CN1967579A - Aid excavating analysis system of financial risk management - Google Patents
Aid excavating analysis system of financial risk management Download PDFInfo
- Publication number
- CN1967579A CN1967579A CNA2006100312193A CN200610031219A CN1967579A CN 1967579 A CN1967579 A CN 1967579A CN A2006100312193 A CNA2006100312193 A CN A2006100312193A CN 200610031219 A CN200610031219 A CN 200610031219A CN 1967579 A CN1967579 A CN 1967579A
- Authority
- CN
- China
- Prior art keywords
- data
- algorithm
- mining
- analysis
- management
- 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
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention disclosed a financial risk management aided mining analysis system, and the system is based on computer LAN, using distributed architecture, including: a data management server; a management controller; a mining processing server; more than one model application server; and the input and output terminals; system devices include corresponding software systems. The analysis system in the invention uses data mining technologies, which directly access to model law by data-driven, and not the modeling technologies based on the ''assumptions'' commonly used in traditional methods, so it can objectively, factually grasp the features of the market laws.
Description
Technical field
The present invention is a kind of employing data mining technology, and in conjunction with quantification financial risk management technology, by analysis to a large amount of historical datas, obtain financial market law characteristic information, for financial institution effectively manages the analytic system that decision-making assistant information is provided to its market risk and credit risk.
Background technology
The world today is the epoch of an informationization and quantification, all has every day countless data producing.Many business activities (as customer analysis, investment decision, risk management, price expectation etc.) of financial institution at present all more and more depend on the analysis to a large amount of historical datas for realizing its scientific management decision-making.Data mining then is one can find technology that it is hidden, useful, that make user's interest pattern and rule and information is provided with the decision-making that succinct, understandable form is people automatically from mass data.Its notion proposes in 1989 International Joint Conferences on Artificial Intelligences (IJCAI) first, causes the attention of a lot of in the world scholars, mechanism immediately.Started the research boom of data mining in the nineties, up till now,, obtained remarkable progress, and be successfully applied to many industries through effort about ten years.Financial risks is the inherent attribute of finance activities, and it extensively exists is the key character in modern finance market.Since the seventies in 20th century, because the influence with factors such as financial liberalization, infotech and financial innovation activities of relaxing control, the undulatory property enhancing in financial market, the stability decreases of financial system.The innovation of this technology to risk management, method has proposed more and more urgent requirement.Modern information technologies role in risk management is more and more important.Big in the world financial institution all pays much attention to and adopts up-to-date infotech, sets up advanced risk management system and the new risk management method of exploitation.In fact, the essence of financial risks is the uncertainty of future profits in the finance activities (loss), thereby how the purpose of risk management will measure exactly, reduces even eliminates various uncertainties.This is crucial again to depend on obtaining of information and knowledge.And in the middle of the data of a large amount of numerous and complicated, obtain the significant information essential place of data mining just.
From finance data, obtain characteristic information and also be the important content in the modern finance econometric theory, classic method obtains to describe the mathematical model of financial time series rule mainly based on the mathematical statistics model by means such as model hypothesis, parameter estimation, model testing and technology.In order to make up model, many assumed conditions are necessary.Requiring time series data such as arma modeling commonly used is stably, and the time series and the error between observation sequence that require arma modeling to produce are separate, and is normal distribution.Yet for many realities, these assumed conditions but are quite " harshnesses ".And always based on the viewpoint of a kind of " overall situation " property, model parameter estimation is a criterion with the optimal adaptation of " owning " being investigated data to this statistical model analytical technology often.In a single day model builds, and it is with " being suitable for " all parts in data, and this obviously is unpractical.
Summary of the invention
The purpose of this invention is to provide a kind of employing data mining technology, directly come the analytic system of obtaining mode rule with data-driven, this analytic system be not based on classic method the modeling technique that generally adopts based on " hypothesis ", thereby its energy is objective, hold the market discipline feature truly.
In order to realize the foregoing invention purpose, the present invention by the following technical solutions:
Aid excavating analysis system of financial risk management is based on LAN (Local Area Network), adopt distributed frame, comprise: a data management server, be used to realize collection, storage, pre-service and the search function of data, excavate basic data and use raw data for total system provides, need as the case may be, it links to each other with other Service Database server with Internet; One Management Controller is used for providing operating platform to the user, realizes that data management, excavation, rule knowledge are safeguarded, application model is set up and the issue of safeguarding control command of model application; One excavates processing server, is used to accept the mining task of Management Controller, calls digging tool, excavates the generation knowledge rule on the mining data collection of appointment; An above model application server comprises corresponding Message Display Terminal, utilizes the knowledge architecture application model of excavating, and constitutes the monitoring tools monitoring and analyze real-time image data, and risk and decision information are provided; And input/output terminal.
