The description and claims of this application and term " first ", " second ", " third ", " in above-mentioned attached drawing
The (if present)s such as four " are to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should manage
The data that solution uses in this way are interchangeable under appropriate circumstances, so that the embodiments described herein can be in addition to illustrating herein
Or the sequence other than the content of description is implemented.In addition, the description of " first ", " second " etc. is used for description purposes only, without
It can be interpreted as its relative importance of indication or suggestion or implicitly indicate the quantity of indicated technical characteristic.It defines as a result,
The feature of " first ", " second " can explicitly or implicitly include at least one of the features.
Further, term " includes " and " having " and their any deformation, it is intended that cover non-exclusive packet
Contain, for example, what the process, method, system, product or equipment for containing a series of steps or units were not necessarily limited to be clearly listed
Those step or units, but may include be not clearly listed or it is intrinsic for these process, methods, product or equipment
Other step or units.
It in addition, the technical solution between each embodiment can be combined with each other, but must be with ordinary skill
Based on personnel can be realized, this technical side will be understood that when the combination of technical solution appearance is conflicting or cannot achieve
The combination of case is not present, also not the present invention claims protection scope within.
The present invention provides a kind of value of the product evaluation method.It is the product that one embodiment of the invention provides shown in referring to Fig.1
The flow diagram of value estimate method.This method can be executed by a device, which can be by software and/or hardware reality
It is existing.
In the present embodiment, value of the product evaluation method includes:
S1, each stage according to existing product in life cycle make profits, and weigh to the value in each stage
Reassignment.
In present pre-ferred embodiments, the Life cycle includes downloading, registering, tie up card, become effective client.
The purpose of the step is to provide objective effective weight for the calculating of income.Life cycle locating for different clients
Stage is different, and the earned value that different life cycle phases is contributed in the value valuation of product is also different, therefore needs
Rationally objective weight assignment is carried out to the different phase of life cycle.
The basis of weight assignment is the stage for clearly dividing life cycle, own to product life cycle maturation according to bank
Divided stages, that is, download, register, tie up card, become effective client on the basis of, present pre-ferred embodiments obtain one kind first
The historical data of bank product is carried out the data predictions such as null value, normalization, then imports pretreated data
Into preset table, wherein each dimension attribute for being classified as data in the table, behavior historical sample data.
The method of weight assignment mainly has entropy assessment, factorial analysis flexible strategy method, principal component analysis flexible strategy method, independence power system
Number method.
The characteristics of entropy assessment is that the comentropy of some index is bigger (i.e. dispersion degree is bigger), shows the information that index provides
It measures more, can play the role of in overall merit also bigger, weight is also bigger.
The purpose of factorial analysis is to be gone to describe the connection between many indexs and factor with a few factor, and the factor does not have
Direct physical meaning.Factorial analysis flexible strategy method is that the contribution rate of accumulative total of the general character factor is calculated to each index to determine power.
The main distinction of principal component analysis flexible strategy method and factor analysis is: principal component is weighted by original characteristic line
It arrives, and in factor analysis, factor linear weights to obtain original feature.Index weights are the variance contribution ratio of principal component.
If independence weight coefficient is characterized in that the multiple correlation coefficient of index and other indexs is bigger, with other indexs
Co-linear relationship is stronger, and duplicate message is more, so index weights are smaller.Namely independence is stronger, index weights are bigger.
Object properties and feature according to the present invention, present pre-ferred embodiments selective factor B analyzes flexible strategy method, specific to flow
Journey is as follows:
(1) one or more kinds of existing products are selected, such as bank product obtains the historical data of selected product；
(2) pretreatment such as null value, normalization is carried out to the historical data, is processed into clean data；
(3) the pretreated data are imported into preset table, wherein the behavior property value in table, in table
The each stage for being classified as life cycle；
(4) according to the stage included by the life cycle, the sample average in each stage is sought respectively；
(5) it is directed to different phase, according to sample average, the matrix of different dimensions is set；
(6) on the basis of step 5, the characteristic value of the matrix in life cycle each stage is calculated separately, constitutes vector；
(7) factorial analysis flexible strategy algorithm is used, factor loading battle array is sought, on the basis of factor loading battle array, finds common factor
Number；
(8) pass through factorial analysis flexible strategy model, the contribution rate of each factor in each stage factor load battle array of step by step calculation, if
Contribution rate threshold value is set, the factor screening that the sum of contribution rate is greater than threshold value is come out, final index factor collection is constituted；
(9) algorithm is weighed using the tax in factorial analysis flexible strategy model, according to index factor collection, each stage is assigned
Power.
