CN109711859A - Prediction technique and device, storage medium, the computer equipment of mixed railway - Google Patents
Prediction technique and device, storage medium, the computer equipment of mixed railway Download PDFInfo
- Publication number
- CN109711859A CN109711859A CN201811340698.6A CN201811340698A CN109711859A CN 109711859 A CN109711859 A CN 109711859A CN 201811340698 A CN201811340698 A CN 201811340698A CN 109711859 A CN109711859 A CN 109711859A
- Authority
- CN
- China
- Prior art keywords
- client
- value
- future
- life cycle
- historical trading
- 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
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
This application discloses a kind of prediction technique of mixed railway and device, storage medium, computer equipment, prediction technique includes: the historical trading data and basic attribute data for obtaining client；According to historical trading data, the current value CCV of client is calculated；According to historical trading data and basic attribute data, the future of life cycle T of client is predicted；According to future of life cycle T, historical trading data and the basic attribute data of client, the future value CFV of client is determined；According to the current value CCV of the client and future value CFV of client, the lifelong value CLV of client is determined.Historical trading data and basic attribute data of the application according to client, by analyzing customer current value CCV and future value CFV, so that it is determined that the specific value of the future value CLV of client, compared with the prior art is by the mode of artificial qualitative analysis, the accuracy for calculating mixed railway CLV is improved, calculating speed is also accelerated.
Description
Technical field
This application involves customer value electric powder predictions, particularly with regard to a kind of prediction technique of mixed railway
And device, storage medium, computer equipment.
Background technique
Have such common recognition in trade marketing field: 80% income from 20% client, and by product or service
The cost for being sold to existing customer is 10 times lower than finding a new user.Therefore, in order to maximize company interest, it is necessary to
Solve existing customer mixed railway (Customer Lifetime Value) (from become corporate client that moment,
The income summation that can be generated in this period is lost to subsidiary company), to maximumlly obtain enough incomes from existing customer.
In current marketing domain, often according to sales force in past business and the following industry predicted based on common sense
Business situation, by client segmentation or layering, such as bronze clients and gold client etc..But this method subjectivity is too strong, together
When excessively rely on the protracted experience of business expert and judge, and for the value of client can only qualitative analysis, lack quantitative
Analysis mode.Traditional prediction technique, it is all to be improved no matter in efficiency or in accuracy rate.
Summary of the invention
In view of this, this application provides a kind of prediction technique of mixed railway and device, storage medium, computers
Equipment is analyzed the future value of client, is quantified to realize to mixed railway by calculating the current value of client
Prediction.
According to the one aspect of the application, a kind of prediction technique of mixed railway is provided, which is characterized in that packet
It includes:
Obtain the historical trading data and basic attribute data of client；
According to the historical trading data, the current value CCV of the client is calculated；
According to the historical trading data and the basic attribute data, the future of life cycle T of the client is predicted；
According to the future of life cycle T of the client, the historical trading data and the basic attribute data, determine
The future value CFV of the client；
According to the current value CCV of the client and future value CFV of the client, the lifelong valence of the client is determined
Value CLV.
According to the another aspect of the application, a kind of prediction meanss of mixed railway are provided, which is characterized in that packet
It includes:
Acquiring unit, for obtaining the historical trading data and basic attribute data of the client；
Current value computing unit, for calculating the current value CCV of the client according to the historical trading data；
Future of life period computing unit is used for according to the historical trading data and the basic attribute data, in advance
Survey the future of life cycle T of the client；
Future value computing unit, for according to the client future of life cycle T and the basic attribute data,
Determine the future value CFV of the client；
Lifelong value calculation unit is summed for the current value CCV and future value CFV according to the client,
Determine the lifelong value CLV of the client.
According to the application another aspect, a kind of storage medium is provided, computer program, described program are stored thereon with
The prediction technique of above-mentioned mixed railway is realized when being executed by processor.
According to the application another aspect, a kind of computer equipment is provided, including storage medium, processor and be stored in
On storage medium and the computer program that can run on a processor, the processor realize above-mentioned client when executing described program
The prediction technique being worth throughout one's life.
