CN101044499A - Rating system and method for identifying desirable customers - Google Patents
Rating system and method for identifying desirable customers Download PDFInfo
- Publication number
- CN101044499A CN101044499A CNA2004800141733A CN200480014173A CN101044499A CN 101044499 A CN101044499 A CN 101044499A CN A2004800141733 A CNA2004800141733 A CN A2004800141733A CN 200480014173 A CN200480014173 A CN 200480014173A CN 101044499 A CN101044499 A CN 101044499A
- Authority
- CN
- China
- Prior art keywords
- data
- client
- described client
- selected type
- relevant
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- 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
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Tourism & Hospitality (AREA)
- Technology Law (AREA)
- Educational Administration (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
An advanced grading method and a system are provided, which is used for confirming ideal clients. A possible profit generation tendency of each client is predicted through calculating a prediction index of the client. The prediction index can be based on calculating various client data, which comprises at least two types of client data among the flowing data: assets condition of the client, population information of the client and trade history of the client. A score for the selected client data is confirmed, and a suitable weighing in corresponding to each client data can be provided. Subsequently, the prediction index is calculated on the basis of each weighing and score of the selected client data. Therefore, whether the client is ideal can be confirmed by comparing the prediction index with a preset threshold value.
Description
Related application
The application requires the right of priority of following U.S. Provisional Application patented claim: the application number of on May 22nd, 2003 application is that 60/472,422 name is called the U.S. Provisional Patent Application of " client mark model "; And with the application number of on May 22nd, 2003 application be that 60/472,412 name is called the U.S. Provisional Patent Application of " based revenue model throughout one's life "; The application number of on May 23rd, 2003 application is that 60/472,748 name is called the U.S. Provisional Patent Application of " finance data market account rentability model "; The application number of on May 23rd, 2003 application is that 60/472,747 name is called the U.S. Provisional Patent Application of " finance data market loss analysis model "; Meanwhile Shen Qing application number for _ _ _ _ name of (agency is labeled as 67389-038) is called the U.S. Patent application of " customer revenue prediction method and system "; Meanwhile Shen Qing application number for _ _ _ _ name of (agency is labeled as 67389-039) is called the U.S. Patent application of " client's rentability computing system of activity-oriented "; Meanwhile Shen Qing application number for _ _ _ _ that the name of (agency is labeled as 67389-040) is called the U.S. Patent application of " method and system that is used to predict customer revenue " is relevant.Incorporate the disclosed content of above-mentioned patented claim at this, on the whole as a reference.
Technical field
The present invention relates generally to a kind of ranking method and system that is used for determining desirable customers, more precisely, relate to a kind of ranking method and system that determines desirable customers by the prediction index of calculating each client, wherein prediction index is based on the attribute relevant with the client, such as assets level, people information and/or transactions history, predict the producible possibility of each client profit.
Background technology
For company, can determine that from existing customers desirable client is important.Client's desirability can be determined based on for example this client possible profit that produced or that can bring.Company's maintenance desirable customers of should trying one's best, and abandon those only produce limited or minimum profit to company client.For company, to tie up on the economics be rational so that desirable customers and same company keep closing to provide better treatment and service to desirable customers.
Now, some companies use hierarchy system based on the client desirability of company is determined the treatment type that this client can enjoy.For example, brokerage firm plans to provide extra treatment to those desirable customers, such as elite services, extra discount, propaganda, service observation or the like are provided.Even Customer Service Center also uses automatic system to have produced or can produce the customer call how many profits connect incoming call based on the client.For example, the computer system in the Customer Service Center is based on the identity of the calling of determining incoming call by the caller ID or the account number of caller's input.Then, retrieve the priority of the brief introduction of this calling customer with this calling of definite response.If it is desirable customers (it may produce or can bring many profits) that client's brief introduction shows this calling customer, then computer system is classified as limit priority with this calling, and this calling soon of existing side by side is connected to a special disposal elite client's middle man.On the other hand, do not produce enough profits to prove that it is elite client if client's brief introduction shows this client, then system to common formation, waits for that next available customer service middle man answers this calling with the call distribution of this incoming call.
Although may profit determine that client's desirability is directly, does not have a kind of client of effective method predict what kind to bring more profit to company based on the client is producible.In the past, brokerage firm thinks that the profit that the client can produce is relevant with this client's assets level.Therefore, some brokerage firms distribute client's mark for each client based on client's assets level separately: client's assets level is high more, and client's mark of distribution is high more.If client's mark surpasses predetermined threshold, this client is confirmed as desirable customers so, and can obtain treatment preferably.
Yet, have been noted that merely and determine that according to the assets level desirable customers can not play good effect.For example, in brokerage firm, some client may have high assets level, but their often capital participation activity such as transaction's stock or common fund, therefore only brings limited service fee to brokerage firm.Therefore, such client although they have high assets level, in fact brings considerably less income to brokerage firm.On the other hand, a lot of transactions although only have low-level assets, in fact take place, such as day traders in some client.Therefore although the assets level is lower, such client produces more profit to brokerage firm, though and should have high assets level than those only to produce the client of limited income to brokerage firm better.Therefore, need a kind of system more accurately or technology to determine desirable customers.
Summary of the invention
The invention provides a kind of advanced person's the ranking method and the system that are used for determining desirable customers.An advantage of this ranking method and system is that client's desirability is based on a plurality of factors rather than only definite based on the assets level.Provide prediction index to show each client's desirability.In addition, this advanced ranking method and system adopt the different importance of unique weight system with the factor that suitably solves the various accuracys that influence grading.