Further, present pre-ferred embodiments efficiently realize the tax in life cycle each stage by the programming of python
Power.
S2, the preset time period for obtaining the existing product, such as 3 years history avail datas, and according to each stage
Weight estimates the prospective earnings in existing product future, so that the operation income for the product provides objective reality and reliably throws
Produce prediction avail data support.
Present pre-ferred embodiments obtain bank product and start in current point in time, the historical yield of three calculated forward year
Data are used and are estimated following prospective earnings with minor function:
Prospective earnings=α (First Year capital × earning rate × time limit/365)+β (second year capital × expected yield ×
Time limit/365)+γ (third year capital × expected yield × time limit/365),
Wherein, the weight in life cycle each stage described in described α, β, γ, and alpha+beta+γ=1.
Wherein, second year capital=First Year capital+income.Third year capital=second year capital+income.The present invention compared with
In good embodiment, the earning rate is according to unified standard as defined in People's Bank of China, and the expected yield used is pre-
The year earning rate of phase, the time limit, when calculating, which need to be converted to, to be calculated in year using day as unit of account.The earning rate indicates certain
The ratio of interest amount and capital, is usually expressed as a percentage in period, and annualized to be then known as Annual Percentage Rate, calculation formula is:
Earning rate=interest amount/capital x time × 100%.
Such as: it is assumed that capital is 100,000 yuans, the reference year earning rate for investing in the product is 5.4%, practical
Time limit is 62 days, then income=100000 × 5.4% of client × 62/360=930 member.
S3, existing product progress category division is estimated into each classification according to the prospective earnings of the existing product
The operation income of product.
Present pre-ferred embodiments can with the following method sort out the product: decision tree, rule-based point
Class, nearest neighbour classification (K-NN), Naive Bayes Classifier, artificial neural network, support vector machines (SVM).
The decision tree is the induced learning algorithm based on example, is conceived to out of order, random from one group
Example in infer with the classifying rules of decision tree representation.The purpose for constructing decision tree is the pass found out between attribute and classification
System, to predict the classification of the record of unknown classification in the future.The decision tree uses top-down recursive fashion, in decision tree
Internal node carries out the comparison of attribute, and the branch downward from the node is judged according to different attribute value, in the leaf segment of decision tree
Point it is concluded that.Main decision Tree algorithms have ID3, C4.5 (C5.0), CART, PUBLIC, SLIQ and SPRINT algorithm etc., it
Selection testing attribute use technology, the structure of decision tree of generation, the method for beta pruning and moment, big number can be handled
There is respective difference according to collection etc..
The rule-based classification is generally to be made of two steps: first step association rules mining algorithm is from training dataset
In excavate all class association rules for meeting specified support and confidence level；Second step is using heuristic from excavating
The rule of one group of high quality is picked out in class association rules for classifying.The algorithm for belonging to associative classification mainly includes CBA, ADT,
CMAR etc..
The nearest neighbour classification, also referred to as k- neighbour (kNN, k-Nearest Neighbors), the algorithm are a kind of based on real
The classification method of example, finds out with unknown sample x apart from k nearest training sample, wherein which majority belongs in this k sample
Which kind of x is just classified as by one kind.
The Naive Bayes Classifier is a kind of algorithm classified using probability statistics knowledge, is mainly utilized
Bayes theorem predicts a possibility that sample of a unknown classification belongs to each classification, selection wherein possibility maximum one
Final classification of a classification as the sample.
The artificial neural network (Artificial Neural Networks, ANN) is that a kind of application is similar to brain
The structure of nerve synapse connection carries out the mathematical model of information processing.In this model, a large amount of node (or " nerve
Member ", or " unit ") between be coupled to each other composition network, i.e., " neural network ", with achieve the purpose that handle information.Neural network
It is generally necessary to be trained, trained process is exactly the process that network is learnt.Training changes the connection weight of network node
Value make it have the function of classification, trained network just can be used for the identification of object.
Support vector machines (SVM, the Support Vector Machine) algorithm is calculated according to the sample in region should
The decision curved surface in region, thereby determines that the classification of unknown sample in the region.
Present pre-ferred embodiments can select most appropriate classifying method according to different classes of product demand, make in this way
The classification for obtaining product has more flexibility, more meets real usability.
In present pre-ferred embodiments, the S3 the specific implementation process is as follows:
(1) customer data of existing product is obtained；
(2) one or more kinds of classifying methods are selected, the classification of the existing product is calculated using the customer data；
(3) classification calculated according to marks class label to each client of the existing product；
(4) according to the prospective earnings of the client of mark class label, the operation of category product is calculated using following formula
Income:
Wherein, YiFor i-th of product, N is the customer quantity for having bought the product, it is contemplated that income is to buy the list of the product
The prospective earnings of a client.