Described aid excavating analysis system of financial risk management device includes corresponding software system, comprising: a total control subsystem, a data acquisition and conversion subsystem, a mining algorithm ADMINISTRATION SUBSYSTEM, are excavated application model ADMINISTRATION SUBSYSTEM, a rule knowledge ADMINISTRATION SUBSYSTEM, a risk identification and Monitor And Control Subsystem.Cooperation by each functional subsystem realizes the functions such as collection, pre-service, rule digging and rule application to finance data.For financial risk management provide the traditional analysis system some implicit informations that can not provide.The basic function of each subsystem is as follows:
Total control subsystem comprises system operation framework interface, systematic parameter maintenance etc., runs on the Management Controller, and by the message exchange of computer network realization with other server, the realization of other server capability is controlled in issue an order.
Data administration subsystem, run on the data management server, comprise data acquisition and modular converter, data preprocessing function module, data source administration module, its purpose is the data integration with various numerous and complicated, guarantee the availability and the validity of data, for data mining provides clear, standard, accordant interface.Wherein data acquisition and modular converter are used for the data source from different-format, obtain data message as databases such as ORACLE/SQL SERVER/INFORMIX/DB2/SYSBASE, data warehouse, text, XML, Excel etc.; Data preprocessing function module is used to solve the vacancy of data, imperfect, inconsistent and noise smoothing, and wherein noise smoothing provides a plurality of tool models such as moving average, wavelet transformation at the actual features of finance data; The data source administration module is used for definition, retrieval, upgrades mining data source and monitor data source.
The mining algorithm ADMINISTRATION SUBSYSTEM runs on and excavates on the processing server, comprises an algorithms library, be used for definition, retrieval, upgrade the master data mining algorithm, system intialization at present following basic digging technology, mainly comprise:
Sorting technique: comprise decision tree ID3 algorithm, C4.5 algorithm, CART algorithm, SLIQ algorithm, SVM etc.;
Clustering technique: comprise hierarchical cluster method, cut apart clustering algorithm PAM, CLARA algorithm, k-means, k-modes clustering algorithm etc. based on bee-line, longest distance and intermediate distance;
The association analysis technology: comprise the Apriori algorithm, the MAQA algorithm of multi-valued attribute is based on the association algorithm of common mechanism;
Techniques of teime series analysis: comprise ARMA, ARCH, GARCH, TSEOPM algorithm;
Nerual network technique: comprise the BP network, Elaman network and Hopfield network.
Excavate the application model ADMINISTRATION SUBSYSTEM, run on the Management Controller, comprise an application model storehouse.Each excavates application model is that concrete application purpose is arranged, and has specified the processing logic of concrete mining data source, mining algorithm, excavation parameter and step.This subsystem realize application model definition, check, delete and start.Native system specifically is divided into credit mining analysis, interest rate mining analysis, exchange rate mining analysis, share price mining analysis and confluence analysis several sections according to finance data classification difference with application model.Selecting on the proper data basis, using and excavate basic algorithm and technique construction mining model for each part.For example, the credit mining analysis, system by the classified excavation method, obtains the credit appraisal rule knowledge according to loan application people's essential information, credit record information, demographic information etc.; And for example, can obtain the credit appraisal rule and the knowledge of mechanism according to the applicant's of mechanism financial information, trade information, open market operation information etc.; The share price mining analysis can excavate according to share price sequence, the trading volume sequence of history for another example, and the share price of following certain section time range is predicted, obtains prediction rule knowledge.
The rule knowledge ADMINISTRATION SUBSYSTEM runs on the Management Controller, be used for to the rule knowledge of having excavated inquire about, add, maintenance management such as deletion, also comprise according to the effect feedback information of practical application rule knowledge suitably adjusted.
Risk identification and Monitor And Control Subsystem run on the application server.It utilizes mining rule knowledge, monitors the real time data of gathering, and the decision information of risk management is provided.Comprise that mainly monitoring data collection, monitoring rule are safeguarded, three functional modules of monitor message issue.The number of application server can be according to using the number flexible configuration.Be but that the different application server moves different application subsystems respectively, guarantee the response speed and the handling property of system.
Total system can be divided four layer architectures by functional hierarchy, i.e. data Layer, algorithm layer, model layer and application layer.