Exemplary client's ranking method is calculated each client's prediction index based on various types of customer datas, wherein, customer data comprises at least two types the data of selecting from below: client's assets level, client's people information and client's transactions history.Then determine the mark of the customer data of every kind of selected type.For example, the mark of client's assets level can comprise that the look-up table of the relation between assets level and the reciprocal fraction finds corresponding to the mark of client's assets level by use and determines.After the mark of the data of having determined every kind of selected type, based on this fractional computation client's prediction index.The producible profit trend of this client of the prediction index predicts that obtains is such as profit more or less.
In one embodiment, client's prediction index is passed through the mark addition calculation with the customer data of every kind of selected type.In another embodiment, when calculating prediction index, unique weight system is used to reflect the different importance of various types of customer datas.For example, the predefined weight of every type customer data is applied to each mark of every type data, such as by weight be multiply by mark, to generate weighted score.Then, the weighted score of the customer data of selected type is through mathematics manipulation, such as addition, with the generation forecast index.The weight of the customer data of every kind of selected type can be determined to experience, returns such as passing through.
In order to determine client's desirability, this advanced ranking method can compare prediction index and one or more preset threshold value.Result based on the comparison distribute a desirability level can for each client, and such as unusual ideal, very desirable, general ideal, undesirable or the like, these grades can be used for further handling or evaluation.
A kind of data handling system such as computing machine, can be used to realize ranking method described here and system.Data handling system can comprise the processor that is used for deal with data, the data storage device that is coupled to processor and data transmission device.Data storage device has instruction, so that data handling system is carried out function described here when being executed instruction by processor.Customer database, reference database and weight database can realize on data storage device or any other data storage device that can be visited by data handling system.Instruction can embed in the machine readable media and carry out client's grading with the control data disposal system.Machine readable media can comprise such as the optical storage media of CD-ROM, DVD etc., comprise the magnetic-based storage media of floppy disk or tape and/or such as the solid-state storage device of storage card, flash memory etc.These instructions also can be used carrier wave transmission and transmission.
According to following detailed explanation, other advantage of current disclosed method and system will become very obvious, and these explanations only are examples of the present invention and unrestricted.Just as will be recognized, this client's ranking method can have other and different embodiment with system, and its several details can various obvious aspect correct, all these does not break away from the present invention.Therefore, accompanying drawing and explanation can be considered to illustrative, and not restrictive in fact.
Description of drawings
Be combined in the instructions and a part of description of drawings exemplary embodiment of book as an illustration.
Fig. 1 is a schematic block diagram of describing the architecture of exemplary client's rating system;
Fig. 2 describes the data structure of exemplary customer database;
Fig. 3 illustrates the exemplary look-up table that is included in the reference database;
Fig. 4 describes the process flow diagram of the example process that the desirability that is used for definite client is described;
Fig. 5 illustrates the schematic block diagram of data handling system, can realize exemplary client's rating system of the present invention based on this system.
Embodiment
In the following description, for illustrative purposes, illustrated a lot of specific detail and understood fully of the present invention to provide.Yet for a person skilled in the art, method and system of the present invention can need not these specific detail and realize clearly.In other example, for fear of unnecessarily covering the present invention, known construction and device shows with the form of block diagram.
For illustrative purposes, the following description discussion is used in brokerage firm to determine the exemplary ranking method and the system of desirable customers.Should be appreciated that ranking method disclosed herein and system can be applied to other industry, and different distortion can be arranged that these distortion all are included within the application's the scope.In Fig. 1, show the schematic block diagram of exemplary client's rating system 100.Provide such as the data handling system 102 of computing machine to generate a plurality of clients' each prediction index 110 based on various types of customer datas.The indication that prediction index 110 provides demonstration or prediction client can produce how many profits.Data handling system 102 addressable three databases: customer database 104, reference database 106 and weight information database 108.Various types of customer datas of the customer database 104 a plurality of clients of storage.Various types of customer datas can include but not limited to assets level, people information and transactions history or the like.Data handling system 102 can select to be stored in partly or completely customer data in the customer database 104 to calculate a plurality of prediction index relevant with a plurality of clients.For example, data handling system can select assets level and people information or assets level and transactions history to calculate prediction index.
When calculating the prediction index of particular customer, data handling system 102 accesses customer database 104 are with the customer data of retrieval corresponding to the selected type of particular customer.Data handling system 102 is also visited reference database 106 with the retrieval reference data relevant with the customer data of selected type.Then, data handling system 102 is distributed the mark of the customer data of every kind of selected type based on reference data.For example, for each the data clauses and subclauses in the customer data of selected type, data handling system 102 is stored in look-up table in the reference database 106 by visit and determines corresponding will to distribute to each data strip purpose mark.Then, data handling system 102 uses unique algorithm to calculate the prediction index of particular customer based on the mark that is assigned with of the customer data of every kind of selected type corresponding with this client.In one embodiment, when the generation forecast index, data handling system 102 access weight information databases 108 are with the pre-stored weights of the customer data of retrieving every kind of selected type, and each weight is applied to be assigned to each mark of the customer data of selected type, make the different importance of during the generation forecast index, considering every type customer data.