S4, when opening new product, according to the feature of the product, by the product assortment in existing classification, and according to this
The operation income of category product carries out value assessment to the new product.
In present pre-ferred embodiments, specific step is as follows by the S4:
(1) signature analysis is carried out to the new product by bank employee, analyze the customers of the product, earning cycle,
The features such as average expectancy earning rate, risk class, according to these features, by the product assortment to existing classification；
(2) customer quantity estimated according to the operation income of category product and the product, the budget new product it is pre-
Phase income, and using this as the value of the new product.Specific formula for calculation are as follows:
Vi=Yi×M
Wherein, ViFor incorporate into i classification new product estimated value, M be the new product expection customer quantity.
The present invention also provides a kind of values of the product to estimate device.It is the production that one embodiment of the invention provides referring to shown in Fig. 2
The schematic diagram of internal structure of product value estimate device.
In the present embodiment, value of the product estimation device 1 can be PC (Personal Computer, PC),
It can be the terminal devices such as smart phone, tablet computer, portable computer.The value of the product estimates that device 1 includes at least storage
Device 11, processor 12, communication bus 13 and network interface 14.
Wherein, memory 11 include at least a type of readable storage medium storing program for executing, the readable storage medium storing program for executing include flash memory,
Hard disk, multimedia card, card-type memory (for example, SD or DX memory etc.), magnetic storage, disk, CD etc..Memory 11
It can be the internal storage unit of value of the product estimation device 1 in some embodiments, such as the value of the product estimates device 1
Hard disk.Memory 11 is also possible to the External memory equipment of value of the product estimation device 1, such as product in further embodiments
The plug-in type hard disk being equipped on value estimate device 1, intelligent memory card (Smart Media Card, SMC), secure digital
(Secure Digital, SD) card, flash card (Flash Card) etc..Further, memory 11 can also both include product
The internal storage unit of value estimate device 1 also includes External memory equipment.Memory 11 can be not only used for storage and be installed on
Value of the product estimates the application software and Various types of data, such as the code of value of the product estimation program 01 etc. of device 1, can also use
In temporarily storing the data that has exported or will export.
Processor 12 can be in some embodiments a central processing unit (Central Processing Unit,
CPU), controller, microcontroller, microprocessor or other data processing chips, the program for being stored in run memory 11
Code or processing data, such as execute value of the product estimation program 01 etc..
Communication bus 13 is for realizing the connection communication between these components.
Network interface 14 optionally may include standard wireline interface and wireless interface (such as WI-FI interface), be commonly used in
Communication connection is established between the device 1 and other electronic equipments.
Optionally, which can also include user interface, and user interface may include display (Display), input
Unit such as keyboard (Keyboard), optional user interface can also include standard wireline interface and wireless interface.It is optional
Ground, in some embodiments, display can be light-emitting diode display, liquid crystal display, touch-control liquid crystal display and OLED
(Organic Light-Emitting Diode, Organic Light Emitting Diode) touches device etc..Wherein, display can also be appropriate
Referred to as display screen or display unit, for being shown in the information handled in value of the product estimation device 1 and for showing visually
The user interface of change.
Fig. 2, which is illustrated only, estimates device 1 with the value of the product of component 11-14 and value of the product estimation program 01, this
Field technical staff, can be with it is understood that structure shown in fig. 1 does not constitute the restriction to value of the product estimation device 1
Including perhaps combining certain components or different component layouts than illustrating less perhaps more components.
In 1 embodiment of device shown in Fig. 2, value of the product estimation program 01 is stored in memory 11；Processor 12
Following steps are realized when executing the value of the product estimation program 01 stored in memory 11:
Step 1: each stage according to existing product in life cycle makes profits, to the value in each stage into
Row weight assignment.
In present pre-ferred embodiments, the Life cycle includes downloading, registering, tie up card, become effective client.
The purpose of the step is to provide objective effective weight for the calculating of income.Life cycle locating for different clients
Stage is different, and the earned value that different life cycle phases is contributed in the value valuation of product is also different, therefore needs
Rationally objective weight assignment is carried out to the different phase of life cycle.
The basis of weight assignment is the stage for clearly dividing life cycle, own to product life cycle maturation according to bank
Divided stages, that is, download, register, tie up card, become effective client on the basis of, present pre-ferred embodiments obtain one kind first
The historical data of bank product is carried out the data predictions such as null value, normalization, then imports pretreated data
Into preset table, wherein each dimension attribute for being classified as data in the table, behavior historical sample data.