By above-mentioned technical proposal, a kind of prediction technique of mixed railway, device and equipment provided by the present application are led to
The technical solution using the application is crossed, according to the historical trading data and basic attribute data of client, calculates client's first
Current value CCV, then carries out prediction to the future of life cycle T of client to analyze the future value CFV of client, final
The lifelong value CLV of client out.With in the prior art, qualitative analysis can only be carried out by potential value of the artificial experience to client
It compares, this application provides a kind of scientific and effective methods that can quantitatively calculate mixed railway CLV, improve client's end
The accuracy of raw value CLV, also accelerates calculating speed.
Above description is only the general introduction of technical scheme, in order to better understand the technological means of the application,
And it can be implemented in accordance with the contents of the specification, and in order to allow above and other objects, features and advantages of the application can
It is clearer and more comprehensible, below the special specific embodiment for lifting the application.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present application, constitutes part of this application, this Shen
Illustrative embodiments and their description please are not constituted an undue limitation on the present application for explaining the application.In the accompanying drawings:
Fig. 1 shows a kind of flow diagram of the prediction technique of mixed railway provided by the embodiments of the present application；
Fig. 2 shows the flow diagrams of the prediction technique of another mixed railway provided by the embodiments of the present application；
Fig. 3 shows a kind of structural schematic diagram of the prediction meanss of mixed railway provided by the embodiments of the present application；
Fig. 4 shows the structural schematic diagram of the prediction meanss of another mixed railway provided by the embodiments of the present application.
Specific embodiment
The application is described in detail below with reference to attached drawing and in conjunction with the embodiments.It should be noted that not conflicting
In the case of, the features in the embodiments and the embodiments of the present application can be combined with each other.
A kind of prediction technique of mixed railway is provided in the present embodiment, as shown in Figure 1, this method comprises:
Step 101, the historical trading data and basic attribute data of client are obtained.
It wherein, may include the friendship of the exchange hour of each transaction of client, each transaction in historical trading data
The easy amount of money and the products transactions type of each transaction, and in basic attribute data may include the age of client, gender, residence
Residence, income situation etc..
For example, the basic attribute data of client's first is 30 years old age, gender male, residence are 20,000 yuan of Beijing, monthly income,
5 Transaction Informations of history of client's first are had recorded in historical trading data, the financing of respectively in August, 2015,30,000 yuan of purchase produces
Product A, in March, 2016, the finance product B of 20,000 yuan of purchase, in October, 2016, the finance product C of 30,000 yuan of purchase, in January, 2017,
It buys 10,000 yuan of finance product D and in September, 2017 buys 50,000 yuan of finance product E.
Step 102, according to historical trading data, the current value CCV of client is calculated.
According to the historical trading data of client, it can determine that client has been enterprise bring customer current value CCV
(Customer Current Value, CCV), by taking the historical trading data of above-mentioned client's first as an example, can calculate separately client
Each transaction transaction amount be enterprise's bring profit and client's first be enterprise save cost and client's first be enterprise
Industry bring additional profit (such as client's first is after having purchased finance product A, and it is very satisfied to finance product A, it introduces oneself
Friend's second also buys this product, then client's second purchase product A is that enterprise's bring profit can also be calculated in client's first
In current value, or client's second is bought into product A and is calculated according to certain percentage in client's first for enterprise's bring profit
In current value), by summation or the other modes such as weighted sum, calculate the current value CCV of client's first.
Step 103, according to historical trading data and basic attribute data, the future of life cycle T of client is predicted.
According to data such as the basic attribute data of client, historical trading time and transaction amount, to the non-next life of client
Life cycle T is predicted, such as the basic attribute data of client third is shown, it is average that the income of client third belongs to the third residence of client
Income level hereinafter, and the historical trading data of client third show that the historical trading amount of money of client third successively decreases year by year, nearest two
The transaction amount in year can predict that the future of life cycle T of client is less than 1 year or even shorter already below 500 yuan.
Step 104, according to future of life cycle T, historical trading data and the basic attribute data of client, client is determined
Future value CFV.