In one embodiment, the algorithm below data handling system 102 is used is to determine client's prediction index:
C＝aA+bB+cC+dD+eE+fF+gG (a)
Wherein:
C is with calculated prediction index;
A, B, C, D, E, F, G are each marks of distributing to client's every type customer data;
A, b, c, d, e, f, g are the predefined weights (being used for determining that the process of each weight is with very fast discussion) corresponding to every type customer data.
Although equation (a) uses six types customer data to calculate prediction index, the actual quantity and/or the type that are used to generate the customer data of desired indicator are not fixed as six.On the contrary, this depends on design preference.More or less the customer data of type can be used for determining prediction index.For example, customer database 102 can be stored the customer data relevant with assets level, people information and transactions history.Yet the algorithm that is used by data handling system 102 can only use two types customer data generation forecast index.For example, algorithm can only use assets level and people information to calculate prediction index.
The details of customer database 102, reference database 106 and weight information database 108 is described now.
(1) customer database
The customer database 104 storages data clauses and subclauses relevant with each client.Data clauses and subclauses in the customer database 104 comprise various types of customer datas, such as assets level, transactions history and demographic data.Client's assets level is defined as the summation (as long as data are available) of all assets of being had by this client.In the example of brokerage firm, can include but not limited to common stock, preferred stock, right/guarantee, unit (unit), option, corporation loan, CMO/MBS/ABS, money market, municipal bond, U.S. government/act on behalf of bond, common fund by the possible assets that the client has, pay bill or assets that the client that hires common fund, UIT and/or any other type can have.
Demographic data is defined as attribute and/or the characteristic information relevant or that can be used for determining the client with relevant client.For example, demographic data can include but not limited to and the quantity of the duration of brokerage firm, the proprietorial state in client, city size, age, sex, education, marital status, income, address, house in the same family, the vehicle that had and/or type, family income, house person quantity, child's quantity, child's age, the frequency of dining out, hobby or the like.This tabulation does not mean that limit.Carried out with any attribute relevant with the client separately to the relevant empirical studies of the influence of prediction index after, these attributes can be used for the generation forecast index.
The data relevant with transactions history are defined as the every type relevant information of any transaction of having carried out in the past with the user.Although can use other transaction data (if knowing), data usually with relevant with the history of wanting to calculate and use the company of forecasting of profit index to conclude the business, are for example concluded the business with brokerage firm in the present example.For such example, transaction history data can comprise the stock quantity of trade date, type of transaction, number of transaction, trading frequency, average number of transaction, every month number of transaction, every monthly average number of transaction, the total number of transaction in the specific period, each transaction, 12 months every month total number of transaction of moving average or the like.Transaction history data can also comprise real revenue or profit data or the tolerance that obtains, for example the brokerage fee amount of money or reality or average percent commission from income or profit.
The customer data of other type can also be included in and be used to calculate prediction index in the customer database 104.For example, for brokerage firm, also can use the customer data of following type: trimestral average, long term marketable value of past, trimestral average short-term market value of past, trimestral average total assets of past, the trimestral commission of average total assets, past in past 12 months, trimestral interest of past and other expense, trimestral number of transaction of past, past is trimestral to deposit the trimestral quantity of fetching fund, Account Type of fund, past and/or deposit grace period or the like in.The quantity and/or the type that are included in the customer data in the customer database 104 depend on design preference.For whether the customer data of determining one type influences the trend of the profit that is produced by the client, can use recurrence experience ground to determine whether the data of a variable or a type might be relevant with the trend that profit produces.
Fig. 2 illustrates the data structure of the exemplary data entry 204 in the customer database 104.Unique Customer ID 211 is assigned to each client and is used for sign.Data clauses and subclauses 204 comprise various types of customer datas, and it comprises the customer data that can be used for generation forecast index 110 218 of assets level 213, people information 215, transactions history 217 and other type.Corresponding to the information stores of every type customer data in data field 223,225,227,229, as above explanation.
(2) reference database
Determine mark for the assets level based on the client, data handling system 102 is accesses customer database 102 at first, with the retrieval data relevant with client's assets, and the assets total amount of computing client.Then, data handling system 102 is by searching the mark that corresponding scope determines to distribute to this client in " the assets level " 322 of look-up table 306.For example, if determine client's assets total amount total amount $375,000, this client's assets Luo Ru $100 so is in 000 to $1,000,000 the scope.As shown in Figure 3, the reciprocal fraction of this scope is 8.33.Therefore, distributed for this client 8.33 fens based on this client's assets level.Look-up table 306 also comprises the information of customer data of other type and corresponding mark, such as quantity, client's net capital and the population in the city that the client lives of client in transaction, duration, client's age, family with company.
Score distribution relevant with the data of particular type and allocation scores needn't be all consistent for all types of customer datas.The mark that is assigned with in the data of particular type depends on that the customer data of a variable or a type has more important for the profit that the prediction client can produce.Higher mark can be distributed to prior customer data, and lower mark can be distributed to not too important customers data.In addition, can be various type with respect to the score distribution of the customer data of particular type, such as linear distribution, normal distribution etc.
(3) weight information database
As previously discussed, after data handling system 102 had been determined mark corresponding to every type customer data of particular customer, data handling system 102 can use equation (a) to calculate the prediction index of particular customer.Equation (a) is expressed as follows once more:
C＝aA+bB+cC+dD+eE+fF+gG (a)
Wherein:
C is with calculated prediction index;
A, B, C, D, E, F, G are each marks of distributing to client's every type customer data;
A, b, c, d, e, f, g are each weights corresponding to every type customer data.