The method of weight assignment mainly has entropy assessment, factorial analysis flexible strategy method, principal component analysis flexible strategy method, independence power system
Number method.
The characteristics of entropy assessment is that the comentropy of some index is bigger (i.e. dispersion degree is bigger), shows the information that index provides
It measures more, can play the role of in overall merit also bigger, weight is also bigger.
The purpose of factorial analysis is to be gone to describe the connection between many indexs and factor with a few factor, and the factor does not have
Direct physical meaning.Factorial analysis flexible strategy method is that the contribution rate of accumulative total of the general character factor is calculated to each index to determine power.
The main distinction of principal component analysis flexible strategy method and factor analysis is: principal component is weighted by original characteristic line
It arrives, and in factor analysis, factor linear weights to obtain original feature.Index weights are the variance contribution ratio of principal component.
If independence weight coefficient is characterized in that the multiple correlation coefficient of index and other indexs is bigger, with other indexs
Co-linear relationship is stronger, and duplicate message is more, so index weights are smaller.Namely independence is stronger, index weights are bigger.
Object properties and feature according to the present invention, present pre-ferred embodiments selective factor B analyzes flexible strategy method, specific to flow
Journey is as follows:
(1) one or more kinds of existing products are selected, such as bank product obtains the historical data of selected product；
(2) pretreatment such as null value, normalization is carried out to the historical data, is processed into clean data；
(3) the pretreated data are imported into preset table, wherein the behavior property value in table, in table
The each stage for being classified as life cycle；
(4) according to the stage included by the life cycle, the sample average in each stage is sought respectively；
(5) it is directed to different phase, according to sample average, the matrix of different dimensions is set；
(6) on the basis of step 5, the characteristic value of the matrix in life cycle each stage is calculated separately, constitutes vector；
(7) factorial analysis flexible strategy algorithm is used, factor loading battle array is sought, on the basis of factor loading battle array, finds common factor
Number；
(8) pass through factorial analysis flexible strategy model, the contribution rate of each factor in each stage factor load battle array of step by step calculation, if
Contribution rate threshold value is set, the factor screening that the sum of contribution rate is greater than threshold value is come out, final index factor collection is constituted；
(9) algorithm is weighed using the tax in factorial analysis flexible strategy model, according to index factor collection, each stage is assigned
Power.
Further, present pre-ferred embodiments efficiently realize the tax in life cycle each stage by the programming of python
Power.
Step 2: the preset time period of the existing product is obtained, such as 3 years history avail datas, and according to each rank
The weight of section, estimates the prospective earnings in existing product future, so as to provide objective reality reliable for the operation income of the product
Operation prediction avail data support.
Present pre-ferred embodiments obtain bank product and start in current point in time, the historical yield of three calculated forward year
Data are used and are estimated following prospective earnings with minor function:
Prospective earnings=α (First Year capital × earning rate × time limit/365)+β (second year capital × expected yield ×
Time limit/365)+γ (third year capital × expected yield × time limit/365),
Wherein, the weight in life cycle each stage described in described α, β, γ, and alpha+beta+γ=1.
Wherein, second year capital=First Year capital+income.Third year capital=second year capital+income.The present invention compared with
In good embodiment, the earning rate is according to unified standard as defined in People's Bank of China, and the expected yield used is pre-
The year earning rate of phase, the time limit, when calculating, which need to be converted to, to be calculated in year using day as unit of account.The earning rate indicates certain
The ratio of interest amount and capital, is usually expressed as a percentage in period, and annualized to be then known as Annual Percentage Rate, calculation formula is:
Earning rate=interest amount/capital x time × 100%.
Such as: it is assumed that capital is 100,000 yuans, the reference year earning rate for investing in the product is 5.4%, practical
Time limit is 62 days, then income=100000 × 5.4% of client × 62/360=930 member.
It is estimated each Step 3: the existing product is carried out category division according to the prospective earnings of the existing product
The operation income of category product.
Present pre-ferred embodiments can with the following method sort out the product: decision tree, rule-based point
Class, nearest neighbour classification (K-NN), Naive Bayes Classifier, artificial neural network, support vector machines (SVM).