It can analyze the standard price of sample client identical with client's essential attribute according to the basic attribute data of client
Value (standard value can be obtained by the Transaction Information conclusion of the historic customer largely with same or similar essential attribute), in conjunction with visitor
In the future of life period at family, can analyze out the life cycle phase that such as client is presently in (may particularly include the acquisition phase, mentions
The phase of liter, maturity period, decline phase and the phase of leaving), thus the Life Cycle current according to the standard value of sample client and client
The future value CFV (Customer Future Value, CFV) of phase phase analysis client, or further combined with client itself
Historical trading situation analyze the difference situation of the client Yu sample client on the basis of the standard value of sample client, then count
Calculate the future value of the client.
Step 105, according to the future value CFV of the current value CCV of client and client, the lifelong value of client is determined
CLV。
Using customer current value CCV calculated in above-mentioned steps, and the client future value CFV of prediction, to visitor
The lifelong value CLV at family is analyzed, and carries out quantum chemical method to the lifelong value CLV of client.
Technical solution by applying this embodiment, it is first according to the historical trading data and basic attribute data of client
The current value CCV of client is first calculated, prediction then is carried out to analyze the following valence of client to the future of life cycle T of client
Value CFV finally obtains the lifelong value CLV of client.With in the prior art, artificial experience can only be relied on to the potential value of client
Qualitative analysis is carried out to compare, this application provides a kind of scientific and effective method that can quantitatively calculate mixed railway CLV,
The accuracy for improving mixed railway CLV, also accelerates calculating speed.
Further, as the refinement and extension of above-described embodiment specific embodiment, in order to completely illustrate the present embodiment
Specific implementation process, provide the prediction technique of another mixed railway, as shown in Fig. 2, this method comprises:
Step 201, the historical trading data and basic attribute data of client are obtained.
Obtain the product category data of each transaction of client, exchange hour data, transaction value data and client
Gender data, income receipt, age data, residence data.
Step 202, according to the historical trading data of client, determine that client originates from life initial time, and from life
Time starts to each year in observation time transaction amount.
In the historical trading data of client, the exchange hour of the first transaction of client is found out, by the first transaction
Exchange hour is determined as the life initial time of client, calculates separately since life initial time, until in observation time
Each year transaction amount.
For example, in the citing of above-mentioned client's first, the first stroke exchange hour of client's first is in May, 2015, when observation
Between be in December, 2017, then the life initial time of client's first is 2015, and transaction amount in 2015 is 30,000 yuan, 2016
Transaction amount be 20,000 yuan+3 ten thousand yuan=50,000 yuan, transaction amount in 2017 is 10,000 yuan+5 ten thousand yuan=60,000 yuan.
Step 203, according to each year transaction amount of client, determine that each year profit of client is worth, and client is every
Current value CCV of the profit value summation in 1 year as client.
According to each year transaction amount of client and each year enterprise's business condition, the transaction in each year of client is analyzed
The amount of money is each year profit of enterprise's bring profit namely client value, is summed so that each year profit of client is worth,
Determining client altogether is enterprise's bring profit value, is the current value CCV of client.
For example, client's first transaction amount in 2015 is 30,000 yuan, 2015 annual interest of enterprise in the citing of above-mentioned client's first
2000 yuan of profits are created with the funds, client's first transaction amount in 2016 is 50,000 yuan, and enterprise utilizes this reward for writing or painting in 2016
Gold creates 5000 yuan of profits, and client's first transaction amount in 2017 is 60,000 yuan, and enterprise is created for 2017 using the funds
6000 yuan of profits, then the gross profit that client generates from life initial time to observation time is 2000+5000+6000=
13000 yuan.
Step 204, according to the basic attribute data of client, the generic of client is determined.
The essential attribute of client is matched with the attribute of historical sample client, thus according to belonging to historical sample client
Classification, determine the classification of the client, in case the subsequent category client according to corresponding to the classification of client specificity analysis should
The characteristic of client.
For example, the attributes match of the essential attribute of client's first and historical sample client X, also, the class of historical sample client X
Wei not be a kind of, then it is a kind of client by the category division of client's first.
Step 205, it according to the classification of client and default client classification-life cycle mapping table, matches and client's classification
Corresponding life cycle.
According to the generic of client, and previously according to default client's classification-life that historical sample customer data determines
Periodic Maps table is ordered, determines the corresponding life cycle of category client, in case subsequent determining client's future of life period.