Native system merges the several data digging technology, can obtain hiding, novel information from data, realizes " deep processing " to finance data.The essence of financial risks is the uncertainty of financial variable fluctuation.Data mining be one comprise data selection, pre-service, model excavate obtain, the process of a plurality of steps such as model evaluation, model use and consolidation.Each step in the process has very important effect to the successful Application of excavating the result, all should consider the actual features of finance data and the specific demand of financial risk management.In addition, the connotation of financial risk management is quite widely, says from the risk form to comprise credit risk, the market risk (interest rate, the exchange rate, stock), legal risk, operational risk, policy risk or the like.From risk subject, comprise bank, insurance, security, enterprise, resident, country etc.Native system is based on data mining method, from a large amount of historical datas, obtain implicit information or knowledge, and utilize the dynamic change of these knowledge monitor datas, the risks and assumptions that identification is wherein implicit, discern and monitor thereby play the market risk and credit risk that financial institution is faced, in time provide the effect of information warning.
Native system comprises multiple digging technologies such as classification analysis, cluster analysis, association analysis, time series analysis, anomaly analysis, can obtain various different kinds of information from data.Can utilize the instrument that presets independently to analyze, develop the excavation application model by the user, many sides, identification and the various risks and assumptions of monitoring existence with multi-angle.This is that traditional risk management technology and risk management system do not realized.
The basis risk analytic function that native system presets specifically has:
Interest rate is analyzed: comprise interest rate trend analysis, interest rate uncertainty analysis, interest rate correlation analysis, term structure analysis, interest rate risk factorial analysis etc.And quantize interest rate gap and interest rate risk, and calculate profit, the sight simulator is provided, simulate the fluctuation of interest rate and the risk-repayment of multiple sight hypothesis.
Foreign Exchange Rate Analysis: comprise exchange rate trend analysis, fluctuation of exchange rate estimation, exchange rate correlation analysis, unusual fluctuations analysis, policy implication analytic function.
Credit analysis: comprise credit grade evaluation, Default Probability analysis, credit association analysis, fraud detection analysis, unusual trading activity analysis, the analysis of bad account client characteristics;
Share price is analyzed: comprise share price forecast analysis, volatility analysis, the association analysis of valency amount, the pattern analysis of share price local prediction, stock cluster analysis, stock exchange analysis of strategies etc.;
Confluence analysis: comprise interest rate and share price relationship analysis, interest rate and exchange rate relationship analysis, share price and credit standing association analysis.
Existing point forecast in the wherein various forecast analysis also has the interval probability prediction.The result of point forecast is a concrete numerical value, and the interval prediction result is a numerical value interval with probability.
Native system compared with prior art has following characteristic:
(1) can realize in-depth analysis to finance data.Traditional financial risks analytic system is just processed processing simply to finance data, provide gather, recurrence and chart etc. analyze function.Its understanding to finance data is based upon in the assurance and understanding basis of people to existing knowledge.User before analyzing is just known for knowledge type, just carries out parameter estimation and result's calculating by computing machine.And native system is based on data mining technology, and purpose is the information that people do not know as yet that obtains from data.The knowledge type of these information, structure are before excavating, and the user is unknown fully.Because the loss majority that financial risks caused all has unexpectedly, key reason just is the implicity of risks and assumptions and intellectual not, and native system is by data mining technology, profoundly excavate in the middle of a large amount of, multidimensional, the complicated data and hide Info, the information that provides has novelty, interesting property, exactly a class unexpectedly, allow the surprised information of people.Thereby more can be fit to the needs of financial risk management.
(2) open platform structural design.Along with the research that deepens continuously of data mining technology, new technology continues to bring out.Native system adopts the Open architecture design, and the user can self-management and safeguarded the digging technology storehouse, constantly expands new mining algorithm.In addition,, can self-management excavate the application model storehouse, expand new application model, thereby improve the availability and the dirigibility of system with safeguarding according to user's needs and research.
(3) the visual of user experience parameter obtained.Data mining is paid much attention to digger's subjective experience or background knowledge is incorporated mining process, and this is very important to interesting property and the serviceability that guarantees the excavation result.Yet problem is that digger's experience preference often shows as a kind of intuition, is a kind of understanding by thinking, thing beyond description.How the difficult problem that this preference is the past most systems is expressed on quantification ground, generally takes the preset parameter method to set up based on certain hypothesis, even avoids this problem fully.Native system has adopted, and visual-answer techniques is obtained user experience and preference information.Both reduced the given randomness of parameter, make its more accurately, meet the true experience requirement of user, the convenience of not losing operation simultaneously again is with quick.
(4) embed exclusive digging technology.System has also comprised the up-to-date digging technology achievement that the inventor is obtained under study for action except the master data digging technology that comprises many present comparative maturities.As TSEOPM, i.e. " time series events sign mode excavation method " (Time SeriesEvent Omen Pattern Mining).Can from time series, seek to sequence pattern---the sign pattern of interested incident with predicting function.