The decision tree is the induced learning algorithm based on example, is conceived to out of order, random from one group
Example in infer with the classifying rules of decision tree representation.The purpose for constructing decision tree is the pass found out between attribute and classification
System, to predict the classification of the record of unknown classification in the future.The decision tree uses top-down recursive fashion, in decision tree
Internal node carries out the comparison of attribute, and the branch downward from the node is judged according to different attribute value, in the leaf segment of decision tree
Point it is concluded that.Main decision Tree algorithms have ID3, C4.5 (C5.0), CART, PUBLIC, SLIQ and SPRINT algorithm etc., it
Selection testing attribute use technology, the structure of decision tree of generation, the method for beta pruning and moment, big number can be handled
There is respective difference according to collection etc..
The rule-based classification is generally to be made of two steps: first step association rules mining algorithm is from training dataset
In excavate all class association rules for meeting specified support and confidence level；Second step is using heuristic from excavating
The rule of one group of high quality is picked out in class association rules for classifying.The algorithm for belonging to associative classification mainly includes CBA, ADT,
CMAR etc..
The nearest neighbour classification, also referred to as k- neighbour (kNN, k-Nearest Neighbors), the algorithm are a kind of based on real
The classification method of example, finds out with unknown sample x apart from k nearest training sample, wherein which majority belongs in this k sample
Which kind of x is just classified as by one kind.
The Naive Bayes Classifier is a kind of algorithm classified using probability statistics knowledge, is mainly utilized
Bayes theorem predicts a possibility that sample of a unknown classification belongs to each classification, selection wherein possibility maximum one
Final classification of a classification as the sample.
The artificial neural network (Artificial Neural Networks, ANN) is that a kind of application is similar to brain
The structure of nerve synapse connection carries out the mathematical model of information processing.In this model, a large amount of node (or " nerve
Member ", or " unit ") between be coupled to each other composition network, i.e., " neural network ", with achieve the purpose that handle information.Neural network
It is generally necessary to be trained, trained process is exactly the process that network is learnt.Training changes the connection weight of network node
Value make it have the function of classification, trained network just can be used for the identification of object.
Support vector machines (SVM, the Support Vector Machine) algorithm is calculated according to the sample in region should
The decision curved surface in region, thereby determines that the classification of unknown sample in the region.
Present pre-ferred embodiments can select most appropriate classifying method according to different classes of product demand, make in this way
The classification for obtaining product has more flexibility, more meets real usability.
In present pre-ferred embodiments, the step 3 the specific implementation process is as follows:
(1) customer data of existing product is obtained；
(2) one or more kinds of classifying methods are selected, the classification of the existing product is calculated using the customer data；
(3) classification calculated according to marks class label to each client of the existing product；
(4) according to the prospective earnings of the client of mark class label, the operation of category product is calculated using following formula
Income:
Wherein, YiFor i-th of product, N is the customer quantity for having bought the product, it is contemplated that income is to buy the list of the product
The prospective earnings of a client.
Step 4: when opening new product, according to the feature of the product, by the product assortment in existing classification, and root
According to the operation income of category product, value assessment is carried out to the new product.
In present pre-ferred embodiments, specific step is as follows for the step 4:
(1) signature analysis is carried out to newly developed product, analyzes customers, the earning cycle, average expectancy receipts of the product
The features such as beneficial rate, risk class, according to these features, by the product assortment to existing classification；
(2) customer quantity estimated according to the operation income of category product and the product, the budget new product it is pre-
Phase income, and using this as the value of the new product.Specific formula for calculation are as follows:
Vi=Yi×M
Wherein, ViFor incorporate into i classification new product estimated value, M be the new product expection customer quantity.
Optionally, in other embodiments, value of the product estimation program can also be divided into one or more module,
One or more module is stored in memory 11, and by one or more processors (the present embodiment is processor 12) institute
It executes to complete the present invention, the so-called module of the present invention is the series of computation machine program instruction for referring to complete specific function
Section, for describing implementation procedure of the value of the product estimation program in value of the product estimation device.
It is the value of the product estimation program in one embodiment of product of the present invention value estimate device for example, referring to shown in Fig. 3
Program module schematic diagram, in the embodiment, value of the product estimation program can be divided into weight assignment module 10, expected receive
Beneficial estimation block 20, operation income calculation module 30, value assessment module 40, illustratively:
Weight assignment module 10 is used for: each stage according to existing product in life cycle makes profits, to described each
The value in stage carries out weight assignment.