According to an embodiment, use to return corresponding to the value of each weight of the customer data of each type and determine.For example, in order to obtain the value of the weight a-g in the equation (a), the regression equation below using:
R＝aA+bB+cC+dD+eE+fF+gG (b)
Wherein:
The known profit that the profit that R=has produced or can produce based on each user according to real data or empirical studies is produced by each client or allocate prediction index in advance to each client;
A-G be be input to equation (a) in each corresponding mark of dissimilar actual customer datas;
A-g represents the respective weights of the data of every kind of selected type.
During regression treatment, the customer data of retrieving from known customers is provided for regression equation (b), determining each coefficient (weight) a-g corresponding to every type customer data, its corresponding to influence from the profit of every type customer data or the trend of prediction index.After regression process, being determined and being stored in corresponding to the value of the weight a-g of every type customer data can be by data handling system 102 when using equation (a) to calculate prediction index in the addressable data storage device, in hard disk.
According to an embodiment, each weight of every type customer data can merge in the reference data.For example, in the look-up table in being stored in reference database, the mark that will distribute to every type customer data has reflected the weight of every type corresponding data.In the profit that prediction is produced by the client, play the part of more key player's one type customer data and compare with the customer data of another kind of type and be endowed or distribute higher mark with less influence so that client's rating system can be when calculating prediction index deletion weight is applied to the step of each client's mark that calculates.
After the prediction index of having determined the client, the prediction index that data handling system 102 can be applied to one or more preset threshold value to be determined is to determine whether the client is desirable for brokerage firm.For example, preset threshold value can be as follows:
Client's score desirability
80＜very is desirable
60-80 is very desirable
The 40-60 ideal
20-40 is generally desirable
0-20 is undesirable
After data handling system 102 was determined each client's that brokerage firm has desirability, data handling system 102 can generate the report of the desirability that shows each client.This report can be implemented as the computer documents that is used for by data handling system 102 or the further visit of other data handling system, so that the service of different brackets to be provided to the client based on client's prediction index separately.For example, this report can be by the computer access in the call center, with the calling in the difference incoming call, based on which client to call out and this client has for brokerage firm and manyly desirablely determines which calling should answer with higher priority.The calling of being undertaken by first client with higher forecasting index should be endowed the higher priority of calling of carrying out than by second client with low prediction index, even second client may call out earlier.
Fig. 4 describes the process flow diagram of the process that the desirability of determining the client is described.In step 401, data handling system 102 accesses customer database 104 are to retrieve various types of customer datas of this client.In step 403, data handling system 102 visit reference databases 106 obtain reference data.Then, data handling system 102 distributes mark (step 405) for every type customer data corresponding to this client based on reference data and customer data.In step 407, data handling system 102 access weight information databases 108 are to obtain the weight information of every type customer data.In step 409, data handling system 102 is by with each weight of customer data be assigned with the prediction index that mark is applied to equation as previously discussed (a) computing client.Then, data handling system 102 is applied to preset threshold value the prediction index calculated to determine client's desirability (step 411).Carry out in order although figure 4 illustrates step 401,403 and 405, these steps can be carried out simultaneously.Selectively, data handling system 102 can first execution in step 403 and 405, and weight information and reference information are stored in the storer of data handling system 102, is used for visit afterwards, and making needn't repeating step 403 and 405 for each client.
Fig. 5 illustrates the block diagram of exemplary data handling system 500, can realize client's rating system 100 and/or data handling system 102 based on this system.Data handling system 500 comprise bus 502 or be used to the information of transmitting other communication mechanisms and with bus 502 coupling be used for data processor for processing data 504.Data handling system 500 also comprises the primary memory 506 of the instruction that is used for canned data and is carried out by processor 504 of being coupled to bus 502, such as random access storage device (RAM) or other dynamic storage device.Primary memory 506 can also be used for carrying out storage temporary variable or other intermediate information between the order period of being carried out by data processor 504.Data handling system 500 also comprises the static information that is used for storage of processor 504 that is coupled to bus 502 and ROM (read-only memory) (ROM) 508 or other static memory of instruction.Memory storage 510 such as disk or CD is provided, and it is coupled to bus 502 and is used for canned data and instruction.Data handling system 500 can have also that to be used for data be the appropriate software and/or the hardware of another kind of form from a kind of format conversion.The example of this conversion operations is that the format conversion with data available in the system 500 is another kind of form, such as the form that makes things convenient for data transmission.
Data handling system 500 can be coupled to the display 512 that is used for to operator's display message by bus 502, such as cathode ray tube (CRT), Plasmia indicating panel or LCD (LCD).Input media 514 comprises alphanumeric keys and other key, is coupled to bus 502, is used for to processor 504 transmission information and command selection.The user input apparatus of another kind of type is a cursor control (not shown), such as mouse, touch pad, trace ball or cursor direction key etc., is used for to processor 504 direction of transfer information and order and control cursor moving on display 512.
Control data disposal system 500 is carried out one or more sequence that is included in one or more instruction in the primary memory 506 with answer processor 504.These instructions can be read in primary memory 506 from another machine readable media such as memory storage 510.The sequence that execution is included in the instruction in the primary memory 506 makes processor 504 carry out treatment step described here.For example, under the control of prestored instruction, data processor 504 visit is stored in data storage device 510 and/or is coupled to customer data, reference data and/or weight data in other data storage device of data handling system, and generates client's client's mark and/or prediction index.In alternate embodiments, hard-wired circuit can be used for the instead of software instruction or grade to realize disclosed client in conjunction with software instruction.Therefore, the client embodiment that grades is not limited to any particular combinations of hardware circuit and software.