Description of drawings
Fig. 1 system hardware structure figure
Fig. 2 system software functional structure chart
Fig. 3 system logic hierarchical chart
Fig. 4 system applies tupe figure
Fig. 5 mining algorithm object building block
Visual-the conversational mode of Fig. 6 sequence similarity preference is obtained
Fig. 7 initial public offering valency predicted data Excel file
Fig. 8 data source management main operation interface
Fig. 9 data importing interface
Figure 10 algorithms library is managed main interface
Figure 11 application model library management master interface
Figure 12 application model definition interfaces
Embodiment
Referring to Fig. 1, aid excavating analysis system of financial risk management is based on LAN (Local Area Network) 01, adopt distributed frame, comprising: a data management server 1, a Management Controller 2, excavate processing server 3, an above model application server 4 and an input/output terminal 5.Referring to Fig. 2, in system and device, include corresponding software system, comprising: run on total control subsystem 6 on the Management Controller, run on data administration subsystem 7 on the data management server, run on the mining algorithm ADMINISTRATION SUBSYSTEM 8 excavated on the processing server, run on excavation application model ADMINISTRATION SUBSYSTEM 9 and rule knowledge ADMINISTRATION SUBSYSTEM 10 on the Management Controller, run on risk identification and Monitor And Control Subsystem 11 on the application server.Wherein, data administration subsystem 7 comprises data acquisition and modular converter 12, data preprocessing function module 13, data source administration module 14; Excavate application model ADMINISTRATION SUBSYSTEM 9, comprise confluence analysis 15, interest rate mining analysis 16, share price mining analysis 17, exchange rate mining analysis 18 and credit mining analysis 19 several sections; Risk identification and Monitor And Control Subsystem 11 comprise that monitoring data collection 20, monitoring rule safeguard 21, monitor message is issued 22 3 functional modules.
Referring to Fig. 3, total system can be divided four layer architectures by functional hierarchy, i.e. data Layer 23, mining algorithm layer 24, excavation application model layer 25 and application layer 26.Data Layer 23 comprises various OLE DB databases, excel file, text, XML etc.; Mining algorithm layer 24 comprises classification, cluster, association analysis, time series analysis algorithm, unusual excavation, neural network, SVM, recurrence etc.; Excavate application model layer 25 and comprise the credit analysis model, interest rate analytical model, share price analytical model, confluence analysis model and other model; Application layer 26 comprises rule application, risk identification, monitoring.
The principle of work of system of the present invention
In conjunction with Fig. 1, as shown in Figure 4.At first utilize Management Controller 2, log-on data management server 1 utilizes metadata acquisition tool 28 to gather from Data Source network 02 and excavates training data 27; And pass through suitable conversion and pre-service as required, standard, arrangement form excavates object data, and deposits in the mining data storehouse 29 in; By Management Controller 2, select suitable Data Mining Tools 32 then, the logical process model is excavated in definition, start and excavate processing server 3, the excavation engine that excavates processing server 3 calls assignment algorithm, and call specific data from mining data storehouse 29 according to the instruction of excavating the logical process model from the mining algorithm storehouse, it is excavated calculating, excavate the result and deposit rule-based knowledge base 33 in; By Management Controller 2, utilize rule and model in the rule-based knowledge base 33, make up and excavate application model, application model is embedded in the application server 4, start application server 4, application server 4 utilizes metadata acquisition tool 30 to call real time data 31 from data management server 1, by calculating, matched rule knowledge is utilized risk identification to combine other quantification financial risk management technology with monitoring tools 34 and is provided the risk management decision information.
System is in order to realize the continuous expansion of digging technology and algorithm, and native system has adopted Open architecture shown in Figure 5 on algorithm management, and mining algorithm 35 is structures of being made up of arthmetic statement 36, algorithm parameter 37 and algorithm run time version 38 trinity.Arthmetic statement adopts database storing, and algorithm parameter adopts the file mode storage, and the algorithm run time version is with the form storage of independent dynamic link library.Thereby guarantee that fully input, output parameter form, number have nothing in common with each other, the compatibility each other of the mining algorithm that function is different, unified management, and its maintenance cost is lower, simple operation.Arthmetic statement comprises the following critical data item, guarantees the unified management to algorithm:
The algorithm code name
The algorithm title
Class of algorithms alias
Algorithm function is described
The algorithm parameter file
The algorithm dll file
Algorithm is set up the date
The user
Associated application model record number
Associated application chain of model pointer
The algorithm parameter file description the required I/O parameter classification of mining algorithm, number of parameters, default parameters.Owing to adopt the document form storage, thereby its dirigibility is stronger than adopting the storage of database form.