For example, client's first is a kind of client, according to default client's classification-life cycle mapping table, a kind of client is corresponding
Life cycle is 8 years, then, the life cycle of client's first is determined as 8 years.
Step 206, the remaining time of client is determined according to historical trading data.
After the life initial time for determining client using the first stroke exchange hour in historical trading data, by observation time
It is made the difference with the life initial time of client, determines the remaining time of client.
For example, the life initial time of client's first is 2015, observation time is 2017, then can determine staying for client
Depositing the time is 2 years.
Step 207, the remaining time of client is determined according to historical trading data.
The future of life cycle T of client, that is, visitor are determined by the life cycle of client and the remaining time of client
To customer churn time span experienced since observation time, future of life cycle T is the meter of client's future value CFV at family
Calculation provides foundation.
For example, the life cycle of client's first is 8 years, remaining time is had been determined as 2 years, then the future of life week of client's first
Phase is then 8-2=6.
In addition, client's future of life cycle T is sought, it can also be by utilizing the historical sample with complete lifecycle data
Client characteristic training COX prediction model, thus by COX prediction model life cycle is predicted in the way of come reality
It is existing, it is not specifically limited herein.
Step 208, according to client's classification, match customer value-time fluctuation rate function r (t) corresponding with classification.
For different classes of customer group, client's trend that customer value changes under different life is also different
, that is to say, that customer value-time fluctuation rate function r (t) of different classes of customer group is also different.With above-mentioned
According to the classification of client, matching life cycle corresponding with client's classification is similar, the other customer value-stability bandwidth of each customer class
Curvilinear function can be concluded by the relevant historical data of the historical sample client of the category, thus according to the affiliated class of client
Not, corresponding customer value-time fluctuation rate function r (t) is matched, it can be in the hope of client's valence of different time according to the function
Value, provides data basis to acquire client's future value CFV.
For example, client's first is a kind of client, then one kind customer value-time fluctuation rate function r1 (t) is matched for client's first.
Step 209, according to client's future value calculation formula, the future value CFV of client is calculated.
In the above-described embodiments, specifically, if the future of life cycle T of client is greater than or equal to default life cycle,
Client's future value calculation formula are as follows:
Wherein, CV is the value by the end of client in observation time, 1 year, and d (t) is cash discount rate.
The future value CFV of client can be used above-mentioned formula and calculate, wherein CV is the client until observation time
The profit value created in 1 year for enterprise, for example, calculating the future value of client's first, it is assumed that observation time is in May, 2018,
Then client's first by the end of in observation time 1 year be enterprise create profit value answer are as follows: in June, 2017 in May, 2018 this
In year, client's first is the gross profit value that enterprise creates.
In addition, if the future of life cycle T of client is longer (being greater than or equal to default life cycle), then calculating client
During future value, would have to consider that inflation rate, discount rate should be the variable changed with time.
In the above-described embodiments, specifically, if the future of life cycle T of client is less than default life cycle, client is not
Carry out value calculation formula are as follows:
Wherein, CV is the value by the end of client in observation time, 1 year, and d is cash discount rate.
And if the future of life period of client has not been grown, then for convenience calculate, can be by customer value-Time Wave
Dynamic rate function r (t) carries out discretization as unit of year, and discount rate is fixed as a quantitative d, to utilize above-mentioned formula pair
The future value CFV of client is calculated.
It should be noted that different values can be arranged according to the difference of enterprise marketing product in default life cycle, example
Such as, if the product of enterprise marketing is usually period longer finance product (scheduling to last for such as 5 years), then can be by default life cycle
Be set as 5 years, 8 years it is even longer, and if enterprise marketing is usually short-term finance product (scheduling to last for such as 1 year), then can will
Default life cycle is set as 1 year, 2 years etc..
In addition, it should be noted that, during calculating customer current value CCV, in addition to above-mentioned each year can be pressed
Profit value it is outer to calculate, can also be counted according to the characteristic of different product according to the profit value of even every day every month
Calculate, likewise, calculating client's future of life cycle T and during client future value CFV, equally can with the moon or
Day is unit.