Here employed term " machine readable media " is meant that any participation provides instruction to carry out or to provide the medium of data to handle to processor 504 to processor 504.This medium can adopt various ways, includes but not limited to non-volatile media, Volatile media and transmission medium.For example, non-volatile media comprises CD or disk, such as memory storage 510.Volatile media comprises dynamic storage, such as primary memory 506.Transmission medium comprises twisted-pair feeder, copper cash and optical fiber, comprises the circuit that comprises bus 502 or external network.Transmission medium also can adopt the form of sound wave or light wave, transmits generating in radiowave and infrared data such as those, and they can transmit on the link of bus or external network.
The common form of machine readable media comprises the medium that for example floppy disk, flexible plastic disc, hard disk, tape or other magnetic mediums, CD-ROM, any other light medium, card punch, paper tape, any physical medium, RAM, PROM, EPROM, flash memory, any other storage chip or box, carrier wave hereinafter described or any other data handling system that other has poroid style can read.
The various forms of machine readable media can participate in one or more sequence with one or more instruction and send processor 504 to and be used for carrying out.For example, instruction can transmit on the disk such as the remote data processing system of server at first.Remote data processing system can be loaded into instruction in the dynamic storage of oneself, and uses modulator-demodular unit to send this instruction by telephone wire.The modulator-demodular unit of data handling system 500 this locality can receive data by telephone wire, and uses infrared transmitter that these data are converted to infrared signal.Infrared eye may be received in the data that transmit in the infrared signal, and suitable circuit can be placed on these data on the bus 502.Certainly, various broadband communication techniques/equipment can be used for any one of these links.Bus 502 is sent to primary memory 506 with data, and processor 504 is retrieval and execution command and/or deal with data from primary memory 506.Instruction that receives by primary memory 506 and/or data can be optionally before the execution of processor 504 or other are handled or be stored in afterwards in the memory storage 510.
Data handling system 500 also comprises the communication interface 518 that is coupled to bus 502.Communication interface 518 provides bidirectional data communication, and it is coupled to the network link 520 that is connected to local network.For example, communication interface can be Integrated Service Digital Network card or modulator-demodular unit, provides data communication to connect with the telephone wire to corresponding types.As another example, communication interface 518 can be wired or WLAN (wireless local area network) (LAN) card, provides data communication to connect with the LAN (Local Area Network) to compatibility.In any one such embodiment, communication interface 518 sends and receives electric signal, electromagnetic signal or the light signal of the digital data stream that is loaded with the various types of information of expression.
Network link 520 provides data communication by one or more network to other data equipments usually.For example, network link 520 can provide connection to the data equipment by ISP (ISP) 526 operations by local network.ISP 526 and then provide data communication services by the current worldwide packet data communication network that is known as the Internet 527.Local ISP network 526 and the Internet 527 all use electric signal, electromagnetic signal or the light signal that is loaded with digital data stream.Through the signal of diverse network and on network link 520 and the signal by communication interface 518 to transmit signals from data handling system 500, and all be the exemplary form of the carrier wave of transmission information.
Data handling system 500 can send message and receive data by network, network link 520 and communication interface 518, comprises program code.In the example of the Internet, server 530 can pass through the code that the Internet 527, ISP 526, local network and communication interface 518 send requested application program.This program for example can realize client's grading as described above.Communication capacity also allows related data is loaded into and is used in the system handling according to the present invention.
Data handling system 500 also has various signal input/output end ports, is used to be connected to such as the peripherals of printer, display etc. and with it communicate.Input/output end port can comprise USB port, PS/2 port, serial port, parallel port, IEEE-1394 port, infrared communications ports or the like, and/or other proprietary port.Data handling system 500 can communicate by these signal input/output end ports and other data handling system.
Although be current modal type, person of skill in the art will appreciate that personal computer (PC) only is one type the data handling system that can be used to realize rating system.Other end-user device comprises portable digital-assistant (PDA), other honeycomb fashion with network or the Internet access capabilities or radio Phone unit, the Web TV equipment etc. with suitable communication interface.
Rating system described here and method can use the combination such as the individual data disposal system of single PC or a plurality of data of different types disposal systems to realize.For example, client-server or distributed data processing architecture can be used to realize rating system, and wherein, a plurality of data handling systems are coupled on the network to communicate mutually.Some data handling system can be used as server, and data streams provides calculation services or access customer data, and/or upgrades the software that resides in other data handling system that is coupled to this network.
It is pointed out that be contained in the above description and all the elements illustrated in the accompanying drawings all should be construed as illustrative, and not restrictive.It is also understood that following claim means covers all general and specific features described here and all statements of various invention thought ranges, and these invention thoughts can be expressed as from the language and fall into wherein.
Claims (38)
1. client's ranking method may further comprise the steps:
Visit the data relevant with the client, accessed data comprise at least two types the data of selecting from the group that the transactions history by described client's assets level, described client's people information and described client constitutes;
Determine the mark of the data of the every kind selected type relevant with described client; And
Based on the mark of the data of the every kind selected type relevant, calculate described client's prediction index with described client;
Wherein, the producible profit trend of the described client of described prediction index predicts.
2. the step of the method for claim 1, wherein calculating described client's prediction index comprises the mark addition with the data of the every kind selected type relevant with described client.