In the management of excavating application model, realize excavating the definition of processing logic by application model definitional language MDL.An application model comprises data source, data preparation logic, mining algorithm three big key elements, constitutes a processing logic jointly.Can specify data source, the data field that will excavate flexibly by the MDL language, before calling concrete mining algorithm, the special processing that will carry out some field and conversion, processing procedure, interim memory location etc.The MDL language has comprised excavation processing logic necessary operations key element commonly used and handling function.
Native system adopts visual way to obtain the user experience parameter, its ultimate principle is such: pass through visual way, raise a series of problems to the user, the user carries out a series of judgement according to the preference of oneself to the figure that provides and selects, final system adopts evaluation model to calculate user's preference coefficient, obtains user preference.As shown in Figure 6, be one and obtain the user judges the preference parameter to Time Series Similarity example.By the user a series of similaritys of two picture groups are up and down judged, provided the judgement conclusion.These a series of judged results of system make up following equation of constraint group, the match user preference, and information gets parms:
min(f(X′，Y′)-θ)
2
Each equation of constraint g
iThe expression judgement that the user did is selected.For example, if the user judges that top sequence is more similar, then get g
i〉=0, and sequence is more similar below judging, then gets g
i≤ 0.Final system calculates the similarity measure parameter of its preference of reflection and experience by this constrained optimization problem of genetic algorithm for solving.
Excavate the application mode that the instantiation of predicting is introduced native system below by setting up an initial public offering valency.
Theoretical according to relevant finance, the factor that influences share price comprises political factor, macroeconomy situations such as economic cycle, inflation, interest rate, the exchange rate, fiscal and monetary policy, the life cycle factor of industry, the financial position of listed company itself, the aspiration level in market, the supply and demand situation of one-level secondary market fund, the prosperous situation of neighboring markets etc.Here we select indexs such as preceding capital stock, new number of share of stock, issue price, net value, stock index, achievement, p/e ratio, HSBC to predict the market price of initial public offering.If having put in order, data are put in the middle of the EXCEL file, as shown in Figure 7.Add the data source button at data source administration interface mid point shown in Figure 8, in the interface of importing as shown in Figure 9 that occurs subsequently, select original EXCEL file, import data and data source is set for information about, as data source name " new stock market price data source ".In algorithms library, system the is built-in general algorithm of BP neural network model is as Figure 10.In model management view shown in Figure 11,, define new application model by model maintenance.Input for information about in model definition interface shown in Figure 12, comprise model name, classification, data source, algorithm, and in the processing logic frame, provide concrete disposal route information by complying with embedded MDL language, and such as the assignment of each required parameter of algorithm, output form, outgoing position etc.Promptly set up a new application model after " determining ".Move this model, the algorithm of system call appointment, and the regulation reading of data source data of pressing processing logic, and corresponding with parameter information in the algorithm parameter message file, parameter is set, after the operation algorithm finishes, according to the regulation of processing logic, the result deposits assigned address in.
Claims (6)
1, a kind of aid excavating analysis system of financial risk management, based on LAN (Local Area Network), adopt distributed frame, it is characterized in that comprising: a data management server, be used to realize collection, storage, pre-service and the search function of data, excavate basic data and use raw data for total system provides, need as the case may be, it links to each other with other Service Database server with Internet; One Management Controller is used for providing operating platform to the user, realizes that data management, excavation, rule knowledge are safeguarded, application model is set up and the issue of safeguarding control command of model application; One excavates processing server, is used to accept the mining task of Management Controller, calls digging tool, excavates the generation knowledge rule on the mining data collection of appointment; An above model application server comprises corresponding Message Display Terminal, utilizes the knowledge architecture application model of excavating, and constitutes the monitoring tools monitoring and analyze real-time image data, and risk and decision information are provided; And input/output terminal; Include corresponding software system in the system and device.
2, aid excavating analysis system of financial risk management according to claim 1 is characterized in that described software systems, comprising:
One total control subsystem comprises system operation framework interface, systematic parameter maintenance etc., runs on the Management Controller, and by the message exchange of computer network realization with other server, the realization of other server capability is controlled in issue an order;
One data administration subsystem runs on the data management server, is used for the data integration with various numerous and complicated, guarantees the availability and the validity of data, for data mining provides clear, standard, accordant interface;
One mining algorithm ADMINISTRATION SUBSYSTEM runs on and excavates on the processing server, comprises an algorithms library, is used for definition, retrieval, upgrades the master data mining algorithm;
One excavates the application model ADMINISTRATION SUBSYSTEM, runs on the Management Controller, comprises an application model storehouse, be used to realize application model definition, check, delete and start;
One rule knowledge ADMINISTRATION SUBSYSTEM runs on the Management Controller, be used for to the rule knowledge of having excavated inquire about, add, maintenance management such as deletion, also comprise according to the effect feedback information of practical application rule knowledge suitably adjusted;
One risk identification and Monitor And Control Subsystem run on the application server.It utilizes mining rule knowledge, monitors the real time data of gathering, and the decision information of risk management is provided.