Step 210, the future value CFV of the current value CCV of client and client are summed, obtains the lifelong value of client
CLV。
Finally, obtaining the lifelong valence of client by way of by customer current value CCV and client's future value CFV summation
Value CLV.And then the grade of client can be determined with specific reference to the lifelong value CLV of client, it is client according to the grade of client
It is premium customers as the lifelong value CLV of client is more than 100,000 yuan with corresponding attendant, matches premium customers for client
It handles and services the satisfaction to guarantee premium customers for it, and according to the future value CFV of client, formulate corresponding clothes for client
Business scheme, the future value CFV such as client is lower, at this point, be not suitable for again to lead referral wholesale finance product, then it can be to client
Recommend the faster finance product of some short-term yields, utmostly to harvest the value of client.
Technical solution by applying this embodiment matches life cycle and the visitor of client according to the essential attribute of client
Family value-time fluctuation rate function, so that client's future of life cycle T is analyzed according to customer life cycle, according to customer value-
Time fluctuation rate function seeks client future value CFV, is combined the calculated customer current value of historical trading data institute
CFV acquires the lifelong value CLV of client by way of by client's future value CFV and customer current value CFV summation, gives
The specific value of client's future value CFV and mixed railway CLV out realizes whole to client's future value CFV and client
The quantitative forecast of raw value CLV, has provided to targetedly match different service plans for enterprise for different clients
The Mathematics Proof and theoretical basis of power.
Further, the specific implementation as Fig. 1 method, the embodiment of the present application provide a kind of the pre- of mixed railway
Device is surveyed, as shown in figure 3, the device includes: acquiring unit 31, current value computing unit 32, future of life period calculating list
First 33, future value computing unit 34, lifelong value calculation unit 35.
Acquiring unit 31, for obtaining the historical trading data and basic attribute data of client；
Current value computing unit 32, for calculating the current value CCV of client according to historical trading data；
Future of life period computing unit 33, for predicting client according to historical trading data and basic attribute data
Future of life cycle T；
Future value computing unit 34 determines visitor for the future of life cycle T and basic attribute data according to client
The future value CFV at family；
Lifelong value calculation unit 35 determines visitor for current value CCV and future value the CFV summation according to client
The lifelong value CLV at family.
In specific application scenarios, to provide a kind of concrete mode for calculating customer current value CCV, as shown in figure 4,
Current value computing unit 32, specifically includes: transaction amount computing unit 321, current value computation subunit 322；
Transaction amount computing unit 321, for the historical trading data according to client, when determining that client originates from life
Between, and the transaction amount since life initial time to each year in observation time；
Current value computation subunit 322, for determining each year benefit of client according to each year transaction amount of client
Profit value, and the current value CCV by the value summation of each year profit of client as client.
In specific application scenarios, before calculating client's future of life cycle T, the complete life for calculating client is also needed
The time span that period and client have survived, therefore, as shown in figure 4, future of life period computing unit 33, specific to wrap
It includes: client's classification determination unit 331, life cycle matching unit 332, remaining time computing unit 333, future of life period meter
Operator unit 334；
Client's classification determination unit 331 determines the generic of client for the basic attribute data according to client；
Life cycle matching unit 332, for being mapped according to classification and default client classification-life cycle of client
Table matches life cycle corresponding with client's classification；
Remaining time computing unit 333, for determining the remaining time of client according to historical trading data；
Future of life period computation subunit 334 obtains client for the life cycle of client and remaining time to be asked poor
Future of life cycle T.
In specific application scenarios, client's future value CFV of different clients classification has different characteristics, in order to count
The future value CFV for calculating client, needs first to determine the customer value characteristic of category client, and then seek client's future value
CFV, as shown in figure 4, future value computing unit 34, specifically includes: customer value function determination unit 341, future value meter
Operator unit 342；
Customer value function determination unit 341 matches customer value-corresponding with classification for client's classification of basis
Time fluctuation rate function r (t)；
Future value computation subunit 342, for calculating the future value of client according to client's future value calculation formula
CFV。
In the above-described embodiments, specifically, the specific embodiment calculated as the first client's future value CFV, not
Carry out value calculation subelement 342, if the future of life cycle T specifically for client is greater than or equal to default life cycle, visitor
Family future value calculation formula are as follows:
Wherein, CV is the value by the end of client in observation time, 1 year, and d (t) is cash discount rate.