3. the method for claim 1, wherein described calculation procedure may further comprise the steps:
Visit the weight of the data of the every kind selected type relevant with described client; And
Based on the weight of the data of the mark of the data of the every kind selected type relevant and the every kind selected type relevant, calculate described client's prediction index with described client with described client.
4. method as claimed in claim 3, wherein, the weight of the data of the every kind selected type relevant with described client is determined by returning.
5. the method for claim 1, further comprising the steps of:
Visit the data relevant with the profit threshold value;
Described prediction index is compared with the data relevant with described profit threshold value; And
The result of step indicates whether described client is desirable based on the comparison.
6. the trend of the method for claim 1, wherein described profit trend indication client aspect producing a profit.
7. method as claimed in claim 6, wherein, described profit is relevant with transaction or commission profit.
8. the method for claim 1 also comprises the step of determining described client's the grade of service based on the prediction index of being calculated.
9. method as claimed in claim 8, wherein, the described grade of service is relevant with the priority of answering the call of being undertaken by described client.
10. the step of mark of the method for claim 1, wherein determining the data of the every kind selected type relevant with described client may further comprise the steps:
Visit comprises the reference data of the mark of the data that will distribute to every kind of selected type;
The data and the corresponding reference data of every kind of selected type are compared; And
The result of step determines the mark of the data of every kind of selected type based on the comparison.
11. method as claimed in claim 10, wherein, described reference data comprises look-up table, the relation between they data that comprise every kind of selected type and the corresponding mark.
12. a data handling system that is used for client's grading comprises:
The processor that is used for deal with data;
Be coupled to the data storage device of described processor;
Described data storage device has makes described data handling system carry out the instruction of following steps:
Visit the data relevant with the client, described accessed data comprise at least two types the data of selecting from the group that the transactions history by described client's assets level, described client's people information and described client constitutes;
Determine the mark of the data of the every kind selected type relevant with described client; And
Based on the mark of the data of the every kind selected type relevant, calculate described client's prediction index with described client;
Wherein, the producible profit trend of the described client of described prediction index predicts.
13. system as claimed in claim 12 wherein, controls described data handling system with by the prediction index with the described client of mark addition calculation of the data of the every kind selected type relevant with described client.
14. system as claimed in claim 12, wherein, described data storage device also has makes described data handling system carry out the instruction of following steps:
Visit the weight of the data of the every kind selected type relevant with described client; And
Based on the weight of the data of the mark of the data of the every kind selected type relevant and the every kind selected type relevant, calculate described client's prediction index with described client with described client.
15. system as claimed in claim 14 wherein, controls the weight of described data handling system with the data by the regression Calculation every kind selected type relevant with described client.
16. system as claimed in claim 12 wherein, controls described data handling system to determine the mark of the data of the every kind selected type relevant with described client by carrying out following steps:
Visit comprises the reference data of the mark of the data that will distribute to every kind of selected type;
The data and the corresponding reference data of every kind of selected type are compared; And
The result of step determines the mark of the data of every kind of selected type based on the comparison.
17. system as claimed in claim 12, wherein, described data storage device also has makes described data handling system carry out the instruction of following steps:
Visit the data relevant with the profit threshold value;
Described prediction index is compared with the data relevant with described profit threshold value; And
The result of step indicates whether described client is desirable based on the comparison.
18. system as claimed in claim 12, wherein, described profit trend is represented the trend of client aspect producing a profit.
19. system as claimed in claim 18, wherein, described profit is relevant with transaction or commission profit.
20. system as claimed in claim 12, wherein, described data storage device also comprises the instruction that makes described data handling system determine described client's the grade of service based on the prediction index of being calculated.
21. system as claimed in claim 20, wherein, the described grade of service is relevant with the priority of answering the call of being undertaken by described client.
22. program that comprises instruction, it can be included in and be used for the control data disposal system in the machine readable media client is graded, and described instruction makes described data handling system carry out the step of the method for claim 1 when being carried out by described data handling system.
23. program as claimed in claim 22, wherein, the step of calculating described prediction index comprises the mark addition with the data of the every kind selected type relevant with described client.
24. program as claimed in claim 22, wherein, calculation procedure is further comprising the steps of:
Visit the weight of the data of the every kind selected type relevant with described client; And
Based on the weight of the data of the mark of the data of the every kind selected type relevant and the every kind selected type relevant, calculate described client's prediction index with described client with described client.
25. program as claimed in claim 24 wherein, is controlled the weight of described data handling system with the data by the regression Calculation every kind selected type relevant with described client.
26. program as claimed in claim 22 wherein, determines that the step of mark of the data of the every kind selected type relevant with described client may further comprise the steps:
Visit comprises the reference data of the mark of the data that will distribute to every kind of selected type;
The data and the corresponding reference data of every kind of selected type are compared; And
The result of step determines the mark of the data of the every kind selected type relevant with described client based on the comparison.
27. program as claimed in claim 22 is also controlled described data handling system and is carried out following steps:
Visit the data relevant with the profit threshold value;
Described prediction index is compared with the data relevant with described profit threshold value; And
The result of step indicates whether described client is desirable based on the comparison.
28. client's ranking method may further comprise the steps:
Visit the data relevant with the client, described accessed data comprise at least two types the data of selecting from the group that the transactions history by described client's assets level, described client's people information and described client constitutes; And
Determine described client's prediction index based on the data of the selected type relevant with described client;
Wherein, the producible profit trend of the described client of described prediction index predicts.