3, aid excavating analysis system of financial risk management according to claim 2, it is characterized in that data administration subsystem comprises data acquisition and modular converter, data preprocessing function module, data source administration module, wherein data acquisition and modular converter are used for obtaining data message from the data source of different-format; Data preprocessing function module is used to solve the vacancy of data, imperfect, inconsistent and noise smoothing; The data source administration module is used for definition, retrieval, upgrades mining data source and monitor data source.
4, aid excavating analysis system of financial risk management according to claim 2 is characterized in that the mining algorithm ADMINISTRATION SUBSYSTEM has preset following basic digging technology, mainly comprises:
Sorting technique: comprise decision tree ID3 algorithm, C4.5 algorithm, CART algorithm, SLIQ algorithm, SVM;
Clustering technique: comprise hierarchical cluster method, cut apart clustering algorithm PAM, CLARA algorithm, k-means, k-modes clustering algorithm based on bee-line, longest distance and intermediate distance;
The association analysis technology: comprise the Apriori algorithm, the MAQA algorithm of multi-valued attribute is based on the association algorithm of common mechanism;
Techniques of teime series analysis: comprise ARMA, ARCH, GARCH, TSEOPM algorithm;
Nerual network technique: comprise the BP network, Elaman network and Hopfield network.
5, aid excavating analysis system of financial risk management according to claim 2, the application model that it is characterized in that excavating in the application model storehouse of application model ADMINISTRATION SUBSYSTEM specifically is divided into credit mining analysis, interest rate mining analysis, exchange rate mining analysis, share price mining analysis and confluence analysis several sections.
6, aid excavating analysis system of financial risk management according to claim 2 is characterized in that risk identification and Monitor And Control Subsystem comprise that monitoring data collection, monitoring rule are safeguarded, three functional modules of monitor message issue.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNA2006100312193A CN1967579A (en) | 2006-02-13 | 2006-02-13 | Aid excavating analysis system of financial risk management |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNA2006100312193A CN1967579A (en) | 2006-02-13 | 2006-02-13 | Aid excavating analysis system of financial risk management |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN1967579A true CN1967579A (en) | 2007-05-23 |
Family
ID=38076336
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNA2006100312193A Pending CN1967579A (en) | 2006-02-13 | 2006-02-13 | Aid excavating analysis system of financial risk management |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN1967579A (en) |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102012918A (en) * | 2010-11-26 | 2011-04-13 | 中金金融认证中心有限公司 | System and method for excavating and executing rule |
| CN102446298A (en) * | 2010-10-15 | 2012-05-09 | 东方钢铁电子商务有限公司 | Information monitoring and evaluating device and method for purchasing system |
| CN102521925A (en) * | 2011-12-08 | 2012-06-27 | 中国工商银行股份有限公司 | Load balancing method and system of bank terminal device |
| CN102779316A (en) * | 2011-05-12 | 2012-11-14 | 株式会社东芝 | Information processing system and method |
| CN102968743A (en) * | 2012-10-29 | 2013-03-13 | 上海大智慧股份有限公司 | Sector rotation data processing system |
| CN103123712A (en) * | 2011-11-17 | 2013-05-29 | 阿里巴巴集团控股有限公司 | Method and system for monitoring network behavior data |
| CN103377223A (en) * | 2012-04-24 | 2013-10-30 | 深圳信息职业技术学院 | School information base management method and system |
| CN103854221A (en) * | 2012-11-28 | 2014-06-11 | 深圳市普路通供应链管理股份有限公司 | Financial storm early warning method and system based on multi-agent |
| CN104052614A (en) * | 2013-03-15 | 2014-09-17 | 南京理工大学常熟研究院有限公司 | Operation maintenance management system for social public safety video information perception platform |
| CN104376397A (en) * | 2014-10-15 | 2015-02-25 | 中国农业银行股份有限公司 | Data real-time analysis method and device |