In the above-described embodiments, specifically, the specific embodiment calculated as second of client's future value CFV, not
Carry out value calculation subelement 342, if the future of life cycle T for being specifically also used to client is less than default life cycle, client is not
Carry out value calculation formula are as follows:
Wherein, CV is the value by the end of client in observation time, 1 year, and d is cash discount rate.
In specific application scenarios, to provide the calculation of specific mixed railway CLV a kind of.
Future value computing unit 34, specifically for seeking the future value CFV of the current value CCV of client and client
With obtain the lifelong value CLV for stating client.
It should be noted that each function involved by a kind of prediction meanss of mixed railway provided by the embodiments of the present application
Other corresponding descriptions of unit, can be with reference to the corresponding description in Fig. 1 and Fig. 2, and details are not described herein.
Based on above-mentioned method as depicted in figs. 1 and 2, correspondingly, the embodiment of the present application also provides a kind of storage medium,
On be stored with computer program, which realizes above-mentioned mixed railway as depicted in figs. 1 and 2 when being executed by processor
Prediction technique.
Based on this understanding, the technical solution of the application can be embodied in the form of software products, which produces
Product can store in a non-volatile memory medium (can be CD-ROM, USB flash disk, mobile hard disk etc.), including some instructions
With so that computer equipment (can be personal computer, server or the network equipment an etc.) execution the application is each
Method described in implement scene.
Based on above-mentioned method as shown in Figure 1 and Figure 2 and Fig. 3, virtual bench embodiment shown in Fig. 4, in order to realize
Above-mentioned purpose, the embodiment of the present application also provides a kind of computer equipments, are specifically as follows personal computer, server, network
Equipment etc., the computer equipment include storage medium and processor；Storage medium, for storing computer program；Processor is used
The prediction technique of above-mentioned mixed railway as depicted in figs. 1 and 2 is realized in execution computer program.
Optionally, which can also include user interface, network interface, camera, radio frequency (Radio
Frequency, RF) circuit, sensor, voicefrequency circuit, WI-FI module etc..User interface may include display screen
(Display), input unit such as keyboard (Keyboard) etc., optional user interface can also connect including USB interface, card reader
Mouthful etc..Network interface optionally may include standard wireline interface and wireless interface (such as blue tooth interface, WI-FI interface).
It will be understood by those skilled in the art that a kind of computer equipment structure provided in this embodiment is not constituted to the reality
The restriction of body equipment may include more or fewer components, perhaps combine certain components or different component layouts.
It can also include operating system, network communication module in storage medium.Operating system is management and preservation computer
The program of device hardware and software resource supports the operation of message handling program and other softwares and/or program.Network communication
Module for realizing the communication between each component in storage medium inside, and with other hardware and softwares in the computer equipment it
Between communicate.
Through the above description of the embodiments, those skilled in the art can be understood that the application can borrow
It helps software that the mode of necessary general hardware platform is added to realize, the technology using the application can also be passed through by hardware realization
Scheme is then right according to the historical trading data and basic attribute data of client, first the current value CCV of calculating client
The future of life cycle T of client carries out prediction to analyze the future value CFV of client, finally obtains the lifelong value of client
CLV.With in the prior art, qualitative analysis can only be carried out by potential value of the artificial experience to client and compared, the application provides
A kind of scientific and effective method that can quantitatively calculate mixed railway CLV, improves the accurate of mixed railway CLV
Property, also accelerate calculating speed.
It will be appreciated by those skilled in the art that the accompanying drawings are only schematic diagrams of a preferred implementation scenario, module in attached drawing or
Process is not necessarily implemented necessary to the application.It will be appreciated by those skilled in the art that the mould in device in implement scene
Block can according to implement scene describe be distributed in the device of implement scene, can also carry out corresponding change be located at be different from
In one or more devices of this implement scene.The module of above-mentioned implement scene can be merged into a module, can also be into one
Step splits into multiple submodule.
Above-mentioned the application serial number is for illustration only, does not represent the superiority and inferiority of implement scene.Disclosed above is only the application
Several specific implementation scenes, still, the application is not limited to this, and the changes that any person skilled in the art can think of is all
The protection scope of the application should be fallen into.