Optionally, the weight assignment module 10 is used in detail:
One or more kinds of existing products are selected, the historical data of selected product is obtained；
The historical data is pre-processed；
The pretreated data are imported into preset table, wherein the behavior property value in table, the column in table
For each stage of life cycle；
According to the stage included by the life cycle, the sample average in each stage is sought respectively；
The matrix of different dimensions is set according to sample average for the different phase of life cycle；
The characteristic value of the matrix in life cycle each stage is calculated separately, vector is constituted；
With factorial analysis flexible strategy algorithm, factor loading battle array is sought, on the basis of factor loading battle array, finds common factor
Number；
By factorial analysis flexible strategy model, the contribution rate of each factor in each stage factor load battle array of step by step calculation, setting
Contribution rate threshold value comes out the factor screening that the sum of contribution rate is greater than threshold value, composing indexes factor set；
Weigh algorithm using the tax in factorial analysis flexible strategy model, according to the index factor collection, to each stage into
Row assigns power.
Prospective earnings estimation block 20 is used for: the historical yield data of the preset time period of the existing product are obtained, and
According to the weight in each stage, the prospective earnings in existing product future are estimated.
Optionally, the prospective earnings estimation block 20 estimates following expected receipts of the existing product using following functions
Benefit:
Prospective earnings=α (First Year capital × earning rate × time limit/365)+β (second year capital × expected yield ×
Time limit/365)+γ (third year capital × expected yield × time limit/365),
Wherein, described α, β, γ are the weight in the life cycle each stage, and alpha+beta+γ=1, the second year sheet
Gold=First Year capital+income, third year capital=second year capital+income.
Operation income calculation module 30 is used for: the existing product being carried out category division, according to the existing product
Prospective earnings estimate the operation income of each category product.
Optionally, the operation income calculation module 30 is used in detail:
Obtain the customer data of existing product；
One or more kinds of classifying methods are selected, the classification of the existing product is calculated using the customer data；
According to the classification calculated, class label is marked to each client of the existing product；
According to the prospective earnings of the client of mark class label, received using the operation that following formula calculates category product
Benefit:
Wherein, YiFor the i-th class product, N is the customer quantity for having bought such product, it is contemplated that income is to buy such product
Client prospective earnings.
Value assessment module 40 is used for: when opening new product, according to the feature of the product, by the product assortment in above-mentioned
Classification value assessment is carried out to the new product and according to the operation income of category product.
Optionally, the value assessment module 40 is used in detail:
Signature analysis is carried out to the new product, and according to the feature, by the product assortment in above-mentioned classification；
According to the estimated customer quantity of the operation income of category product and the product, the expection of the budget new product
Income, and using this as the value of the new product, calculation formula are as follows:
Vi=Yi×M
Wherein, ViFor incorporate into i classification new product estimated value, YiFor the operation income of category product, M is should
The expection customer quantity of new product.
Above-mentioned weight assignment module 10, prospective earnings estimation block 20, operation income calculation module 30, value assessment module
The program modules such as 40 are performed realized functions or operations step and are substantially the same with above-described embodiment, and details are not described herein.
In addition, the embodiment of the present invention also proposes a kind of computer readable storage medium, the computer readable storage medium
On be stored with value of the product estimation program, the value of the product estimation program can be executed by one or more processors, with realize
Following operation:
Each stage according to existing product in life cycle makes profits, and carries out weight tax to the value in each stage
Value；
Obtain the historical yield data of the preset time period of the existing product, and according to the weight in each stage,
Estimate the prospective earnings in existing product future；
The existing product is subjected to category division, according to the prospective earnings of the existing product, each classification is estimated and produces
The operation income of product；And
When opening new product, according to the feature of the product, by the product assortment in above-mentioned classification, and according to the category
The operation income of product carries out value assessment to the new product.
Computer readable storage medium specific embodiment of the present invention and each reality of the said goods value estimate device and method
It is essentially identical to apply example, does not make tired state herein.
It should be noted that the serial number of the above embodiments of the invention is only for description, do not represent the advantages or disadvantages of the embodiments.And
The terms "include", "comprise" herein or any other variant thereof is intended to cover non-exclusive inclusion, so that packet
Process, device, article or the method for including a series of elements not only include those elements, but also including being not explicitly listed
Other element, or further include for this process, device, article or the intrinsic element of method.Do not limiting more
In the case where, the element that is limited by sentence "including a ...", it is not excluded that including process, device, the article of the element
Or there is also other identical elements in method.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior art
The part contributed out can be embodied in the form of software products, which is stored in one as described above
In storage medium (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that terminal device (it can be mobile phone,
Computer, server or network equipment etc.) execute method described in each embodiment of the present invention.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of value of the product evaluation method, which is characterized in that the described method includes:
S1, each stage according to existing product in life cycle make profits, and carry out weight tax to the value in each stage
Value；
The historical yield data of the preset time period of S2, the acquisition existing product, and according to the weight in each stage, estimate
Calculate the prospective earnings in existing product future；
S3, existing product progress category division is estimated into each category product according to the prospective earnings of the existing product
Operation income；And
S4, when opening new product, according to the feature of the product, by the product assortment in above-mentioned classification, and according to the category
The operation income of product carries out value assessment to the new product.