| WO2015196397A1 (en) * | 2014-06-25 | 2015-12-30 | 北京百付宝科技有限公司 | Method and device for data mining based on user's search behaviour |
| CN105354198A (en) * | 2014-08-19 | 2016-02-24 | 中国移动通信集团湖北有限公司 | Data processing method and apparatus |
| CN106294847A (en) * | 2016-08-22 | 2017-01-04 | 成都天地网络科技有限公司 | Business operation system based on data mining |
| CN106484884A (en) * | 2016-10-18 | 2017-03-08 | 安徽天达网络科技有限公司 | A kind of data handling system |
| CN107025509A (en) * | 2016-02-01 | 2017-08-08 | 腾讯科技（深圳）有限公司 | Decision system and method based on business model |
| CN107578193A (en) * | 2017-10-12 | 2018-01-12 | 国家计算机网络与信息安全管理中心 | Internet Financial Risk Analysis visualizes system |
| CN108038228A (en) * | 2017-12-25 | 2018-05-15 | 佛山市车品匠汽车用品有限公司 | A kind of method for digging and device based on database |
| CN108194143A (en) * | 2017-12-25 | 2018-06-22 | 陕西煤业化工技术研究院有限责任公司 | Masonry beam DEFORMATION MONITORING SYSTEM and monitoring and pre-alarming method based on Hopfield neural networks |
| CN108229563A (en) * | 2018-01-04 | 2018-06-29 | 众安信息技术服务有限公司 | A kind of treasury bond futures actively do city's system |
| CN108984748A (en) * | 2018-07-17 | 2018-12-11 | 商丘师范学院 | A kind of Financial Information statistic management system |
| CN109241179A (en) * | 2018-08-01 | 2019-01-18 | 协同数据技术（深圳）有限公司 | Data administering method, system and computer equipment based on data space |
| CN109840844A (en) * | 2017-11-27 | 2019-06-04 | 上海仪电（集团）有限公司中央研究院 | A kind of financial big data acquisition processing device and system based on FPGA |
| CN114817681A (en) * | 2022-04-28 | 2022-07-29 | 北京辰行科技有限公司 | Financial wind control system based on big data analysis and management equipment thereof |
-
2006
- 2006-02-13 CN CNA2006100312193A patent/CN1967579A/en active Pending
Cited By (31)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102446298A (en) * | 2010-10-15 | 2012-05-09 | 东方钢铁电子商务有限公司 | Information monitoring and evaluating device and method for purchasing system |
| CN102012918A (en) * | 2010-11-26 | 2011-04-13 | 中金金融认证中心有限公司 | System and method for excavating and executing rule |
| CN102012918B (en) * | 2010-11-26 | 2012-11-21 | 中金金融认证中心有限公司 | System and method for excavating and executing rule |
| CN102779316A (en) * | 2011-05-12 | 2012-11-14 | 株式会社东芝 | Information processing system and method |
| CN107103548A (en) * | 2011-11-17 | 2017-08-29 | 阿里巴巴集团控股有限公司 | The monitoring method and system and risk monitoring and control method and system of network behavior data |
| CN103123712A (en) * | 2011-11-17 | 2013-05-29 | 阿里巴巴集团控股有限公司 | Method and system for monitoring network behavior data |
| CN102521925A (en) * | 2011-12-08 | 2012-06-27 | 中国工商银行股份有限公司 | Load balancing method and system of bank terminal device |
| CN102521925B (en) * | 2011-12-08 | 2013-10-23 | 中国工商银行股份有限公司 | Load balancing method and system of bank terminal device |
| CN103377223B (en) * | 2012-04-24 | 2016-08-10 | 深圳信息职业技术学院 | The management method of school information base and system |
| CN103377223A (en) * | 2012-04-24 | 2013-10-30 | 深圳信息职业技术学院 | School information base management method and system |
| CN102968743A (en) * | 2012-10-29 | 2013-03-13 | 上海大智慧股份有限公司 | Sector rotation data processing system |
| CN103854221A (en) * | 2012-11-28 | 2014-06-11 | 深圳市普路通供应链管理股份有限公司 | Financial storm early warning method and system based on multi-agent |
| CN104052614A (en) * | 2013-03-15 | 2014-09-17 | 南京理工大学常熟研究院有限公司 | Operation maintenance management system for social public safety video information perception platform |
| WO2015196397A1 (en) * | 2014-06-25 | 2015-12-30 | 北京百付宝科技有限公司 | Method and device for data mining based on user's search behaviour |
| US10896461B2 (en) | 2014-06-25 | 2021-01-19 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method and apparatus for data mining based on users' search behavior |
| CN105354198A (en) * | 2014-08-19 | 2016-02-24 | 中国移动通信集团湖北有限公司 | Data processing method and apparatus |
| CN104376397B (en) * | 2014-10-15 | 2018-07-06 | 中国农业银行股份有限公司 | A kind of data real-time analysis method and device |
| CN104376397A (en) * | 2014-10-15 | 2015-02-25 | 中国农业银行股份有限公司 | Data real-time analysis method and device |