Claims (10)
1. a kind of prediction technique of mixed railway characterized by comprising
Obtain the historical trading data and basic attribute data of client；
According to the historical trading data, the current value CCV of the client is calculated；
According to the historical trading data and the basic attribute data, the future of life cycle T of the client is predicted；
According to the future of life cycle T of the client, the historical trading data and the basic attribute data, determine described in
The future value CFV of client；
According to the current value CCV of the client and future value CFV of the client, the lifelong value of the client is determined
CLV。
2. calculating the visitor the method according to claim 1, wherein described according to the historical trading data
The current value CCV at family, specifically includes:
According to the historical trading data of the client, determine that the client originates from life initial time, and from the life
Time starts to each year in observation time transaction amount；
According to each year transaction amount of the client, determine that each year profit of the client is worth, and the client is every
Current value CCV of the profit value summation in 1 year as the client.
3. the method according to claim 1, wherein described according to the historical trading data and described basic
Attribute data is predicted the future of life cycle T of the client, is specifically included:
According to the basic attribute data of the client, the generic of the client is determined；
According to the classification of the client and default client classification-life cycle mapping table, match corresponding with client's classification
Life cycle；
The remaining time of the client is determined according to the historical trading data；
The life cycle of the client and the remaining time are asked poor, obtain the future of life cycle T of the client.
4. according to the method described in claim 3, it is characterized in that, the future of life cycle T according to the client, described
Historical trading data and the basic attribute data determine the future value CFV of the client, specifically include:
According to client's classification, customer value-time fluctuation rate function r (t) corresponding with the classification is matched；
According to client's future value calculation formula, the future value CFV of the client is calculated.
5. according to the method described in claim 4, it is characterized in that, if the future of life cycle T of the client is greater than or equal to
Life cycle is preset, then client's future value calculation formula are as follows:
Wherein, CV is the value by the end of client described in the observation time, 1 year, and d (t) is cash discount rate.
6. according to the method described in claim 4, it is characterized in that, if the future of life cycle T of the client is less than default life
The period is ordered, then client's future value calculation formula are as follows:
Wherein, CV is the value by the end of client described in the observation time, 1 year, and d is cash discount rate.
7. method according to any one of claim 1 to 6, which is characterized in that described to work as present value according to the client
The future value CFV of value CCV and the client determine the lifelong value CLV of the client, specifically include:
The future value CFV of the current value CCV of the client and the client are summed, the lifelong value of the client is obtained
CLV。
8. a kind of prediction meanss of mixed railway characterized by comprising
Acquiring unit, for obtaining the historical trading data and basic attribute data of the client；
Current value computing unit, for calculating the current value CCV of the client according to the historical trading data；
Future of life period computing unit, for predicting institute according to the historical trading data and the basic attribute data
State the future of life cycle T of client；
Future value computing unit, for according to the client future of life cycle T and the basic attribute data, determine
The future value CFV of the client；
Lifelong value calculation unit is summed for the current value CCV and future value CFV according to the client, is determined
The lifelong value CLV of the client.
9. a kind of storage medium, is stored thereon with computer program, which is characterized in that realization when described program is executed by processor
The prediction technique of mixed railway described in any one of claims 1 to 7.