2. value of the product evaluation method as described in claim 1, which is characterized in that the S1 includes:
One or more kinds of existing products are selected, the historical data of selected product is obtained；
The historical data is pre-processed；
The pretreated data are imported into preset table, wherein the behavior property value in table is classified as life in table
Order each stage in period；
According to the stage included by the life cycle, the sample average in each stage is sought respectively；
The matrix of different dimensions is set according to sample average for the different phase of life cycle；
The characteristic value of the matrix in life cycle each stage is calculated separately, vector is constituted；
With factorial analysis flexible strategy algorithm, factor loading battle array is sought, on the basis of factor loading battle array, finds common factor number；
By factorial analysis flexible strategy model, the contribution rate of each factor in each stage factor load battle array of step by step calculation, setting contribution
Rate threshold value comes out the factor screening that the sum of contribution rate is greater than threshold value, composing indexes factor set；
Each stage is assigned according to the index factor collection using the tax power algorithm in factorial analysis flexible strategy model
Power.
3. value of the product evaluation method as described in claim 1, which is characterized in that this method uses described in the estimation of following functions
The prospective earnings in existing product future:
Prospective earnings=α (First Year capital × earning rate × time limit/365)+β (second year capital × expected yield × time limit/
365)+γ (third year capital × expected yield × time limit/365),
Wherein, described α, β, γ are the weight in the life cycle each stage, and alpha+beta+γ=1, the second year capital=
First Year capital+income, third year capital=second year capital+income.
4. the value of the product evaluation method as described in any one of claims 1 to 3, which is characterized in that the S3 includes:
Obtain the customer data of existing product；
One or more kinds of classifying methods are selected, the classification of the existing product is calculated using the customer data；
According to the classification calculated, class label is marked to each client of the existing product；
According to the prospective earnings of the client of mark class label, the operation income of category product is calculated using following formula:
Wherein, YiFor the i-th class product, N is the customer quantity for having bought such product, it is contemplated that income is to buy the visitor of such product
The prospective earnings at family.
5. value of the product evaluation method as claimed in claim 4, which is characterized in that the S4 includes:
Signature analysis is carried out to the new product, and according to the feature, by the product assortment in above-mentioned classification；
According to the estimated customer quantity of the operation income of category product and the product, the prospective earnings of the budget new product,
And using this as the value of the new product, calculation formula are as follows:
Vi=Yi×M
Wherein, ViFor incorporate into i classification new product estimated value, YiFor the operation income of category product, M is the new production
The expection customer quantity of product.
6. a kind of value of the product estimates device, which is characterized in that described device includes memory and processor, on the memory
It is stored with the value of the product estimation program that can be run on the processor, the value of the product estimation program is by the processor
Following steps are realized when execution:
S1, each stage according to existing product in life cycle make profits, and carry out weight tax to the value in each stage
Value；
The historical yield data of the preset time period of S2, the acquisition existing product, and according to the weight in each stage, estimate
Calculate the prospective earnings in existing product future；
S3, existing product progress category division is estimated into each category product according to the prospective earnings of the existing product
Operation income；And
S4, when opening new product, according to the feature of the product, by the product assortment in above-mentioned classification, and according to the category
The operation income of product carries out value assessment to the new product.
7. value of the product as claimed in claim 6 estimates device, which is characterized in that the S1 includes:
One or more kinds of existing products are selected, the historical data of selected product is obtained；
The historical data is pre-processed；
The pretreated data are imported into preset table, wherein the behavior property value in table is classified as life in table
Order each stage in period；
According to the stage included by the life cycle, the sample average in each stage is sought respectively；
The matrix of different dimensions is set according to sample average for the different phase of life cycle；
The characteristic value of the matrix in life cycle each stage is calculated separately, vector is constituted；
With factorial analysis flexible strategy algorithm, factor loading battle array is sought, on the basis of factor loading battle array, finds common factor number；
By factorial analysis flexible strategy model, the contribution rate of each factor in each stage factor load battle array of step by step calculation, setting contribution
Rate threshold value comes out the factor screening that the sum of contribution rate is greater than threshold value, composing indexes factor set；
Each stage is assigned according to the index factor collection using the tax power algorithm in factorial analysis flexible strategy model
Power.