29. as right 28 described methods, wherein, described prediction index is determined by following steps:
Determine the mark of the data of the every kind selected type relevant with described client; And
Prediction index based on the described client of fractional computation of the data of the every kind selected type relevant with described client.
30. as right 29 described methods, wherein, the step of calculating described prediction index comprises the mark addition with the data of the every kind selected type relevant with described client.
31. as right 29 described methods, wherein, calculation procedure is further comprising the steps of:
Visit the weight of the data of the every kind selected type relevant with described client; And
Based on the weight of the data of the mark of the data of the every kind selected type relevant and the every kind selected type relevant, calculate described client's prediction index with described client with described client.
32. as right 31 described methods, wherein, the weight of the data of the every kind selected type relevant with described client is determined by returning.
33., wherein, determine that the step of mark of the data of the every kind selected type relevant with described client may further comprise the steps as right 29 described methods:
Visit comprises the reference data of the mark of the data that will distribute to every kind of selected type;
The data and the corresponding reference data of every kind of selected type are compared; And
The result of step determines the mark of the data of the every kind selected type relevant with described client based on the comparison.
34., further comprising the steps of as right 28 described methods:
Visit the data relevant with the profit threshold value;
Described prediction index is compared with the data relevant with described profit threshold value; And
The result of step indicates whether described client is desirable based on the comparison.
35. as right 28 described methods, wherein, the trend of described profit trend indication client aspect producing a profit.
36. method as claimed in claim 35, wherein, described profit is relevant with transaction or commission profit.
37. method as claimed in claim 28 also comprises the step of determining described client's the grade of service based on the prediction index of being calculated.
38. method as claimed in claim 37, wherein, the described grade of service is relevant with the priority of answering the call of being undertaken by described client.
Applications Claiming Priority (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| US47242203P | 2003-05-22 | 2003-05-22 | |
| US60/472,422 | 2003-05-22 | ||
| PCT/US2004/016273 WO2004107117A2 (en) | 2003-05-22 | 2004-05-24 | Rating system and method for identifying desirable customers |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN101044499A true CN101044499A (en) | 2007-09-26 |
Family
ID=33490501
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNA2004800141733A Pending CN101044499A (en) | 2003-05-22 | 2004-05-24 | Rating system and method for identifying desirable customers |
Country Status (7)
| Country | Link |
|---|---|
| EP (1) | EP1625481A4 (en) |
| JP (1) | JP2007502482A (en) |
| KR (1) | KR100751966B1 (en) |
| CN (1) | CN101044499A (en) |
| AU (1) | AU2004244266B2 (en) |
| CA (1) | CA2522612A1 (en) |
| WO (1) | WO2004107117A2 (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102915481A (en) * | 2012-09-26 | 2013-02-06 | 北京百度网讯科技有限公司 | Method, device and unit for managing user accounts |
| CN107688892A (en) * | 2017-07-31 | 2018-02-13 | 平安科技（深圳）有限公司 | Distribution method, storage medium and the server of breakpoint list |
| CN108320089A (en) * | 2018-01-25 | 2018-07-24 | 平安科技（深圳）有限公司 | It attends a banquet distribution method, electronic device and computer readable storage medium |
| CN108765094A (en) * | 2018-06-06 | 2018-11-06 | 中国平安人寿保险股份有限公司 | Insurance data processing method, device, computer equipment and storage medium |
| CN109409908A (en) * | 2018-10-10 | 2019-03-01 | 北京长城华冠汽车技术开发有限公司 | Customer value classification method and device, computer-readable medium |
| CN111986030A (en) * | 2020-09-02 | 2020-11-24 | 河北幸福消费金融股份有限公司 | Data processing method, data processing device, storage medium and computer equipment |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2521185A1 (en) * | 2003-05-22 | 2004-12-09 | Pershing Investments, Llc | Method and system for predicting attrition customers |
| KR100902009B1 (en) * | 2007-03-16 | 2009-06-12 | 주식회사 신한은행 | System for Producing Profitable Integrated Group Classified by Custom |
| US20150142638A1 (en) * | 2013-05-02 | 2015-05-21 | The Dun & Bradstreet Corporation | Calculating a probability of a business being delinquent |
| US10339477B2 (en) | 2014-12-10 | 2019-07-02 | [24] 7.ai, Inc. | Method and apparatus for facilitating staffing of resources |
| CN105677881B (en) * | 2016-01-12 | 2020-07-03 | 腾讯科技（深圳）有限公司 | Information recommendation method and device and server |
| JP7153613B2 (en) * | 2019-07-03 | 2022-10-14 | 株式会社日立製作所 | Customer management system and customer management method |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6119103A (en) * | 1997-05-27 | 2000-09-12 | Visa International Service Association | Financial risk prediction systems and methods therefor |
| JP2001022851A (en) * | 1999-07-09 | 2001-01-26 | Hitachi Ltd | Method and system for scoring |
| JP2001109733A (en) * | 1999-10-12 | 2001-04-20 | Hitachi Ltd | Method for evaluating identification model and method for adjusting threshold |
| JP2004528611A (en) * | 2000-07-14 | 2004-09-16 | レイネス，シルバイン | Structured financial performance monitoring indicators |