10. a kind of computer equipment, including storage medium, processor and storage can be run on a storage medium and on a processor
Computer program, which is characterized in that the processor is realized described in any one of claims 1 to 7 when executing described program
Mixed railway prediction technique.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811340698.6A CN109711859A (en) | 2018-11-12 | 2018-11-12 | Prediction technique and device, storage medium, the computer equipment of mixed railway |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811340698.6A CN109711859A (en) | 2018-11-12 | 2018-11-12 | Prediction technique and device, storage medium, the computer equipment of mixed railway |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109711859A true CN109711859A (en) | 2019-05-03 |
Family
ID=66254742
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811340698.6A Pending CN109711859A (en) | 2018-11-12 | 2018-11-12 | Prediction technique and device, storage medium, the computer equipment of mixed railway |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109711859A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110826793A (en) * | 2019-10-30 | 2020-02-21 | 京东数字科技控股有限公司 | Value evaluation method, device, electronic equipment and medium for asset allocation |
| CN112990386A (en) * | 2021-05-17 | 2021-06-18 | 太平金融科技服务(上海)有限公司深圳分公司 | User value clustering method and device, computer equipment and storage medium |
| CN113538070A (en) * | 2020-10-30 | 2021-10-22 | 深圳市九九互动科技有限公司 | User life value cycle detection method and device and computer equipment |
| CN113743991A (en) * | 2021-09-03 | 2021-12-03 | 上海幻电信息科技有限公司 | Life cycle value prediction method and device |
| CN113935529A (en) * | 2021-10-13 | 2022-01-14 | 北京沃东天骏信息技术有限公司 | Method, device, equipment and medium for determining life cycle value of customer |
-
2018
- 2018-11-12 CN CN201811340698.6A patent/CN109711859A/en active Pending
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110826793A (en) * | 2019-10-30 | 2020-02-21 | 京东数字科技控股有限公司 | Value evaluation method, device, electronic equipment and medium for asset allocation |
| CN113538070A (en) * | 2020-10-30 | 2021-10-22 | 深圳市九九互动科技有限公司 | User life value cycle detection method and device and computer equipment |
| CN113538070B (en) * | 2020-10-30 | 2023-12-26 | 深圳市九九互动科技有限公司 | User life value cycle detection method and device and computer equipment |
| CN112990386A (en) * | 2021-05-17 | 2021-06-18 | 太平金融科技服务(上海)有限公司深圳分公司 | User value clustering method and device, computer equipment and storage medium |
| CN112990386B (en) * | 2021-05-17 | 2021-08-03 | 太平金融科技服务(上海)有限公司深圳分公司 | User value clustering method and device, computer equipment and storage medium |
| CN113743991A (en) * | 2021-09-03 | 2021-12-03 | 上海幻电信息科技有限公司 | Life cycle value prediction method and device |
| CN113935529A (en) * | 2021-10-13 | 2022-01-14 | 北京沃东天骏信息技术有限公司 | Method, device, equipment and medium for determining life cycle value of customer |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109711859A (en) | Prediction technique and device, storage medium, the computer equipment of mixed railway | |
| Pauwels et al. | The long-term effects of price promotions on category incidence, brand choice, and purchase quantity | |
| Pousttchi et al. | Surrounded by middlemen-how multi-sided platforms change the insurance industry | |
| CN109409963A (en) | Prediction technique and device, storage medium, the computer equipment of customer life cycle | |
| Fu et al. | An analysis of the factors affecting the adoption of cloud consumer relationship management in the machinery industry in Taiwan | |
| US20200234218A1 (en) | Systems and methods for entity performance and risk scoring | |
| US20150379545A1 (en) | Capacity calculator | |
| US20170213288A1 (en) | Systems and methods for personalized investment allocation | |
| JP2017509947A (en) | Obtaining the social relationship type of a network subject | |
| US9916563B1 (en) | Version recall for computerized catalog management | |
| US20140188787A1 (en) | Crowdsourcing directory system | |
| US20150081398A1 (en) | Determining a performance target setting | |
| US20150254651A1 (en) | Optimizing financial transactions network flow | |
| CN109727085A (en) | Insurance sale method, apparatus, equipment and readable storage medium storing program for executing | |
| US20150100386A1 (en) | Digital framework for business model innovation | |
| US10614402B2 (en) | Human steering dashboard to analyze 360-degree market view for merchants based on financial transactions | |
| US20200234327A1 (en) | Systems and methods for dynamic product offerings | |
| US10096045B2 (en) | Tying objective ratings to online items | |
| KR20230133205A (en) | Off-premise and on-premise based customer-customized it system construction service provision device, method and program | |
| US20210326910A1 (en) | System and method for optimizing an observation campaign in response to observed real-world data | |
| KR20200068064A (en) | Differential fee payment system through professional experts | |
| US10915416B1 (en) | System for environmental impact | |
| US11688157B2 (en) | Shopper analysis using an acceleration sensor and imaging | |
| Shams et al. | App Cost Estimation: Evaluating Agile Environments | |
| CN109714381B (en) | Consumption tracking based information pushing method, equipment, storage medium and device |
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: 20190503 |