| CN107025509A (en) * | 2016-02-01 | 2017-08-08 | 腾讯科技（深圳）有限公司 | Decision system and method based on business model |
| CN107025509B (en) * | 2016-02-01 | 2021-06-18 | 腾讯科技（深圳）有限公司 | Decision making system and method based on business model |
| CN106294847A (en) * | 2016-08-22 | 2017-01-04 | 成都天地网络科技有限公司 | Business operation system based on data mining |
| CN106484884A (en) * | 2016-10-18 | 2017-03-08 | 安徽天达网络科技有限公司 | A kind of data handling system |
| CN107578193A (en) * | 2017-10-12 | 2018-01-12 | 国家计算机网络与信息安全管理中心 | Internet Financial Risk Analysis visualizes system |
| CN109840844A (en) * | 2017-11-27 | 2019-06-04 | 上海仪电（集团）有限公司中央研究院 | A kind of financial big data acquisition processing device and system based on FPGA |
| CN109840844B (en) * | 2017-11-27 | 2023-12-22 | 上海仪电（集团）有限公司中央研究院 | Financial big data acquisition processing device and system based on FPGA |
| CN108194143A (en) * | 2017-12-25 | 2018-06-22 | 陕西煤业化工技术研究院有限责任公司 | Masonry beam DEFORMATION MONITORING SYSTEM and monitoring and pre-alarming method based on Hopfield neural networks |
| CN108038228A (en) * | 2017-12-25 | 2018-05-15 | 佛山市车品匠汽车用品有限公司 | A kind of method for digging and device based on database |
| CN108229563A (en) * | 2018-01-04 | 2018-06-29 | 众安信息技术服务有限公司 | A kind of treasury bond futures actively do city's system |
| CN108984748A (en) * | 2018-07-17 | 2018-12-11 | 商丘师范学院 | A kind of Financial Information statistic management system |
| CN109241179A (en) * | 2018-08-01 | 2019-01-18 | 协同数据技术（深圳）有限公司 | Data administering method, system and computer equipment based on data space |
| CN114817681A (en) * | 2022-04-28 | 2022-07-29 | 北京辰行科技有限公司 | Financial wind control system based on big data analysis and management equipment thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN1967579A (en) | Aid excavating analysis system of financial risk management | |
| US8751273B2 (en) | Predictor variable selection and dimensionality reduction for a predictive model | |
| US7725300B2 (en) | Target profiling in predictive modeling | |
| US8170841B2 (en) | Predictive model validation | |
| US7499897B2 (en) | Predictive model variable management | |
| US8165853B2 (en) | Dimension reduction in predictive model development | |
| US20140351023A1 (en) | Aggregating business analytics architecture and configurator | |
| Sentas et al. | Categorical missing data imputation for software cost estimation by multinomial logistic regression | |
| Park et al. | A data warehouse-based decision support system for sewer infrastructure management | |
| US20110112986A1 (en) | Generative Investment Method and System | |
| EP1760657A2 (en) | Methods and systems for assessing loss severity for commercial loans | |
| Senouci et al. | Multiobjective optimization model for scheduling of construction projects under extreme weather | |
| CN111080241A (en) | Internet platform-based data-based talent management analysis system | |
| CN116089495A (en) | Self-service analysis platform based on big data | |
| Aghimien et al. | A review of the application of data mining for sustainable construction in Nigeria | |
| CN1777901A (en) | Cascaded planning of an enterprise planning model | |
| Baalousha et al. | An integrated web-based data warehouse and artificial neural networks system for unit price analysis with inflation adjustment | |
| CN117522607A (en) | Enterprise financial management system | |
| Kumar et al. | Knowledge discovery from data mining techniques | |
| US20240185159A1 (en) | Systems And Methods For Identifying An Officer At Risk Of An Adverse Event | |
| Purohit et al. | Database design for data mining driven forecasting software tool for quality function deployment | |
| Turktarhan et al. | Re-architecting the firm for increased value: How business models are adapting to the new AI environment | |
| Elhadad | Insurance Business Enterprises' Intelligence in View of Big Data Analytics | |
| Zhao et al. | An integrated risk management model for construction projects | |
| Yixin et al. | Research on financial management of Guangdong-Hong Kong-macao greater Bay Area based on LS-SVM algorithm and multi-model fusion |
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: 20070523 |