| JP2002092305A (en) * | 2000-09-13 | 2002-03-29 | Hitachi Ltd | Score calculating method, and score providing method |
| JP2002157422A (en) * | 2000-11-20 | 2002-05-31 | Fujitsu Ltd | Credit method and recording medium |
| JP2003022359A (en) * | 2001-07-06 | 2003-01-24 | Hitachi Ltd | Method and device for analyzing customer lifetime value |
| JP2003114977A (en) * | 2001-10-03 | 2003-04-18 | Hitachi Ltd | Method and system for calculating customer's lifelong value |
| AU2003293135A1 (en) * | 2002-12-03 | 2004-06-23 | Future Quote Incorporated | System and method for managing investment information |
| US7877265B2 (en) * | 2003-05-13 | 2011-01-25 | At&T Intellectual Property I, L.P. | System and method for automated customer feedback |
-
2004
- 2004-05-24 CA CA002522612A patent/CA2522612A1/en not_active Abandoned
- 2004-05-24 WO PCT/US2004/016273 patent/WO2004107117A2/en active Application Filing
- 2004-05-24 AU AU2004244266A patent/AU2004244266B2/en not_active Ceased
- 2004-05-24 JP JP2006533355A patent/JP2007502482A/en active Pending
- 2004-05-24 EP EP04753149A patent/EP1625481A4/en not_active Withdrawn
- 2004-05-24 CN CNA2004800141733A patent/CN101044499A/en active Pending
- 2004-05-24 KR KR1020057022076A patent/KR100751966B1/en not_active IP Right Cessation
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102915481A (en) * | 2012-09-26 | 2013-02-06 | 北京百度网讯科技有限公司 | Method, device and unit for managing user accounts |
| CN102915481B (en) * | 2012-09-26 | 2016-08-17 | 北京百度网讯科技有限公司 | A kind of method, device and equipment for user account is managed |
| CN107688892A (en) * | 2017-07-31 | 2018-02-13 | 平安科技（深圳）有限公司 | Distribution method, storage medium and the server of breakpoint list |
| CN108320089A (en) * | 2018-01-25 | 2018-07-24 | 平安科技（深圳）有限公司 | It attends a banquet distribution method, electronic device and computer readable storage medium |
| WO2019144516A1 (en) * | 2018-01-25 | 2019-08-01 | 平安科技（深圳）有限公司 | Agent allocation method, electronic device, and computer-readable storage medium |
| CN108765094A (en) * | 2018-06-06 | 2018-11-06 | 中国平安人寿保险股份有限公司 | Insurance data processing method, device, computer equipment and storage medium |
| CN109409908A (en) * | 2018-10-10 | 2019-03-01 | 北京长城华冠汽车技术开发有限公司 | Customer value classification method and device, computer-readable medium |
| CN111986030A (en) * | 2020-09-02 | 2020-11-24 | 河北幸福消费金融股份有限公司 | Data processing method, data processing device, storage medium and computer equipment |
| CN111986030B (en) * | 2020-09-02 | 2023-09-08 | 河北幸福消费金融股份有限公司 | Data processing method, device, storage medium and computer equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| EP1625481A2 (en) | 2006-02-15 |
| KR20060021854A (en) | 2006-03-08 |
| AU2004244266B2 (en) | 2008-01-17 |
| JP2007502482A (en) | 2007-02-08 |
| WO2004107117A2 (en) | 2004-12-09 |
| CA2522612A1 (en) | 2004-12-09 |
| WO2004107117A3 (en) | 2006-06-01 |
| KR100751966B1 (en) | 2007-08-24 |
| EP1625481A4 (en) | 2009-07-01 |
| AU2004244266A1 (en) | 2004-12-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN1795462A (en) | Customer revenue prediction method and system | |
| CN103270528B (en) | Use the anonymous configuration file distribution system of target data, method and computer-readable medium | |
| CN108681970A (en) | Finance product method for pushing, system and computer storage media based on big data | |
| CN110298547A (en) | Methods of risk assessment, device, computer installation and storage medium | |
| CN102750645A (en) | Implementing computer interaction response tests | |
| US11270375B1 (en) | Method and system for aggregating personal financial data to predict consumer financial health | |
| CN107885868A (en) | Generate method, system and the medium of the graph-based of channel contribution | |
| CN101044499A (en) | Rating system and method for identifying desirable customers | |
| CN108764332A (en) | A kind of Channel Quality analysis method, computing device and storage medium | |
| CN109190028A (en) | Activity recommendation method, apparatus, electronic equipment and storage medium based on big data | |
| CN112204610A (en) | Neural network based electronic content | |
| CN108351787A (en) | The device-based filtering of content item associated with mobile application | |
| CN110109955A (en) | Data call amount statistical method, system, computer installation and readable storage medium storing program for executing | |
| US20120046990A1 (en) | Process and system for creating a compatibility rating used by entrepreneurs to allow them to select business opportunity providers | |
| CN109075987A (en) | Optimize digital assembly analysis system | |
| CN112449002B (en) | Method, device and equipment for pushing object to be pushed and storage medium | |
| CN111598632B (en) | Method and device for determining equity shares and equity share sequence | |
| US9973910B1 (en) | Mobile content distribution system | |
| CN112070564B (en) | Advertisement pulling method, device and system and electronic equipment | |
| US20220036386A1 (en) | Subscription renewal prediction with a cooperative component | |
| CN112967131A (en) | Loan collection scheme pushing method and device | |
| Flamm et al. | effects of market structure on broadband quality in local us residential service markets | |
| CN113434560A (en) | Sorting method, electronic equipment and related product | |
| CN112418654A (en) | Resource allocation method and device, electronic equipment and storage medium | |
| CN111461863A (en) | Data processing method and device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Open date: 20070926 |