8. value of the product as claimed in claim 6 estimates device, which is characterized in that the estimation existing product future
Prospective earnings use such as minor function:
Prospective earnings=α (First Year capital × earning rate × time limit/365)+β (second year capital × expected yield × time limit/
365)+γ (third year capital × expected yield × time limit/365),
Wherein, described α, β, γ are the weight in the life cycle each stage, and alpha+beta+γ=1, the second year capital=
First Year capital+income, third year capital=second year capital+income.
9. value of the product as described in any one of claim 6 to 8 estimates device, which is characterized in that the S3 includes:
Obtain the customer data of existing product；
One or more kinds of classifying methods are selected, the classification of the existing product is calculated using the customer data；
According to the classification calculated, class label is marked to each client of the existing product；
According to the prospective earnings of the client of mark class label, the operation income of category product is calculated using following formula:
Wherein, YiFor the i-th class product, N is the customer quantity for having bought such product, it is contemplated that income is to buy the visitor of such product
The prospective earnings at family.
10. a kind of computer readable storage medium, which is characterized in that be stored with product valence on the computer readable storage medium
Be worth estimation program, the value of the product estimation program can execute by one or more processor, with realize as claim 1 to
Described in any one of 5 the step of value of the product evaluation method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910422084.0A CN110276634A (en) | 2019-05-21 | 2019-05-21 | Value of the product evaluation method, device and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910422084.0A CN110276634A (en) | 2019-05-21 | 2019-05-21 | Value of the product evaluation method, device and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110276634A true CN110276634A (en) | 2019-09-24 |
Family
ID=67960133
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910422084.0A Pending CN110276634A (en) | 2019-05-21 | 2019-05-21 | Value of the product evaluation method, device and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110276634A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113112138A (en) * | 2021-04-01 | 2021-07-13 | 中国民航大学 | Construction method of comprehensive aviation patent evaluation system |
-
2019
- 2019-05-21 CN CN201910422084.0A patent/CN110276634A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113112138A (en) * | 2021-04-01 | 2021-07-13 | 中国民航大学 | Construction method of comprehensive aviation patent evaluation system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Doumpos et al. | Operational research and artificial intelligence methods in banking | |
| Kotu et al. | Predictive analytics and data mining: concepts and practice with rapidminer | |
| Zhang et al. | A causal feature selection algorithm for stock prediction modeling | |
| Tsai | Combining cluster analysis with classifier ensembles to predict financial distress | |
| Sahin et al. | Detecting credit card fraud by ANN and logistic regression | |
| De Andrés et al. | Bankruptcy forecasting: A hybrid approach using Fuzzy c-means clustering and Multivariate Adaptive Regression Splines (MARS) | |
| Livieris et al. | An advanced deep learning model for short-term forecasting US natural gas price and movement | |
| Kasemsap | Multifaceted applications of data mining, business intelligence, and knowledge management | |
| CN109858762A (en) | A kind of business risk prediction technique and device | |
| CN109670724A (en) | Methods of risk assessment and device | |
| CN107481143A (en) | A kind of intelligent stock commending system and implementation method | |
| Djurisic et al. | Bank CRM optimization using predictive classification based on the support vector machine method | |
| Lee et al. | Progressive performance modeling for the strategic determinants of market value in the high-tech oriented SMEs | |
| Baralis et al. | Discovering profitable stocks for intraday trading | |
| Mazraeh et al. | Stock portfolio optimization using a combined approach of multi objective grey wolf optimizer and machine learning preselection methods | |
| Pai et al. | Using internet search trends and historical trading data for predicting stock markets by the least squares support vector regression model | |
| CN115545886A (en) | Overdue risk identification method, overdue risk identification device, overdue risk identification equipment and storage medium | |
| Makinde et al. | An Improved Customer Relationship Management Model for Business-to-Business E-commerce Using Genetic-Based Data Mining Process | |
| Jinbo et al. | The application ofadaboost in customer churn prediction | |
| Busch et al. | Deep Learning for Commodity Procurement: Nonlinear Data-Driven Optimization of Hedging Decisions | |
| CN110276634A (en) | Value of the product evaluation method, device and computer readable storage medium | |
| Wang et al. | Digital economy meets artificial intelligence: forecasting economic conditions based on big data analytics | |
| CN116029760A (en) | Message pushing method, device, computer equipment and storage medium | |
| Dong | Potential Customer Prediction of Telecom Marketing based on Machine Learning | |
| Culbert et al. | Customer churn prediction in superannuation: a sequential pattern mining approach |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190924 |